{"302ai/chatgpt-4o-latest":{"id":"302ai/chatgpt-4o-latest","name":"chatgpt-4o-latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-08","last_updated":"2024-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":5,"output":15},"sourceProvider":"302ai"},"302ai/claude-3-5-haiku-20241022":{"id":"302ai/claude-3-5-haiku-20241022","name":"claude-3-5-haiku-20241022","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":0.8,"output":4},"sourceProvider":"302ai"},"302ai/claude-3-5-haiku-latest":{"id":"302ai/claude-3-5-haiku-latest","name":"claude-3-5-haiku-latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":0.8,"output":4},"sourceProvider":"302ai"},"302ai/claude-haiku-4-5":{"id":"302ai/claude-haiku-4-5","name":"claude-haiku-4-5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"sourceProvider":"302ai"},"302ai/claude-haiku-4-5-20251001":{"id":"302ai/claude-haiku-4-5-20251001","name":"claude-haiku-4-5-20251001","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"sourceProvider":"302ai"},"302ai/claude-opus-4-1-20250805":{"id":"302ai/claude-opus-4-1-20250805","name":"claude-opus-4-1-20250805","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"302ai"},"302ai/claude-opus-4-1-20250805-thinking":{"id":"302ai/claude-opus-4-1-20250805-thinking","name":"claude-opus-4-1-20250805-thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-27","last_updated":"2025-05-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"302ai"},"302ai/claude-opus-4-20250514":{"id":"302ai/claude-opus-4-20250514","name":"claude-opus-4-20250514","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"302ai"},"302ai/claude-opus-4-5":{"id":"302ai/claude-opus-4-5","name":"claude-opus-4-5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"sourceProvider":"302ai"},"302ai/claude-opus-4-5-20251101":{"id":"302ai/claude-opus-4-5-20251101","name":"claude-opus-4-5-20251101","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"sourceProvider":"302ai"},"302ai/claude-opus-4-5-20251101-thinking":{"id":"302ai/claude-opus-4-5-20251101-thinking","name":"claude-opus-4-5-20251101-thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"sourceProvider":"302ai"},"302ai/claude-opus-4-6":{"id":"302ai/claude-opus-4-6","name":"claude-opus-4-6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-06","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"302ai"},"302ai/claude-opus-4-6-thinking":{"id":"302ai/claude-opus-4-6-thinking","name":"claude-opus-4-6-thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-02-06","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"302ai"},"302ai/claude-opus-4-7":{"id":"302ai/claude-opus-4-7","name":"claude-opus-4-7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-20250514":{"id":"302ai/claude-sonnet-4-20250514","name":"claude-sonnet-4-20250514","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-5":{"id":"302ai/claude-sonnet-4-5","name":"claude-sonnet-4-5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-5-20250929":{"id":"302ai/claude-sonnet-4-5-20250929","name":"claude-sonnet-4-5-20250929","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-5-20250929-thinking":{"id":"302ai/claude-sonnet-4-5-20250929-thinking","name":"claude-sonnet-4-5-20250929-thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-6":{"id":"302ai/claude-sonnet-4-6","name":"claude-sonnet-4-6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-18","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/claude-sonnet-4-6-thinking":{"id":"302ai/claude-sonnet-4-6-thinking","name":"claude-sonnet-4-6-thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-18","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"302ai"},"302ai/deepseek-chat":{"id":"302ai/deepseek-chat","name":"Deepseek-Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-11-29","last_updated":"2024-11-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.29,"output":0.43},"sourceProvider":"302ai"},"302ai/deepseek-reasoner":{"id":"302ai/deepseek-reasoner","name":"Deepseek-Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.29,"output":0.43},"sourceProvider":"302ai"},"302ai/deepseek-v3.2":{"id":"302ai/deepseek-v3.2","name":"deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.29,"output":0.43},"sourceProvider":"302ai"},"302ai/deepseek-v3.2-thinking":{"id":"302ai/deepseek-v3.2-thinking","name":"DeepSeek-V3.2-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.29,"output":0.43},"sourceProvider":"302ai"},"302ai/doubao-seed-1-6-thinking-250715":{"id":"302ai/doubao-seed-1-6-thinking-250715","name":"doubao-seed-1-6-thinking-250715","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16000},"cost":{"input":0.121,"output":1.21},"sourceProvider":"302ai"},"302ai/doubao-seed-1-6-vision-250815":{"id":"302ai/doubao-seed-1-6-vision-250815","name":"doubao-seed-1-6-vision-250815","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.114,"output":1.143},"sourceProvider":"302ai"},"302ai/doubao-seed-1-8-251215":{"id":"302ai/doubao-seed-1-8-251215","name":"doubao-seed-1-8-251215","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":224000,"output":64000},"cost":{"input":0.114,"output":0.286},"sourceProvider":"302ai"},"302ai/doubao-seed-code-preview-251028":{"id":"302ai/doubao-seed-code-preview-251028","name":"doubao-seed-code-preview-251028","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-11","last_updated":"2025-11-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.17,"output":1.14},"sourceProvider":"302ai"},"302ai/gemini-2.0-flash-lite":{"id":"302ai/gemini-2.0-flash-lite","name":"gemini-2.0-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-11","release_date":"2025-06-16","last_updated":"2025-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":8192},"cost":{"input":0.075,"output":0.3},"sourceProvider":"302ai"},"302ai/gemini-2.5-flash":{"id":"302ai/gemini-2.5-flash","name":"gemini-2.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"sourceProvider":"302ai"},"302ai/gemini-2.5-flash-image":{"id":"302ai/gemini-2.5-flash-image","name":"gemini-2.5-flash-image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-08","last_updated":"2025-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"sourceProvider":"302ai"},"302ai/gemini-2.5-flash-lite-preview-09-2025":{"id":"302ai/gemini-2.5-flash-lite-preview-09-2025","name":"gemini-2.5-flash-lite-preview-09-2025","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4},"sourceProvider":"302ai"},"302ai/gemini-2.5-flash-nothink":{"id":"302ai/gemini-2.5-flash-nothink","name":"gemini-2.5-flash-nothink","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-24","last_updated":"2025-06-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"sourceProvider":"302ai"},"302ai/gemini-2.5-flash-preview-09-2025":{"id":"302ai/gemini-2.5-flash-preview-09-2025","name":"gemini-2.5-flash-preview-09-2025","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":2.5},"sourceProvider":"302ai"},"302ai/gemini-2.5-pro":{"id":"302ai/gemini-2.5-pro","name":"gemini-2.5-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":10},"sourceProvider":"302ai"},"302ai/gemini-3-flash-preview":{"id":"302ai/gemini-3-flash-preview","name":"gemini-3-flash-preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"302ai"},"302ai/gemini-3-pro-image-preview":{"id":"302ai/gemini-3-pro-image-preview","name":"gemini-3-pro-image-preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":64000},"cost":{"input":2,"output":120},"sourceProvider":"302ai"},"302ai/gemini-3-pro-preview":{"id":"302ai/gemini-3-pro-preview","name":"gemini-3-pro-preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12},"sourceProvider":"302ai"},"302ai/gemini-3.1-flash-image-preview":{"id":"302ai/gemini-3.1-flash-image-preview","name":"gemini-3.1-flash-image-preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":60},"sourceProvider":"302ai"},"302ai/glm-4.5":{"id":"302ai/glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.286,"output":1.142},"sourceProvider":"302ai"},"302ai/glm-4.5-air":{"id":"302ai/glm-4.5-air","name":"glm-4.5-air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.1143,"output":0.286},"sourceProvider":"302ai"},"302ai/glm-4.5-airx":{"id":"302ai/glm-4.5-airx","name":"glm-4.5-airx","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.572,"output":1.714},"sourceProvider":"302ai"},"302ai/glm-4.5-x":{"id":"302ai/glm-4.5-x","name":"glm-4.5-x","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.143,"output":2.29},"sourceProvider":"302ai"},"302ai/glm-4.5v":{"id":"302ai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.29,"output":0.86},"sourceProvider":"302ai"},"302ai/glm-4.6":{"id":"302ai/glm-4.6","name":"glm-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.286,"output":1.142},"sourceProvider":"302ai"},"302ai/glm-4.6v":{"id":"302ai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.145,"output":0.43},"sourceProvider":"302ai"},"302ai/glm-4.7":{"id":"302ai/glm-4.7","name":"glm-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.286,"output":1.142},"sourceProvider":"302ai"},"302ai/glm-4.7-flashx":{"id":"302ai/glm-4.7-flashx","name":"glm-4.7-flashx","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-20","last_updated":"2026-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.0715,"output":0.429},"sourceProvider":"302ai"},"302ai/glm-5":{"id":"302ai/glm-5","name":"glm-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.6},"sourceProvider":"302ai"},"302ai/glm-5-turbo":{"id":"302ai/glm-5-turbo","name":"glm-5-turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.72,"output":3.2},"sourceProvider":"302ai"},"302ai/glm-5.1":{"id":"302ai/glm-5.1","name":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-10","last_updated":"2026-04-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.86,"output":3.5},"sourceProvider":"302ai"},"302ai/glm-5v-turbo":{"id":"302ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.72,"output":3.2},"sourceProvider":"302ai"},"302ai/glm-for-coding":{"id":"302ai/glm-for-coding","name":"glm-for-coding","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.086,"output":0.343},"sourceProvider":"302ai"},"302ai/gpt-4.1":{"id":"302ai/gpt-4.1","name":"gpt-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8},"sourceProvider":"302ai"},"302ai/gpt-4.1-mini":{"id":"302ai/gpt-4.1-mini","name":"gpt-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6},"sourceProvider":"302ai"},"302ai/gpt-4.1-nano":{"id":"302ai/gpt-4.1-nano","name":"gpt-4.1-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4},"sourceProvider":"302ai"},"302ai/gpt-4o":{"id":"302ai/gpt-4o","name":"gpt-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"sourceProvider":"302ai"},"302ai/gpt-5":{"id":"302ai/gpt-5","name":"gpt-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"sourceProvider":"302ai"},"302ai/gpt-5-mini":{"id":"302ai/gpt-5-mini","name":"gpt-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2},"sourceProvider":"302ai"},"302ai/gpt-5-pro":{"id":"302ai/gpt-5-pro","name":"gpt-5-pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-08","last_updated":"2025-10-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"302ai"},"302ai/gpt-5-thinking":{"id":"302ai/gpt-5-thinking","name":"gpt-5-thinking","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"sourceProvider":"302ai"},"302ai/gpt-5.1":{"id":"302ai/gpt-5.1","name":"gpt-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"sourceProvider":"302ai"},"302ai/gpt-5.1-chat-latest":{"id":"302ai/gpt-5.1-chat-latest","name":"gpt-5.1-chat-latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10},"sourceProvider":"302ai"},"302ai/gpt-5.2":{"id":"302ai/gpt-5.2","name":"gpt-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"302ai"},"302ai/gpt-5.2-chat-latest":{"id":"302ai/gpt-5.2-chat-latest","name":"gpt-5.2-chat-latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14},"sourceProvider":"302ai"},"302ai/gpt-5.4":{"id":"302ai/gpt-5.4","name":"gpt-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":0,"tiers":[{"input":5,"output":22.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5}},"sourceProvider":"302ai"},"302ai/gpt-5.4-mini":{"id":"302ai/gpt-5.4-mini","name":"gpt-5.4-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5},"sourceProvider":"302ai"},"302ai/gpt-5.4-mini-2026-03-17":{"id":"302ai/gpt-5.4-mini-2026-03-17","name":"gpt-5.4-mini-2026-03-17","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5},"sourceProvider":"302ai"},"302ai/gpt-5.4-nano":{"id":"302ai/gpt-5.4-nano","name":"gpt-5.4-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25},"sourceProvider":"302ai"},"302ai/gpt-5.4-nano-2026-03-17":{"id":"302ai/gpt-5.4-nano-2026-03-17","name":"gpt-5.4-nano-2026-03-17","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25},"sourceProvider":"302ai"},"302ai/gpt-5.4-pro":{"id":"302ai/gpt-5.4-pro","name":"gpt-5.4-pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":0,"cache_write":0,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"302ai"},"302ai/grok-4-1-fast-non-reasoning":{"id":"302ai/grok-4-1-fast-non-reasoning","name":"grok-4-1-fast-non-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"302ai"},"302ai/grok-4-1-fast-reasoning":{"id":"302ai/grok-4-1-fast-reasoning","name":"grok-4-1-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"302ai"},"302ai/grok-4-fast-non-reasoning":{"id":"302ai/grok-4-fast-non-reasoning","name":"grok-4-fast-non-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"302ai"},"302ai/grok-4-fast-reasoning":{"id":"302ai/grok-4-fast-reasoning","name":"grok-4-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"302ai"},"302ai/grok-4.1":{"id":"302ai/grok-4.1","name":"grok-4.1","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":2,"output":10},"sourceProvider":"302ai"},"302ai/grok-4.20-beta-0309-non-reasoning":{"id":"302ai/grok-4.20-beta-0309-non-reasoning","name":"grok-4.20-beta-0309-non-reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6},"sourceProvider":"302ai"},"302ai/grok-4.20-beta-0309-reasoning":{"id":"302ai/grok-4.20-beta-0309-reasoning","name":"grok-4.20-beta-0309-reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6},"sourceProvider":"302ai"},"302ai/grok-4.20-multi-agent-beta-0309":{"id":"302ai/grok-4.20-multi-agent-beta-0309","name":"grok-4.20-multi-agent-beta-0309","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6},"sourceProvider":"302ai"},"302ai/kimi-k2-0905-preview":{"id":"302ai/kimi-k2-0905-preview","name":"kimi-k2-0905-preview","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.632,"output":2.53},"sourceProvider":"302ai"},"302ai/kimi-k2-thinking":{"id":"302ai/kimi-k2-thinking","name":"kimi-k2-thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.575,"output":2.3},"sourceProvider":"302ai"},"302ai/kimi-k2-thinking-turbo":{"id":"302ai/kimi-k2-thinking-turbo","name":"kimi-k2-thinking-turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.265,"output":9.119},"sourceProvider":"302ai"},"302ai/MiniMax-M1":{"id":"302ai/MiniMax-M1","name":"MiniMax-M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-16","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.132,"output":1.254},"sourceProvider":"302ai"},"302ai/MiniMax-M2":{"id":"302ai/MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-10-26","last_updated":"2025-10-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.33,"output":1.32},"sourceProvider":"302ai"},"302ai/MiniMax-M2.1":{"id":"302ai/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"302ai"},"302ai/MiniMax-M2.7":{"id":"302ai/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"302ai"},"302ai/MiniMax-M2.7-highspeed":{"id":"302ai/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":4.8},"sourceProvider":"302ai"},"302ai/ministral-14b-2512":{"id":"302ai/ministral-14b-2512","name":"ministral-14b-2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.33,"output":0.33},"sourceProvider":"302ai"},"302ai/mistral-large-2512":{"id":"302ai/mistral-large-2512","name":"mistral-large-2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":262144},"cost":{"input":1.1,"output":3.3},"sourceProvider":"302ai"},"302ai/qwen-flash":{"id":"302ai/qwen-flash","name":"Qwen-Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.022,"output":0.22},"sourceProvider":"302ai"},"302ai/qwen-max-latest":{"id":"302ai/qwen-max-latest","name":"Qwen-Max-Latest","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.343,"output":1.372},"sourceProvider":"302ai"},"302ai/qwen-plus":{"id":"302ai/qwen-plus","name":"Qwen-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.12,"output":1.2},"sourceProvider":"302ai"},"302ai/qwen3-235b-a22b":{"id":"302ai/qwen3-235b-a22b","name":"Qwen3-235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.29,"output":2.86},"sourceProvider":"302ai"},"302ai/qwen3-235b-a22b-instruct-2507":{"id":"302ai/qwen3-235b-a22b-instruct-2507","name":"qwen3-235b-a22b-instruct-2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":65536},"cost":{"input":0.29,"output":1.143},"sourceProvider":"302ai"},"302ai/qwen3-30b-a3b":{"id":"302ai/qwen3-30b-a3b","name":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.11,"output":1.08},"sourceProvider":"302ai"},"302ai/qwen3-coder-480b-a35b-instruct":{"id":"302ai/qwen3-coder-480b-a35b-instruct","name":"qwen3-coder-480b-a35b-instruct","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.86,"output":3.43},"sourceProvider":"302ai"},"302ai/qwen3-max-2025-09-23":{"id":"302ai/qwen3-max-2025-09-23","name":"qwen3-max-2025-09-23","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":258048,"output":65536},"cost":{"input":0.86,"output":3.43},"sourceProvider":"302ai"},"abacus/claude-3-7-sonnet-20250219":{"id":"abacus/claude-3-7-sonnet-20250219","name":"Claude Sonnet 3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/claude-fable-5":{"id":"abacus/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"sourceProvider":"abacus"},"abacus/claude-haiku-4-5-20251001":{"id":"abacus/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5},"sourceProvider":"abacus"},"abacus/claude-opus-4-1-20250805":{"id":"abacus/claude-opus-4-1-20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"abacus"},"abacus/claude-opus-4-20250514":{"id":"abacus/claude-opus-4-20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"abacus"},"abacus/claude-opus-4-5-20251101":{"id":"abacus/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25},"sourceProvider":"abacus"},"abacus/claude-opus-4-6":{"id":"abacus/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"abacus"},"abacus/claude-opus-4-7":{"id":"abacus/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"abacus"},"abacus/claude-opus-4-8":{"id":"abacus/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"abacus"},"abacus/claude-opus-5":{"id":"abacus/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"abacus"},"abacus/claude-sonnet-4-20250514":{"id":"abacus/claude-sonnet-4-20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/claude-sonnet-4-5-20250929":{"id":"abacus/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/claude-sonnet-4-6":{"id":"abacus/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/claude-sonnet-5":{"id":"abacus/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/deepseek-ai/DeepSeek-R1":{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":3,"output":7},"sourceProvider":"abacus"},"abacus/deepseek-ai/DeepSeek-V3.1-Terminus":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27,"output":1},"sourceProvider":"abacus"},"abacus/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-15","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.27,"output":0.4},"sourceProvider":"abacus"},"abacus/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"sourceProvider":"abacus"},"abacus/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.74,"output":3.48,"cache_read":0.15},"sourceProvider":"abacus"},"abacus/deepseek/deepseek-v3.1":{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.55,"output":1.66},"sourceProvider":"abacus"},"abacus/gemini-2.5-flash":{"id":"abacus/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"abacus"},"abacus/gemini-2.5-flash-image":{"id":"abacus/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"sourceProvider":"abacus"},"abacus/gemini-2.5-pro":{"id":"abacus/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"abacus"},"abacus/gemini-3-flash-preview":{"id":"abacus/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"abacus"},"abacus/gemini-3-pro-image":{"id":"abacus/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"abacus"},"abacus/gemini-3-pro-image-preview":{"id":"abacus/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"abacus"},"abacus/gemini-3.1-flash-image":{"id":"abacus/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"abacus"},"abacus/gemini-3.1-flash-image-preview":{"id":"abacus/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"abacus"},"abacus/gemini-3.1-flash-lite":{"id":"abacus/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"sourceProvider":"abacus"},"abacus/gemini-3.1-flash-lite-preview":{"id":"abacus/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1},"sourceProvider":"abacus"},"abacus/gemini-3.1-pro-preview":{"id":"abacus/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"abacus"},"abacus/gemini-3.5-flash":{"id":"abacus/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"abacus"},"abacus/gemini-3.5-flash-lite":{"id":"abacus/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"abacus"},"abacus/gemini-3.6-flash":{"id":"abacus/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"sourceProvider":"abacus"},"abacus/gemini-3.7-flash":{"id":"abacus/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"abacus"},"abacus/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"sourceProvider":"abacus"},"abacus/gpt-4.1":{"id":"abacus/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"abacus"},"abacus/gpt-4.1-mini":{"id":"abacus/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"abacus"},"abacus/gpt-4.1-nano":{"id":"abacus/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"abacus"},"abacus/gpt-4o":{"id":"abacus/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"abacus"},"abacus/gpt-4o-2024-11-20":{"id":"abacus/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"sourceProvider":"abacus"},"abacus/gpt-4o-mini":{"id":"abacus/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"sourceProvider":"abacus"},"abacus/gpt-5":{"id":"abacus/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"abacus"},"abacus/gpt-5-codex":{"id":"abacus/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"abacus"},"abacus/gpt-5-mini":{"id":"abacus/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"abacus"},"abacus/gpt-5-nano":{"id":"abacus/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"abacus"},"abacus/gpt-5.1":{"id":"abacus/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"abacus"},"abacus/gpt-5.1-chat-latest":{"id":"abacus/gpt-5.1-chat-latest","name":"GPT-5.1 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10},"sourceProvider":"abacus"},"abacus/gpt-5.1-codex":{"id":"abacus/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"abacus"},"abacus/gpt-5.1-codex-max":{"id":"abacus/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10},"sourceProvider":"abacus"},"abacus/gpt-5.2":{"id":"abacus/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"abacus"},"abacus/gpt-5.2-chat-latest":{"id":"abacus/gpt-5.2-chat-latest","name":"GPT-5.2 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"abacus"},"abacus/gpt-5.2-codex":{"id":"abacus/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"abacus"},"abacus/gpt-5.3-chat-latest":{"id":"abacus/gpt-5.3-chat-latest","name":"GPT-5.3 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"abacus"},"abacus/gpt-5.3-codex":{"id":"abacus/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.18},"sourceProvider":"abacus"},"abacus/gpt-5.3-codex-xhigh":{"id":"abacus/gpt-5.3-codex-xhigh","name":"GPT-5.3 Codex XHigh","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"abacus"},"abacus/gpt-5.4":{"id":"abacus/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"abacus"},"abacus/gpt-5.4-mini":{"id":"abacus/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"abacus"},"abacus/gpt-5.4-nano":{"id":"abacus/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"abacus"},"abacus/gpt-5.5":{"id":"abacus/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"abacus"},"abacus/gpt-5.6-luna":{"id":"abacus/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1},"sourceProvider":"abacus"},"abacus/gpt-5.6-sol":{"id":"abacus/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"abacus"},"abacus/gpt-5.6-terra":{"id":"abacus/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"abacus"},"abacus/grok-4-0709":{"id":"abacus/grok-4-0709","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/grok-4-1-fast-non-reasoning":{"id":"abacus/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":16384},"cost":{"input":0.2,"output":0.5},"sourceProvider":"abacus"},"abacus/grok-4-fast-non-reasoning":{"id":"abacus/grok-4-fast-non-reasoning","name":"Grok 4 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":16384},"cost":{"input":0.2,"output":0.5},"sourceProvider":"abacus"},"abacus/grok-4.3":{"id":"abacus/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"abacus"},"abacus/grok-4.5":{"id":"abacus/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32768},"cost":{"input":2,"output":6},"sourceProvider":"abacus"},"abacus/grok-4.6":{"id":"abacus/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32768},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"abacus"},"abacus/grok-code-fast-1":{"id":"abacus/grok-code-fast-1","name":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.2,"output":1.5},"sourceProvider":"abacus"},"abacus/kimi-k2-turbo-preview":{"id":"abacus/kimi-k2-turbo-preview","name":"Kimi K2 Turbo Preview","description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":0.15,"output":8},"sourceProvider":"abacus"},"abacus/kimi-k2.5":{"id":"abacus/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3},"sourceProvider":"abacus"},"abacus/llama-3.3-70b-versatile":{"id":"abacus/llama-3.3-70b-versatile","name":"Llama 3.3 70B Versatile","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.59,"output":0.79},"sourceProvider":"abacus"},"abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.14,"output":0.59},"sourceProvider":"abacus"},"abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo":{"id":"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo","name":"Llama 3.1 405B Instruct Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":3.5,"output":3.5},"sourceProvider":"abacus"},"abacus/meta-llama/Meta-Llama-3.1-8B-Instruct":{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.02,"output":0.05},"sourceProvider":"abacus"},"abacus/meta-llama/Meta-Llama-3.3-70B-Instruct":{"id":"meta-llama/Meta-Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.59,"output":0.79},"sourceProvider":"abacus"},"abacus/mimo-v2-pro":{"id":"abacus/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":3,"cache_read":0.2},"sourceProvider":"abacus"},"abacus/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"abacus"},"abacus/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"abacus"},"abacus/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"abacus"},"abacus/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"abacus"},"abacus/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"abacus"},"abacus/muse-spark-1.1":{"id":"abacus/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"abacus"},"abacus/muse-spark-1.2":{"id":"abacus/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"abacus"},"abacus/o3":{"id":"abacus/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"abacus"},"abacus/o3-mini":{"id":"abacus/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"abacus"},"abacus/o3-pro":{"id":"abacus/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":40},"sourceProvider":"abacus"},"abacus/o4-mini":{"id":"abacus/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4},"sourceProvider":"abacus"},"abacus/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.08,"output":0.44},"sourceProvider":"abacus"},"abacus/qwen-2.5-coder-32b":{"id":"abacus/qwen-2.5-coder-32b","name":"Qwen 2.5 Coder 32B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-11-11","last_updated":"2024-11-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.79,"output":0.79},"sourceProvider":"abacus"},"abacus/Qwen/Qwen2.5-72B-Instruct":{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen 2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.11,"output":0.38},"sourceProvider":"abacus"},"abacus/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.13,"output":0.6},"sourceProvider":"abacus"},"abacus/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.09,"output":0.29},"sourceProvider":"abacus"},"abacus/Qwen/Qwen3-Coder-480B-A35B-Instruct":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.29,"output":1.2},"sourceProvider":"abacus"},"abacus/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.32,"output":3.2},"sourceProvider":"abacus"},"abacus/Qwen/QwQ-32B":{"id":"Qwen/QwQ-32B","name":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2024-11-28","last_updated":"2024-11-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.4,"output":0.4},"sourceProvider":"abacus"},"abacus/qwen3-max":{"id":"abacus/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":1.2,"output":6},"sourceProvider":"abacus"},"abacus/qwen3.7-max":{"id":"abacus/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.5,"output":7.5},"sourceProvider":"abacus"},"abacus/qwen3.8-max":{"id":"abacus/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6},"sourceProvider":"abacus"},"abacus/route-llm":{"id":"abacus/route-llm","name":"RouteLLM","description":"RouteLLM routes prompts to an appropriate Abacus-backed text-generation model","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2026-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"abacus"},"abacus/thinkingmachines/Inkling":{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":3.74,"output":9.36,"cache_read":0.748},"sourceProvider":"abacus"},"abacus/zai-org/GLM-4.5":{"id":"zai-org/GLM-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":96000},"cost":{"input":0.6,"output":2.2},"sourceProvider":"abacus"},"abacus/zai-org/GLM-4.6":{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2},"sourceProvider":"abacus"},"abacus/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2},"sourceProvider":"abacus"},"abacus/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2},"sourceProvider":"abacus"},"abacus/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"abacus"},"abacus/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"abacus"},"abliteration-ai/abliterated-model":{"id":"abliteration-ai/abliterated-model","name":"Abliterated Model","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01-06","last_updated":"2026-07-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":150000,"input":150000,"output":8192},"cost":{"input":3,"output":3,"cache_read":0.3},"sourceProvider":"abliteration-ai"},"abliteration-ai/abliterated-model-large":{"id":"abliteration-ai/abliterated-model-large","name":"Abliterated Model Large","description":"GLM-5.2 model abliterated and finetuned for cyber, ML red teaming, and agent testing","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]},{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-25","last_updated":"2026-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":999990},"cost":{"input":5,"output":5,"cache_read":0.5},"sourceProvider":"abliteration-ai"},"ai-router/gpt-5.4":{"id":"ai-router/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"ai-router"},"ai-router/gpt-5.5":{"id":"ai-router/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"ai-router"},"ai-router/gpt-5.6-luna":{"id":"ai-router/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"ai-router"},"ai-router/gpt-5.6-sol":{"id":"ai-router/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ai-router"},"ai-router/gpt-5.6-terra":{"id":"ai-router/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"ai-router"},"aiand/deepseek-ai/deepseek-v4-flash":{"id":"deepseek-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.25},"sourceProvider":"aiand"},"aiand/deepseek-ai/deepseek-v4-pro":{"id":"deepseek-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1,"output":2.5},"sourceProvider":"aiand"},"aiand/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.5},"sourceProvider":"aiand"},"aiand/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":3.5},"sourceProvider":"aiand"},"aiand/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":12.5,"cache_read":0.5},"sourceProvider":"aiand"},"aiand/motif-technologies/motif-3":{"id":"motif-technologies/motif-3","name":"Motif 3","description":"Motif 3 is a large-scale, decoder-only Mixture-of-Experts (MoE) language model with 314 billion total parameters and 13.2 billion parameters activated per token.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2},"sourceProvider":"aiand"},"aiand/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"aiand"},"aiand/qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.32,"output":3.2},"sourceProvider":"aiand"},"aiand/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":4},"sourceProvider":"aiand"},"aihubmix/alicloud-deepseek-v4-flash":{"id":"aihubmix/alicloud-deepseek-v4-flash","name":"DeepSeek V4 Flash (Alibaba Cloud)","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"aihubmix"},"aihubmix/alicloud-deepseek-v4-pro":{"id":"aihubmix/alicloud-deepseek-v4-pro","name":"DeepSeek V4 Pro (Alibaba Cloud)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.69,"output":3.38,"cache_read":0.13},"sourceProvider":"aihubmix"},"aihubmix/alicloud-glm-5.1":{"id":"aihubmix/alicloud-glm-5.1","name":"GLM-5.1 (Alibaba Cloud)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.84,"output":3.38,"cache_read":0.169,"cache_write":1.05625},"sourceProvider":"aihubmix"},"aihubmix/claude-fable-5":{"id":"aihubmix/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-6":{"id":"aihubmix/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-6-think":{"id":"aihubmix/claude-opus-4-6-think","name":"Claude Opus 4.6 Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-7":{"id":"aihubmix/claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-7-think":{"id":"aihubmix/claude-opus-4-7-think","name":"Claude Opus 4.7 Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-8":{"id":"aihubmix/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-4-8-think":{"id":"aihubmix/claude-opus-4-8-think","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"aihubmix"},"aihubmix/claude-opus-5":{"id":"aihubmix/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"aihubmix"},"aihubmix/claude-sonnet-4-6":{"id":"aihubmix/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-sonnet-4-6-think":{"id":"aihubmix/claude-sonnet-4-6-think","name":"Claude Sonnet 4.6 Thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"aihubmix"},"aihubmix/claude-sonnet-5":{"id":"aihubmix/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"aihubmix"},"aihubmix/coding-glm-5.1":{"id":"aihubmix/coding-glm-5.1","name":"Coding GLM 5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-11","last_updated":"2026-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.06,"output":0.22,"cache_read":0.013},"sourceProvider":"aihubmix"},"aihubmix/coding-glm-5.1-free":{"id":"aihubmix/coding-glm-5.1-free","name":"Coding GLM 5.1 (free)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-11","last_updated":"2026-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"aihubmix"},"aihubmix/coding-minimax-m2.7":{"id":"aihubmix/coding-minimax-m2.7","name":"Coding MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128100},"cost":{"input":0.2,"output":0.2},"sourceProvider":"aihubmix"},"aihubmix/coding-minimax-m2.7-free":{"id":"aihubmix/coding-minimax-m2.7-free","name":"Coding MiniMax M2.7 (Free)","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128100},"cost":{"input":0,"output":0},"sourceProvider":"aihubmix"},"aihubmix/coding-minimax-m2.7-highspeed":{"id":"aihubmix/coding-minimax-m2.7-highspeed","name":"Coding MiniMax M2.7 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128100},"cost":{"input":0.2,"output":0.2},"sourceProvider":"aihubmix"},"aihubmix/coding-xiaomi-mimo-v2.5":{"id":"aihubmix/coding-xiaomi-mimo-v2.5","name":"Coding Xiaomi MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.08,"output":0.4,"cache_read":0.016,"tiers":[{"input":0.16,"output":0.8,"cache_read":0.032,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.16,"output":0.8,"cache_read":0.032}},"sourceProvider":"aihubmix"},"aihubmix/coding-xiaomi-mimo-v2.5-pro":{"id":"aihubmix/coding-xiaomi-mimo-v2.5-pro","name":"Coding Xiaomi MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.2,"output":0.6,"cache_read":0.04,"tiers":[{"input":0.4,"output":1.2,"cache_read":0.08,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.4,"output":1.2,"cache_read":0.08}},"sourceProvider":"aihubmix"},"aihubmix/deep-deepseek-v4-flash":{"id":"aihubmix/deep-deepseek-v4-flash","name":"DeepSeek V4 Flash (DeepSeek)","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.154,"output":0.308,"cache_read":0.0308},"sourceProvider":"aihubmix"},"aihubmix/deep-deepseek-v4-pro":{"id":"aihubmix/deep-deepseek-v4-pro","name":"DeepSeek V4 Pro (DeepSeek)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.478,"output":0.956,"cache_read":0.004302},"sourceProvider":"aihubmix"},"aihubmix/doubao-seed-2-0-code-preview":{"id":"aihubmix/doubao-seed-2-0-code-preview","name":"Doubao Seed 2.0 Code Preview","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.48,"output":2.41,"cache_read":0.09644,"tiers":[{"input":0.72,"output":3.62,"cache_read":0.144656,"tier":{"type":"context","size":32000}},{"input":1.45,"output":7.23,"cache_read":0.28932,"tier":{"type":"context","size":128000}}]},"sourceProvider":"aihubmix"},"aihubmix/doubao-seed-2-0-lite-260428":{"id":"aihubmix/doubao-seed-2-0-lite-260428","name":"Doubao Seed 2.0 Lite 260428","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.08,"output":0.51,"cache_read":0.01692,"input_audio":1.269,"tiers":[{"input":0.13,"output":0.76,"cache_read":0.02536,"input_audio":1.902,"tier":{"type":"context","size":32000}},{"input":0.25,"output":1.52,"cache_read":0.05072,"input_audio":3.804,"tier":{"type":"context","size":128000}}]},"sourceProvider":"aihubmix"},"aihubmix/doubao-seed-2-0-mini-260428":{"id":"aihubmix/doubao-seed-2-0-mini-260428","name":"Doubao Seed 2.0 Mini 260428","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.03,"output":0.28,"cache_read":0.00564,"input_audio":0.423,"tiers":[{"input":0.06,"output":0.56,"cache_read":0.01128,"input_audio":0.846,"tier":{"type":"context","size":32000}},{"input":0.11,"output":1.13,"cache_read":0.02256,"input_audio":1.692,"tier":{"type":"context","size":128000}}]},"sourceProvider":"aihubmix"},"aihubmix/doubao-seed-2-0-pro":{"id":"aihubmix/doubao-seed-2-0-pro","name":"Doubao Seed 2.0 Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.48,"output":2.41,"cache_read":0.09644,"tiers":[{"input":0.72,"output":3.62,"cache_read":0.144656,"tier":{"type":"context","size":32000}},{"input":1.45,"output":7.23,"cache_read":0.28932,"tier":{"type":"context","size":128000}}]},"sourceProvider":"aihubmix"},"aihubmix/gemini-2.5-flash":{"id":"aihubmix/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"aihubmix"},"aihubmix/gemini-2.5-pro":{"id":"aihubmix/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"aihubmix"},"aihubmix/gemini-3-flash-preview":{"id":"aihubmix/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"tiers":[{"input":0.5,"output":3,"cache_read":0.05,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.5,"output":3,"cache_read":0.05}},"sourceProvider":"aihubmix"},"aihubmix/gemini-3.1-flash-lite":{"id":"aihubmix/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1},"sourceProvider":"aihubmix"},"aihubmix/gemini-3.1-pro-preview":{"id":"aihubmix/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"aihubmix"},"aihubmix/gemini-3.1-pro-preview-customtools":{"id":"aihubmix/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"aihubmix"},"aihubmix/gemini-3.5-flash":{"id":"aihubmix/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":1.5},"sourceProvider":"aihubmix"},"aihubmix/gemini-3.7-flash":{"id":"aihubmix/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"aihubmix"},"aihubmix/glm-5.2":{"id":"aihubmix/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.1268,"output":3.9438,"cache_read":0.2817},"sourceProvider":"aihubmix"},"aihubmix/glm-5v-turbo":{"id":"aihubmix/glm-5v-turbo","name":"GLM 5 Vision Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-09","last_updated":"2026-05-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.7042,"output":3.09848,"cache_read":0.169008},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.1":{"id":"aihubmix/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.1-codex":{"id":"aihubmix/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.1-codex-mini":{"id":"aihubmix/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.2":{"id":"aihubmix/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.2-codex":{"id":"aihubmix/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.3-codex":{"id":"aihubmix/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.4":{"id":"aihubmix/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.4-mini":{"id":"aihubmix/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.5":{"id":"aihubmix/gpt-5.5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.6-luna":{"id":"aihubmix/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.6-sol":{"id":"aihubmix/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"aihubmix"},"aihubmix/gpt-5.6-terra":{"id":"aihubmix/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"aihubmix"},"aihubmix/grok-4.3":{"id":"aihubmix/grok-4.3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"aihubmix"},"aihubmix/grok-4.5":{"id":"aihubmix/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"aihubmix"},"aihubmix/grok-build-0.1":{"id":"aihubmix/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"aihubmix"},"aihubmix/hy3-preview":{"id":"aihubmix/hy3-preview","name":"Hy3 Preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":128000},"cost":{"input":0.17,"output":0.566661,"cache_read":0.051},"sourceProvider":"aihubmix"},"aihubmix/kimi-k2.5":{"id":"aihubmix/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"aihubmix"},"aihubmix/kimi-k2.6":{"id":"aihubmix/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"aihubmix"},"aihubmix/kimi-k2.7-code":{"id":"aihubmix/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":3.9995,"cache_read":0.160835},"sourceProvider":"aihubmix"},"aihubmix/kimi-k2.7-code-highspeed":{"id":"aihubmix/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":1.9,"output":7.999,"cache_read":0.32167},"sourceProvider":"aihubmix"},"aihubmix/kimi-k3":{"id":"aihubmix/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"aihubmix"},"aihubmix/minimax-m2.7":{"id":"aihubmix/minimax-m2.7","name":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"aihubmix"},"aihubmix/qwen3.6-flash":{"id":"aihubmix/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":0.17,"output":1.01,"cache_read":0.0169,"cache_write":0.21125,"tiers":[{"input":0.68,"output":4.06,"cache_read":0.0676,"cache_write":0.845,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.68,"output":4.06,"cache_read":0.0676,"cache_write":0.845}},"sourceProvider":"aihubmix"},"aihubmix/qwen3.6-max-preview":{"id":"aihubmix/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"qwen3.6","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-09","last_updated":"2026-05-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":240000,"output":64000},"cost":{"input":1.27,"output":7.61,"cache_read":0.1268,"cache_write":1.585,"tiers":[{"input":2.11,"output":12.67,"cache_read":0.2112,"cache_write":2.64,"tier":{"type":"context","size":128000}}]},"sourceProvider":"aihubmix"},"aihubmix/qwen3.6-plus":{"id":"aihubmix/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-09","last_updated":"2026-05-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":0.28,"output":1.69,"cache_read":0.0282,"cache_write":0.3525,"tiers":[{"input":1.13,"output":6.77,"cache_read":0.1128,"cache_write":1.41,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.13,"output":6.77,"cache_read":0.1128,"cache_write":1.41}},"sourceProvider":"aihubmix"},"aihubmix/qwen3.7-max":{"id":"aihubmix/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":1.69,"output":5.07,"cache_read":0.169,"cache_write":2.1125},"sourceProvider":"aihubmix"},"aihubmix/qwen3.7-plus":{"id":"aihubmix/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":0.282,"output":1.128,"cache_read":0.0564,"cache_write":0.3525},"sourceProvider":"aihubmix"},"aihubmix/qwen3.8-max":{"id":"aihubmix/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":128000},"cost":{"input":1.69,"output":5.07,"cache_read":0.169,"cache_write":2.1125},"sourceProvider":"aihubmix"},"aihubmix/xiaomi-mimo-v2.5":{"id":"aihubmix/xiaomi-mimo-v2.5","name":"Xiaomi MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.44,"output":2.2,"cache_read":0.088,"tiers":[{"input":0.88,"output":4.4,"cache_read":0.176,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.88,"output":4.4,"cache_read":0.176}},"sourceProvider":"aihubmix"},"aihubmix/xiaomi-mimo-v2.5-free":{"id":"aihubmix/xiaomi-mimo-v2.5-free","name":"Xiaomi MiMo-V2.5 (free)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo-v2.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"aihubmix"},"aihubmix/xiaomi-mimo-v2.5-pro":{"id":"aihubmix/xiaomi-mimo-v2.5-pro","name":"Xiaomi MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.1,"output":3.3,"cache_read":0.22,"tiers":[{"input":2.2,"output":6.6,"cache_read":0.44,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2.2,"output":6.6,"cache_read":0.44}},"sourceProvider":"aihubmix"},"aihubmix/xiaomi-mimo-v2.5-pro-free":{"id":"aihubmix/xiaomi-mimo-v2.5-pro-free","name":"Xiaomi MiMo-V2.5-Pro (free)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo-v2.5-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"aihubmix"},"aihubmix/zai-glm-5.1":{"id":"aihubmix/zai-glm-5.1","name":"GLM-5.1 (Z.ai)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.845,"output":3.38,"cache_read":0.183112},"sourceProvider":"aihubmix"},"aki-io/deepseek-v4-flash-0731-284b":{"id":"aki-io/deepseek-v4-flash-0731-284b","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":81920},"cost":{"input":0.2,"output":0.5,"cache_read":0.1},"sourceProvider":"aki-io"},"aki-io/gemma4-26b":{"id":"aki-io/gemma4-26b","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.1,"output":0.5},"sourceProvider":"aki-io"},"aki-io/gpt-oss-120b":{"id":"aki-io/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.55},"sourceProvider":"aki-io"},"aki-io/kimi-k2.7-code-1100b":{"id":"aki-io/kimi-k2.7-code-1100b","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.86,"output":3,"cache_read":0.18},"sourceProvider":"aki-io"},"aki-io/mistral4-119b":{"id":"aki-io/mistral4-119b","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.2,"output":0.6},"sourceProvider":"aki-io"},"aki-io/qwen3.6-35b":{"id":"aki-io/qwen3.6-35b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.15,"output":0.5},"sourceProvider":"aki-io"},"aki-io/qwen3.8-27b":{"id":"aki-io/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":2.2,"cache_read":0.1},"sourceProvider":"aki-io"},"alibaba-cn/deepseek-r1":{"id":"alibaba-cn/deepseek-r1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.574,"output":2.294},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-0528":{"id":"alibaba-cn/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.574,"output":2.294},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-llama-70b":{"id":"alibaba-cn/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-llama-8b":{"id":"alibaba-cn/deepseek-r1-distill-llama-8b","name":"DeepSeek R1 Distill Llama 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-qwen-1-5b":{"id":"alibaba-cn/deepseek-r1-distill-qwen-1-5b","name":"DeepSeek R1 Distill Qwen 1.5B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-qwen-14b":{"id":"alibaba-cn/deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.144,"output":0.431},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-qwen-32b":{"id":"alibaba-cn/deepseek-r1-distill-qwen-32b","name":"DeepSeek R1 Distill Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-r1-distill-qwen-7b":{"id":"alibaba-cn/deepseek-r1-distill-qwen-7b","name":"DeepSeek R1 Distill Qwen 7B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.072,"output":0.144},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-v3":{"id":"alibaba-cn/deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.287,"output":1.147},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-v3-1":{"id":"alibaba-cn/deepseek-v3-1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.574,"output":1.721},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-v3-2-exp":{"id":"alibaba-cn/deepseek-v3-2-exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.287,"output":0.431},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-v4-flash":{"id":"alibaba-cn/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"alibaba-cn"},"alibaba-cn/deepseek-v4-pro":{"id":"alibaba-cn/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"alibaba-cn"},"alibaba-cn/glm-5":{"id":"alibaba-cn/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0.86,"output":3.15},"sourceProvider":"alibaba-cn"},"alibaba-cn/glm-5.1":{"id":"alibaba-cn/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.87,"output":3.48,"cache_read":0.17},"sourceProvider":"alibaba-cn"},"alibaba-cn/glm-5.2":{"id":"alibaba-cn/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.1,"output":3.851,"cache_read":0.275,"cache_write":0},"sourceProvider":"alibaba-cn"},"alibaba-cn/kimi-k2-thinking":{"id":"alibaba-cn/kimi-k2-thinking","name":"Moonshot Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.574,"output":2.294},"sourceProvider":"alibaba-cn"},"alibaba-cn/kimi-k2.5":{"id":"alibaba-cn/kimi-k2.5","name":"Moonshot Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.574,"output":2.411},"sourceProvider":"alibaba-cn"},"alibaba-cn/kimi-k2.6":{"id":"alibaba-cn/kimi-k2.6","name":"Moonshot Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.929,"output":3.858},"sourceProvider":"alibaba-cn"},"alibaba-cn/kimi/kimi-k2.5":{"id":"kimi/kimi-k2.5","name":"kimi/kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"alibaba-cn"},"alibaba-cn/MiniMax-M2.5":{"id":"alibaba-cn/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"alibaba-cn"},"alibaba-cn/MiniMax/MiniMax-M2.7":{"id":"MiniMax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"alibaba-cn"},"alibaba-cn/moonshot-kimi-k2-instruct":{"id":"alibaba-cn/moonshot-kimi-k2-instruct","name":"Moonshot Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.574,"output":2.294},"sourceProvider":"alibaba-cn"},"alibaba-cn/qvq-max":{"id":"alibaba-cn/qvq-max","name":"QVQ Max","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qvq","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":1.147,"output":4.588},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-deep-research":{"id":"alibaba-cn/qwen-deep-research","name":"Qwen Deep Research","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":7.742,"output":23.367},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-doc-turbo":{"id":"alibaba-cn/qwen-doc-turbo","name":"Qwen Doc Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.087,"output":0.144},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-flash":{"id":"alibaba-cn/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.022,"output":0.216},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-long":{"id":"alibaba-cn/qwen-long","name":"Qwen Long","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-25","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":10000000,"output":8192},"cost":{"input":0.072,"output":0.287},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-math-plus":{"id":"alibaba-cn/qwen-math-plus","name":"Qwen Math Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-08-16","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":3072},"cost":{"input":0.574,"output":1.721},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-math-turbo":{"id":"alibaba-cn/qwen-math-turbo","name":"Qwen Math Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":3072},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-max":{"id":"alibaba-cn/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.345,"output":1.377},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-mt-plus":{"id":"alibaba-cn/qwen-mt-plus","name":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.259,"output":0.775},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-mt-turbo":{"id":"alibaba-cn/qwen-mt-turbo","name":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.101,"output":0.28},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-omni-turbo":{"id":"alibaba-cn/qwen-omni-turbo","name":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.058,"output":0.23,"input_audio":3.584,"output_audio":7.168},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-omni-turbo-realtime":{"id":"alibaba-cn/qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-05-08","last_updated":"2025-05-08","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.23,"output":0.918,"input_audio":3.584,"output_audio":7.168},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-plus":{"id":"alibaba-cn/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.115,"output":0.287,"reasoning":1.147},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-plus-character":{"id":"alibaba-cn/qwen-plus-character","name":"Qwen Plus Character","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.115,"output":0.287},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-turbo":{"id":"alibaba-cn/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":16384},"cost":{"input":0.044,"output":0.087,"reasoning":0.431},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-vl-max":{"id":"alibaba-cn/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.574},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-vl-ocr":{"id":"alibaba-cn/qwen-vl-ocr","name":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-10-28","last_updated":"2025-04-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":34096,"output":4096},"cost":{"input":0.717,"output":0.717},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen-vl-plus":{"id":"alibaba-cn/qwen-vl-plus","name":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.115,"output":0.287},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-14b-instruct":{"id":"alibaba-cn/qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.431},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-32b-instruct":{"id":"alibaba-cn/qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-72b-instruct":{"id":"alibaba-cn/qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.574,"output":1.721},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-7b-instruct":{"id":"alibaba-cn/qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.072,"output":0.144},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-coder-32b-instruct":{"id":"alibaba-cn/qwen2-5-coder-32b-instruct","name":"Qwen2.5-Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11","last_updated":"2024-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-coder-7b-instruct":{"id":"alibaba-cn/qwen2-5-coder-7b-instruct","name":"Qwen2.5-Coder 7B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11","last_updated":"2024-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.287},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-math-72b-instruct":{"id":"alibaba-cn/qwen2-5-math-72b-instruct","name":"Qwen2.5-Math 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3072},"cost":{"input":0.574,"output":1.721},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-math-7b-instruct":{"id":"alibaba-cn/qwen2-5-math-7b-instruct","name":"Qwen2.5-Math 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3072},"cost":{"input":0.144,"output":0.287},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-omni-7b":{"id":"alibaba-cn/qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0.087,"output":0.345,"input_audio":5.448},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-vl-72b-instruct":{"id":"alibaba-cn/qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.294,"output":6.881},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen2-5-vl-7b-instruct":{"id":"alibaba-cn/qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.717},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-14b":{"id":"alibaba-cn/qwen3-14b","name":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.144,"output":0.574,"reasoning":1.434},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-235b-a22b":{"id":"alibaba-cn/qwen3-235b-a22b","name":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.287,"output":1.147,"reasoning":2.868},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-32b":{"id":"alibaba-cn/qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.287,"output":1.147,"reasoning":2.868},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-8b":{"id":"alibaba-cn/qwen3-8b","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.072,"output":0.287,"reasoning":0.717},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-asr-flash":{"id":"alibaba-cn/qwen3-asr-flash","name":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-04","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":0.032,"output":0.032},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-coder-30b-a3b-instruct":{"id":"alibaba-cn/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.216,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-coder-480b-a35b-instruct":{"id":"alibaba-cn/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.861,"output":3.441},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-coder-flash":{"id":"alibaba-cn/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.144,"output":0.574},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-coder-plus":{"id":"alibaba-cn/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":1,"output":5},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-max":{"id":"alibaba-cn/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.861,"output":3.441},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-next-80b-a3b-instruct":{"id":"alibaba-cn/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.144,"output":0.574},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-next-80b-a3b-thinking":{"id":"alibaba-cn/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.144,"output":1.434},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-omni-flash":{"id":"alibaba-cn/qwen3-omni-flash","name":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.058,"output":0.23,"input_audio":3.584,"output_audio":7.168},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-omni-flash-realtime":{"id":"alibaba-cn/qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.23,"output":0.918,"input_audio":3.584,"output_audio":7.168},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-vl-235b-a22b":{"id":"alibaba-cn/qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.286705,"output":1.14682,"reasoning":2.867051},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-vl-30b-a3b":{"id":"alibaba-cn/qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.108,"output":0.431,"reasoning":1.076},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3-vl-plus":{"id":"alibaba-cn/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.143353,"output":1.433525,"reasoning":4.300576},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.5-397b-a17b":{"id":"alibaba-cn/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.43,"output":2.58,"reasoning":2.58},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.5-flash":{"id":"alibaba-cn/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.172,"output":1.72,"reasoning":1.72},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.5-plus":{"id":"alibaba-cn/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.573,"output":3.44,"reasoning":3.44},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.6-flash":{"id":"alibaba-cn/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.6-max-preview":{"id":"alibaba-cn/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":245800,"output":65536},"cost":{"input":1.32,"output":7.9,"cache_read":0.132},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.6-plus":{"id":"alibaba-cn/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.7-flash":{"id":"alibaba-cn/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.02962,"output":0.1185,"cache_read":0.002962,"cache_write":0.03703,"tiers":[{"input":0.08887,"output":0.35549,"cache_read":0.008887,"cache_write":0.11109,"tier":{"type":"context","size":32000}},{"input":0.17774,"output":0.71098,"cache_read":0.017774,"cache_write":0.22218,"tier":{"type":"context","size":256000}}]},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.7-max":{"id":"alibaba-cn/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.7-plus":{"id":"alibaba-cn/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":128000}}]},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwen3.8-max":{"id":"alibaba-cn/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.77744,"output":5.33231,"cache_read":0.22218,"cache_write":2.22179},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwq-32b":{"id":"alibaba-cn/qwq-32b","name":"QwQ 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.287,"output":0.861},"sourceProvider":"alibaba-cn"},"alibaba-cn/qwq-plus":{"id":"alibaba-cn/qwq-plus","name":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.574},"sourceProvider":"alibaba-cn"},"alibaba-cn/siliconflow/deepseek-r1-0528":{"id":"siliconflow/deepseek-r1-0528","name":"siliconflow/deepseek-r1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":32768},"cost":{"input":0.5,"output":2.18},"sourceProvider":"alibaba-cn"},"alibaba-cn/siliconflow/deepseek-v3-0324":{"id":"siliconflow/deepseek-v3-0324","name":"siliconflow/deepseek-v3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":1},"sourceProvider":"alibaba-cn"},"alibaba-cn/siliconflow/deepseek-v3.1-terminus":{"id":"siliconflow/deepseek-v3.1-terminus","name":"siliconflow/deepseek-v3.1-terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":1},"sourceProvider":"alibaba-cn"},"alibaba-cn/siliconflow/deepseek-v3.2":{"id":"siliconflow/deepseek-v3.2","name":"siliconflow/deepseek-v3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.42},"sourceProvider":"alibaba-cn"},"alibaba-cn/tongyi-intent-detect-v3":{"id":"alibaba-cn/tongyi-intent-detect-v3","name":"Tongyi Intent Detect V3","description":"General-purpose chat model for instruction following, writing, and analysis","family":"yi","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1024},"cost":{"input":0.058,"output":0.144},"sourceProvider":"alibaba-cn"},"alibaba-coding-plan-cn/glm-4.7":{"id":"alibaba-coding-plan-cn/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/glm-5":{"id":"alibaba-coding-plan-cn/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/kimi-k2.5":{"id":"alibaba-coding-plan-cn/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/MiniMax-M2.5":{"id":"alibaba-coding-plan-cn/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":24576},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3-coder-next":{"id":"alibaba-coding-plan-cn/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3-coder-plus":{"id":"alibaba-coding-plan-cn/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3-max-2026-01-23":{"id":"alibaba-coding-plan-cn/qwen3-max-2026-01-23","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3.5-plus":{"id":"alibaba-coding-plan-cn/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3.6-flash":{"id":"alibaba-coding-plan-cn/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3.6-plus":{"id":"alibaba-coding-plan-cn/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3.7-max":{"id":"alibaba-coding-plan-cn/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan-cn/qwen3.7-plus":{"id":"alibaba-coding-plan-cn/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan-cn"},"alibaba-coding-plan/glm-4.7":{"id":"alibaba-coding-plan/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/glm-5":{"id":"alibaba-coding-plan/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/kimi-k2.5":{"id":"alibaba-coding-plan/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/MiniMax-M2.5":{"id":"alibaba-coding-plan/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":24576},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3-coder-next":{"id":"alibaba-coding-plan/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3-coder-plus":{"id":"alibaba-coding-plan/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3-max-2026-01-23":{"id":"alibaba-coding-plan/qwen3-max-2026-01-23","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3.5-plus":{"id":"alibaba-coding-plan/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3.6-flash":{"id":"alibaba-coding-plan/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3.6-plus":{"id":"alibaba-coding-plan/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3.7-max":{"id":"alibaba-coding-plan/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"alibaba-coding-plan"},"alibaba-coding-plan/qwen3.7-plus":{"id":"alibaba-coding-plan/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-coding-plan"},"alibaba-token-plan-cn/deepseek-v3.2":{"id":"alibaba-token-plan-cn/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-03","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/deepseek-v4-flash":{"id":"alibaba-token-plan-cn/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/deepseek-v4-flash-0731":{"id":"alibaba-token-plan-cn/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/deepseek-v4-pro":{"id":"alibaba-token-plan-cn/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/deepseek-v4-pro-0813":{"id":"alibaba-token-plan-cn/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/glm-5":{"id":"alibaba-token-plan-cn/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/glm-5.1":{"id":"alibaba-token-plan-cn/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/glm-5.2":{"id":"alibaba-token-plan-cn/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/happyhorse-1.1-i2v":{"id":"alibaba-token-plan-cn/happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/happyhorse-1.1-r2v":{"id":"alibaba-token-plan-cn/happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/happyhorse-1.1-t2v":{"id":"alibaba-token-plan-cn/happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/kimi-k2.5":{"id":"alibaba-token-plan-cn/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/kimi-k2.6":{"id":"alibaba-token-plan-cn/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/kimi-k2.7-code":{"id":"alibaba-token-plan-cn/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/MiniMax-M2.5":{"id":"alibaba-token-plan-cn/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen-image-2.0":{"id":"alibaba-token-plan-cn/qwen-image-2.0","name":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen-image-2.0-pro":{"id":"alibaba-token-plan-cn/qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.6-flash":{"id":"alibaba-token-plan-cn/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.6-plus":{"id":"alibaba-token-plan-cn/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.7-max":{"id":"alibaba-token-plan-cn/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.7-plus":{"id":"alibaba-token-plan-cn/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.8-max":{"id":"alibaba-token-plan-cn/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/qwen3.8-max-preview":{"id":"alibaba-token-plan-cn/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/wan2.7-image":{"id":"alibaba-token-plan-cn/wan2.7-image","name":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan-cn/wan2.7-image-pro":{"id":"alibaba-token-plan-cn/wan2.7-image-pro","name":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan-cn"},"alibaba-token-plan/deepseek-v3.2":{"id":"alibaba-token-plan/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-03","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/deepseek-v4-flash":{"id":"alibaba-token-plan/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/deepseek-v4-flash-0731":{"id":"alibaba-token-plan/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/deepseek-v4-pro":{"id":"alibaba-token-plan/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/deepseek-v4-pro-0813":{"id":"alibaba-token-plan/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/glm-5":{"id":"alibaba-token-plan/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/glm-5.1":{"id":"alibaba-token-plan/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/glm-5.2":{"id":"alibaba-token-plan/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/happyhorse-1.1-i2v":{"id":"alibaba-token-plan/happyhorse-1.1-i2v","name":"HappyHorse 1.1 Image-to-Video","description":"Video model for image-to-video generation","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/happyhorse-1.1-r2v":{"id":"alibaba-token-plan/happyhorse-1.1-r2v","name":"HappyHorse 1.1 Reference-to-Video","description":"Video model for reference-guided video generation","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["image","text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/happyhorse-1.1-t2v":{"id":"alibaba-token-plan/happyhorse-1.1-t2v","name":"HappyHorse 1.1 Text-to-Video","description":"Video model for prompt-driven text-to-video generation","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-17","last_updated":"2026-07-17","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/kimi-k2.5":{"id":"alibaba-token-plan/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/kimi-k2.6":{"id":"alibaba-token-plan/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/kimi-k2.7-code":{"id":"alibaba-token-plan/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/MiniMax-M2.5":{"id":"alibaba-token-plan/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":196601,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen-image-2.0":{"id":"alibaba-token-plan/qwen-image-2.0","name":"Qwen Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen-image-2.0-pro":{"id":"alibaba-token-plan/qwen-image-2.0-pro","name":"Qwen Image 2.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.6-flash":{"id":"alibaba-token-plan/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.6-plus":{"id":"alibaba-token-plan/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":131072}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.7-max":{"id":"alibaba-token-plan/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.7-plus":{"id":"alibaba-token-plan/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.8-max":{"id":"alibaba-token-plan/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/qwen3.8-max-preview":{"id":"alibaba-token-plan/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"beta","cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/wan2.7-image":{"id":"alibaba-token-plan/wan2.7-image","name":"Wan2.7 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba-token-plan/wan2.7-image-pro":{"id":"alibaba-token-plan/wan2.7-image-pro","name":"Wan2.7 Image Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"alibaba-token-plan"},"alibaba/deepseek-v4-flash-0731":{"id":"alibaba/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"sourceProvider":"alibaba"},"alibaba/glm-5.2":{"id":"alibaba/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.28,"cache_write":0},"sourceProvider":"alibaba"},"alibaba/qvq-max":{"id":"alibaba/qvq-max","name":"QVQ Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qvq","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":1.2,"output":4.8},"sourceProvider":"alibaba"},"alibaba/qwen-flash":{"id":"alibaba/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4},"sourceProvider":"alibaba"},"alibaba/qwen-max":{"id":"alibaba/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"sourceProvider":"alibaba"},"alibaba/qwen-mt-plus":{"id":"alibaba/qwen-mt-plus","name":"Qwen-MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":2.46,"output":7.37},"sourceProvider":"alibaba"},"alibaba/qwen-mt-turbo":{"id":"alibaba/qwen-mt-turbo","name":"Qwen-MT Turbo","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":8192},"cost":{"input":0.16,"output":0.49},"sourceProvider":"alibaba"},"alibaba/qwen-omni-turbo":{"id":"alibaba/qwen-omni-turbo","name":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.07,"output":0.27,"input_audio":4.44,"output_audio":8.89},"sourceProvider":"alibaba"},"alibaba/qwen-omni-turbo-realtime":{"id":"alibaba/qwen-omni-turbo-realtime","name":"Qwen-Omni Turbo Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-05-08","last_updated":"2025-05-08","modalities":{"input":["text","image","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.27,"output":1.07,"input_audio":4.44,"output_audio":8.89},"sourceProvider":"alibaba"},"alibaba/qwen-plus":{"id":"alibaba/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.2,"reasoning":4},"sourceProvider":"alibaba"},"alibaba/qwen-plus-character-ja":{"id":"alibaba/qwen-plus-character-ja","name":"Qwen Plus Character (Japanese)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":512},"cost":{"input":0.5,"output":1.4},"sourceProvider":"alibaba"},"alibaba/qwen-turbo":{"id":"alibaba/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":16384},"cost":{"input":0.05,"output":0.2,"reasoning":0.5},"sourceProvider":"alibaba"},"alibaba/qwen-vl-max":{"id":"alibaba/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":3.2},"sourceProvider":"alibaba"},"alibaba/qwen-vl-ocr":{"id":"alibaba/qwen-vl-ocr","name":"Qwen-VL OCR","description":"OCR model for extracting structured text from documents and screenshots","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-10-28","last_updated":"2025-04-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":34096,"output":4096},"cost":{"input":0.72,"output":0.72},"sourceProvider":"alibaba"},"alibaba/qwen-vl-plus":{"id":"alibaba/qwen-vl-plus","name":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.21,"output":0.63},"sourceProvider":"alibaba"},"alibaba/qwen2-5-14b-instruct":{"id":"alibaba/qwen2-5-14b-instruct","name":"Qwen2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.4},"sourceProvider":"alibaba"},"alibaba/qwen2-5-32b-instruct":{"id":"alibaba/qwen2-5-32b-instruct","name":"Qwen2.5 32B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.7,"output":2.8},"sourceProvider":"alibaba"},"alibaba/qwen2-5-72b-instruct":{"id":"alibaba/qwen2-5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":1.4,"output":5.6},"sourceProvider":"alibaba"},"alibaba/qwen2-5-7b-instruct":{"id":"alibaba/qwen2-5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.175,"output":0.7},"sourceProvider":"alibaba"},"alibaba/qwen2-5-omni-7b":{"id":"alibaba/qwen2-5-omni-7b","name":"Qwen2.5-Omni 7B","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0.1,"output":0.4,"input_audio":6.76},"sourceProvider":"alibaba"},"alibaba/qwen2-5-vl-72b-instruct":{"id":"alibaba/qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.8,"output":8.4},"sourceProvider":"alibaba"},"alibaba/qwen2-5-vl-7b-instruct":{"id":"alibaba/qwen2-5-vl-7b-instruct","name":"Qwen2.5-VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.05},"sourceProvider":"alibaba"},"alibaba/qwen3-14b":{"id":"alibaba/qwen3-14b","name":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.35,"output":1.4,"reasoning":4.2},"sourceProvider":"alibaba"},"alibaba/qwen3-235b-a22b":{"id":"alibaba/qwen3-235b-a22b","name":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"sourceProvider":"alibaba"},"alibaba/qwen3-32b":{"id":"alibaba/qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"sourceProvider":"alibaba"},"alibaba/qwen3-8b":{"id":"alibaba/qwen3-8b","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.18,"output":0.7,"reasoning":2.1},"sourceProvider":"alibaba"},"alibaba/qwen3-asr-flash":{"id":"alibaba/qwen3-asr-flash","name":"Qwen3-ASR Flash","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-04","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":0.035,"output":0.035},"sourceProvider":"alibaba"},"alibaba/qwen3-coder-30b-a3b-instruct":{"id":"alibaba/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":2.25},"sourceProvider":"alibaba"},"alibaba/qwen3-coder-480b-a35b-instruct":{"id":"alibaba/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":1.5,"output":7.5},"sourceProvider":"alibaba"},"alibaba/qwen3-coder-flash":{"id":"alibaba/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5},"sourceProvider":"alibaba"},"alibaba/qwen3-coder-plus":{"id":"alibaba/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":1,"output":5},"sourceProvider":"alibaba"},"alibaba/qwen3-livetranslate-flash-realtime":{"id":"alibaba/qwen3-livetranslate-flash-realtime","name":"Qwen3-LiveTranslate Flash Realtime","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":53248,"output":4096},"cost":{"input":10,"output":10,"input_audio":10,"output_audio":38},"sourceProvider":"alibaba"},"alibaba/qwen3-max":{"id":"alibaba/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.2,"output":6},"sourceProvider":"alibaba"},"alibaba/qwen3-next-80b-a3b-instruct":{"id":"alibaba/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":2},"sourceProvider":"alibaba"},"alibaba/qwen3-next-80b-a3b-thinking":{"id":"alibaba/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":6},"sourceProvider":"alibaba"},"alibaba/qwen3-omni-flash":{"id":"alibaba/qwen3-omni-flash","name":"Qwen3-Omni Flash","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.43,"output":1.66,"input_audio":3.81,"output_audio":15.11},"sourceProvider":"alibaba"},"alibaba/qwen3-omni-flash-realtime":{"id":"alibaba/qwen3-omni-flash-realtime","name":"Qwen3-Omni Flash Realtime","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":65536,"output":16384},"cost":{"input":0.52,"output":1.99,"input_audio":4.57,"output_audio":18.13},"sourceProvider":"alibaba"},"alibaba/qwen3-vl-235b-a22b":{"id":"alibaba/qwen3-vl-235b-a22b","name":"Qwen3-VL 235B-A22B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":2.8,"reasoning":8.4},"sourceProvider":"alibaba"},"alibaba/qwen3-vl-30b-a3b":{"id":"alibaba/qwen3-vl-30b-a3b","name":"Qwen3-VL 30B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.8,"reasoning":2.4},"sourceProvider":"alibaba"},"alibaba/qwen3-vl-plus":{"id":"alibaba/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"reasoning":4.8},"sourceProvider":"alibaba"},"alibaba/qwen3.5-122b-a10b":{"id":"alibaba/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"sourceProvider":"alibaba"},"alibaba/qwen3.5-27b":{"id":"alibaba/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"sourceProvider":"alibaba"},"alibaba/qwen3.5-35b-a3b":{"id":"alibaba/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"sourceProvider":"alibaba"},"alibaba/qwen3.5-397b-a17b":{"id":"alibaba/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"alibaba"},"alibaba/qwen3.5-plus":{"id":"alibaba/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"sourceProvider":"alibaba"},"alibaba/qwen3.6-27b":{"id":"alibaba/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"alibaba"},"alibaba/qwen3.6-35b-a3b":{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"sourceProvider":"alibaba"},"alibaba/qwen3.6-flash":{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"sourceProvider":"alibaba"},"alibaba/qwen3.6-max-preview":{"id":"alibaba/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.3,"output":7.8,"cache_read":0.13,"cache_write":1.625},"sourceProvider":"alibaba"},"alibaba/qwen3.6-plus":{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"alibaba"},"alibaba/qwen3.7-max":{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"alibaba"},"alibaba/qwen3.7-plus":{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-04","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"alibaba"},"alibaba/qwen3.8-max":{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"alibaba"},"alibaba/qwq-plus":{"id":"alibaba/qwq-plus","name":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":2.4},"sourceProvider":"alibaba"},"amazon-bedrock/amazon.nova-2-lite-v1:0":{"id":"amazon-bedrock/amazon.nova-2-lite-v1:0","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.33,"output":2.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/amazon.nova-lite-v1:0":{"id":"amazon-bedrock/amazon.nova-lite-v1:0","name":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.06,"output":0.24,"cache_read":0.015},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/amazon.nova-micro-v1:0":{"id":"amazon-bedrock/amazon.nova-micro-v1:0","name":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/amazon.nova-pro-v1:0":{"id":"amazon-bedrock/amazon.nova-pro-v1:0","name":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.8,"output":3.2,"cache_read":0.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-fable-5":{"id":"amazon-bedrock/anthropic.claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0":{"id":"amazon-bedrock/anthropic.claude-opus-4-1-20250805-v1:0","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-4-5-20251101-v1:0":{"id":"amazon-bedrock/anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-4-6-v1":{"id":"amazon-bedrock/anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-4-7":{"id":"amazon-bedrock/anthropic.claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-4-8":{"id":"amazon-bedrock/anthropic.claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-opus-5":{"id":"amazon-bedrock/anthropic.claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/anthropic.claude-sonnet-5":{"id":"amazon-bedrock/anthropic.claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/au.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (AU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-opus-4-6-v1":{"id":"amazon-bedrock/au.anthropic.claude-opus-4-6-v1","name":"AU Anthropic Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":16.5,"output":82.5,"cache_read":1.65,"cache_write":20.625},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-opus-4-8":{"id":"amazon-bedrock/au.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (AU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-opus-5":{"id":"amazon-bedrock/au.anthropic.claude-opus-5","name":"Claude Opus 5 (AU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/au.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (AU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/au.anthropic.claude-sonnet-4-6","name":"AU Anthropic Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/au.anthropic.claude-sonnet-5":{"id":"amazon-bedrock/au.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (AU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/deepseek.r1-v1:0":{"id":"amazon-bedrock/deepseek.r1-v1:0","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/deepseek.v3-v1:0":{"id":"amazon-bedrock/deepseek.v3-v1:0","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.58,"output":1.68},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/deepseek.v3.2":{"id":"amazon-bedrock/deepseek.v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.62,"output":1.85},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-fable-5":{"id":"amazon-bedrock/eu.anthropic.claude-fable-5","name":"Claude Fable 5 (EU)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/eu.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (EU)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.1,"output":5.5,"cache_read":0.11,"cache_write":1.375},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-opus-4-5-20251101-v1:0":{"id":"amazon-bedrock/eu.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (EU)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-opus-4-6-v1":{"id":"amazon-bedrock/eu.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (EU)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-opus-4-7":{"id":"amazon-bedrock/eu.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (EU)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-opus-4-8":{"id":"amazon-bedrock/eu.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (EU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-opus-5":{"id":"amazon-bedrock/eu.anthropic.claude-opus-5","name":"Claude Opus 5 (EU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5.5,"output":27.5,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/eu.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/eu.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (EU)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3.3,"output":16.5,"cache_read":0.33,"cache_write":4.125},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/eu.anthropic.claude-sonnet-5":{"id":"amazon-bedrock/eu.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (EU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.2,"output":11,"cache_read":0.22,"cache_write":2.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-fable-5":{"id":"amazon-bedrock/global.anthropic.claude-fable-5","name":"Claude Fable 5 (Global)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (Global)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0":{"id":"amazon-bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (Global)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-opus-4-6-v1":{"id":"amazon-bedrock/global.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (Global)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-opus-4-7":{"id":"amazon-bedrock/global.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (Global)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-opus-4-8":{"id":"amazon-bedrock/global.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (Global)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-opus-5":{"id":"amazon-bedrock/global.anthropic.claude-opus-5","name":"Claude Opus 5 (Global)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (Global)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/global.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Global)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.anthropic.claude-sonnet-5":{"id":"amazon-bedrock/global.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (Global)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.openai.gpt-5.6-luna":{"id":"amazon-bedrock/global.openai.gpt-5.6-luna","name":"GPT-5.6 Luna (Global)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.openai.gpt-5.6-sol":{"id":"amazon-bedrock/global.openai.gpt-5.6-sol","name":"GPT-5.6 Sol (Global)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5.5,"output":33,"cache_read":0.55,"cache_write":6.875,"tiers":[{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/global.openai.gpt-5.6-terra":{"id":"amazon-bedrock/global.openai.gpt-5.6-terra","name":"GPT-5.6 Terra (Global)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/google.gemma-3-12b-it":{"id":"amazon-bedrock/google.gemma-3-12b-it","name":"Google Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.049999999999999996,"output":0.09999999999999999},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/google.gemma-3-27b-it":{"id":"amazon-bedrock/google.gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-27","last_updated":"2025-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":8192},"cost":{"input":0.12,"output":0.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/google.gemma-3-4b-it":{"id":"amazon-bedrock/google.gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.04,"output":0.08},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/jp.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (JP)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-opus-4-7":{"id":"amazon-bedrock/jp.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (JP)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-opus-4-8":{"id":"amazon-bedrock/jp.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (JP)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-opus-5":{"id":"amazon-bedrock/jp.anthropic.claude-opus-5","name":"Claude Opus 5 (JP)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/jp.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (JP)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/jp.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (JP)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/jp.anthropic.claude-sonnet-5":{"id":"amazon-bedrock/jp.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (JP)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/meta.llama3-1-70b-instruct-v1:0":{"id":"amazon-bedrock/meta.llama3-1-70b-instruct-v1:0","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/meta.llama3-1-8b-instruct-v1:0":{"id":"amazon-bedrock/meta.llama3-1-8b-instruct-v1:0","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.22,"output":0.22},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/meta.llama3-3-70b-instruct-v1:0":{"id":"amazon-bedrock/meta.llama3-3-70b-instruct-v1:0","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.72,"output":0.72},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0":{"id":"amazon-bedrock/meta.llama4-maverick-17b-instruct-v1:0","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.24,"output":0.97},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/meta.llama4-scout-17b-instruct-v1:0":{"id":"amazon-bedrock/meta.llama4-scout-17b-instruct-v1:0","name":"Llama 4 Scout 17B Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":3500000,"output":16384},"cost":{"input":0.17,"output":0.66},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/minimax.minimax-m2":{"id":"amazon-bedrock/minimax.minimax-m2","name":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204608,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/minimax.minimax-m2.1":{"id":"amazon-bedrock/minimax.minimax-m2.1","name":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/minimax.minimax-m2.5":{"id":"amazon-bedrock/minimax.minimax-m2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":98304},"cost":{"input":0.3,"output":1.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.devstral-2-123b":{"id":"amazon-bedrock/mistral.devstral-2-123b","name":"Devstral 2 123B","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.4,"output":2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.magistral-small-2509":{"id":"amazon-bedrock/mistral.magistral-small-2509","name":"Magistral Small 1.2","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":40000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.ministral-3-14b-instruct":{"id":"amazon-bedrock/mistral.ministral-3-14b-instruct","name":"Ministral 14B 3.0","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.2,"output":0.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.ministral-3-3b-instruct":{"id":"amazon-bedrock/mistral.ministral-3-3b-instruct","name":"Ministral 3 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.1,"output":0.1},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.ministral-3-8b-instruct":{"id":"amazon-bedrock/mistral.ministral-3-8b-instruct","name":"Ministral 3 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.15,"output":0.15},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.mistral-large-3-675b-instruct":{"id":"amazon-bedrock/mistral.mistral-large-3-675b-instruct","name":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.5,"output":1.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.pixtral-large-2502-v1:0":{"id":"amazon-bedrock/mistral.pixtral-large-2502-v1:0","name":"Pixtral Large (25.02)","description":"Mistral vision-language model for image understanding and multimodal chat","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-04-08","last_updated":"2025-04-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2,"output":6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.voxtral-mini-3b-2507":{"id":"amazon-bedrock/mistral.voxtral-mini-3b-2507","name":"Voxtral Mini 3B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["audio","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.04,"output":0.04},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/mistral.voxtral-small-24b-2507":{"id":"amazon-bedrock/mistral.voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.15,"output":0.35},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/moonshot.kimi-k2-thinking":{"id":"amazon-bedrock/moonshot.kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262143,"output":16000},"cost":{"input":0.6,"output":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/moonshotai.kimi-k2.5":{"id":"amazon-bedrock/moonshotai.kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262143,"output":16000},"cost":{"input":0.6,"output":3},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/nvidia.nemotron-nano-12b-v2":{"id":"amazon-bedrock/nvidia.nemotron-nano-12b-v2","name":"NVIDIA Nemotron Nano 12B v2 VL BF16","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.2,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/nvidia.nemotron-nano-3-30b":{"id":"amazon-bedrock/nvidia.nemotron-nano-3-30b","name":"NVIDIA Nemotron Nano 3 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.06,"output":0.24},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/nvidia.nemotron-nano-9b-v2":{"id":"amazon-bedrock/nvidia.nemotron-nano-9b-v2","name":"NVIDIA Nemotron Nano 9B v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.06,"output":0.23},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/nvidia.nemotron-super-3-120b":{"id":"amazon-bedrock/nvidia.nemotron-super-3-120b","name":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.65},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-5.4":{"id":"amazon-bedrock/openai.gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.75,"output":16.5,"cache_read":0.275},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-5.5":{"id":"amazon-bedrock/openai.gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":5.5,"output":33,"cache_read":0.55},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-5.6-luna":{"id":"amazon-bedrock/openai.gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275,"tiers":[{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.44,"output":1.98,"cache_read":0.044,"cache_write":0.55}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-5.6-sol":{"id":"amazon-bedrock/openai.gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":5.5,"output":33,"cache_read":0.55,"cache_write":6.875,"tiers":[{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":11,"output":49.5,"cache_read":1.1,"cache_write":13.75}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-5.6-terra":{"id":"amazon-bedrock/openai.gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75,"tiers":[{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.4,"output":19.8,"cache_read":0.44,"cache_write":5.5}},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-120b":{"id":"amazon-bedrock/openai.gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/v1","shape":"responses"},"cost":{"input":0.15,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-120b-1:0":{"id":"amazon-bedrock/openai.gpt-oss-120b-1:0","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-20b":{"id":"amazon-bedrock/openai.gpt-oss-20b","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/v1","shape":"responses"},"cost":{"input":0.07,"output":0.3},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-20b-1:0":{"id":"amazon-bedrock/openai.gpt-oss-20b-1:0","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.3},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-safeguard-120b":{"id":"amazon-bedrock/openai.gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/openai.gpt-oss-safeguard-20b":{"id":"amazon-bedrock/openai.gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-235b-a22b-2507-v1:0":{"id":"amazon-bedrock/qwen.qwen3-235b-a22b-2507-v1:0","name":"Qwen3 235B A22B 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.22,"output":0.88},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-32b-v1:0":{"id":"amazon-bedrock/qwen.qwen3-32b-v1:0","name":"Qwen3 32B (dense)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.15,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-coder-30b-a3b-v1:0":{"id":"amazon-bedrock/qwen.qwen3-coder-30b-a3b-v1:0","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-coder-480b-a35b-v1:0":{"id":"amazon-bedrock/qwen.qwen3-coder-480b-a35b-v1:0","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-18","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.22,"output":1.8},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-coder-next":{"id":"amazon-bedrock/qwen.qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.22,"output":1.8},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-next-80b-a3b":{"id":"amazon-bedrock/qwen.qwen3-next-80b-a3b","name":"Qwen/Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.14,"output":1.4},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/qwen.qwen3-vl-235b-a22b":{"id":"amazon-bedrock/qwen.qwen3-vl-235b-a22b","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.3,"output":1.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-fable-5":{"id":"amazon-bedrock/us.anthropic.claude-fable-5","name":"Claude Fable 5 (US)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0":{"id":"amazon-bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0","name":"Claude Haiku 4.5 (US)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0":{"id":"amazon-bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0","name":"Claude Opus 4.1 (US)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0":{"id":"amazon-bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0","name":"Claude Opus 4.5 (US)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-4-6-v1":{"id":"amazon-bedrock/us.anthropic.claude-opus-4-6-v1","name":"Claude Opus 4.6 (US)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-4-7":{"id":"amazon-bedrock/us.anthropic.claude-opus-4-7","name":"Claude Opus 4.7 (US)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-4-8":{"id":"amazon-bedrock/us.anthropic.claude-opus-4-8","name":"Claude Opus 4.8 (US)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-opus-5":{"id":"amazon-bedrock/us.anthropic.claude-opus-5","name":"Claude Opus 5 (US)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0":{"id":"amazon-bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0","name":"Claude Sonnet 4.5 (US)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-sonnet-4-6":{"id":"amazon-bedrock/us.anthropic.claude-sonnet-4-6","name":"Claude Sonnet 4.6 (US)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.anthropic.claude-sonnet-5":{"id":"amazon-bedrock/us.anthropic.claude-sonnet-5","name":"Claude Sonnet 5 (US)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.deepseek.r1-v1:0":{"id":"amazon-bedrock/us.deepseek.r1-v1:0","name":"DeepSeek-R1 (US)","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0":{"id":"amazon-bedrock/us.meta.llama4-maverick-17b-instruct-v1:0","name":"Llama 4 Maverick 17B Instruct (US)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.24,"output":0.97},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0":{"id":"amazon-bedrock/us.meta.llama4-scout-17b-instruct-v1:0","name":"Llama 4 Scout 17B Instruct (US)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":3500000,"output":16384},"cost":{"input":0.17,"output":0.66},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/writer.palmyra-x4-v1:0":{"id":"amazon-bedrock/writer.palmyra-x4-v1:0","name":"Palmyra X4","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"palmyra","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":122880,"output":8192},"cost":{"input":2.5,"output":10},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/writer.palmyra-x5-v1:0":{"id":"amazon-bedrock/writer.palmyra-x5-v1:0","name":"Palmyra X5","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"palmyra","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"output":8192},"cost":{"input":0.6,"output":6},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/xai.grok-4.3":{"id":"amazon-bedrock/xai.grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-06-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/xai.grok-4.6":{"id":"amazon-bedrock/xai.grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/amazon-bedrock/mantle","api":"https://bedrock-mantle.${AWS_REGION}.api.aws/openai/v1","shape":"responses"},"cost":{"input":2.2,"output":6.6,"cache_read":0.55},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/zai.glm-4.7":{"id":"amazon-bedrock/zai.glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/zai.glm-4.7-flash":{"id":"amazon-bedrock/zai.glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4},"sourceProvider":"amazon-bedrock"},"amazon-bedrock/zai.glm-5":{"id":"amazon-bedrock/zai.glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":101376},"cost":{"input":1,"output":3.2},"sourceProvider":"amazon-bedrock"},"ambient/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":0},"sourceProvider":"ambient"},"ambient/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.08,"output":0.18,"cache_read":0.016,"cache_write":0},"sourceProvider":"ambient"},"ambient/large":{"id":"ambient/large","name":"Ambient Large","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":0.6,"output":2,"cache_read":0.15,"cache_write":0},"sourceProvider":"ambient"},"ambient/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.2,"cache_write":0},"sourceProvider":"ambient"},"ambient/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.69,"output":3.49,"cache_read":0.14,"cache_write":0},"sourceProvider":"ambient"},"ambient/stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.19,"output":1.14,"cache_read":0.03,"cache_write":0},"sourceProvider":"ambient"},"ambient/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.08,"cache_write":0},"sourceProvider":"ambient"},"ambient/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":0.6,"output":2,"cache_read":0.15,"cache_write":0},"sourceProvider":"ambient"},"ambient/zai-org/GLM-5.1-FP8":{"id":"zai-org/GLM-5.1-FP8","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0,"cache_write":0},"sourceProvider":"ambient"},"ambient/zai-org/GLM-5.2-FP8":{"id":"zai-org/GLM-5.2-FP8","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.2,"output":4.2,"cache_read":0.26,"cache_write":0},"sourceProvider":"ambient"},"amd/DeepSeek-V4-Flash":{"id":"amd/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"amd"},"anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-07","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"anthropic"},"anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"anthropic"},"anthropic/claude-haiku-4-5-20251001":{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-4-5":{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-4-5-20251101":{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-04","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-14","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"anthropic"},"anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"anthropic"},"anthropic/claude-sonnet-4-5-20250929":{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"anthropic"},"anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"anthropic"},"anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-29","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"anthropic"},"anyapi/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"anyapi"},"anyapi/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"sourceProvider":"anyapi"},"anyapi/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"sourceProvider":"anyapi"},"anyapi/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"anyapi"},"anyapi/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"sourceProvider":"anyapi"},"anyapi/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"sourceProvider":"anyapi"},"anyapi/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"sourceProvider":"anyapi"},"anyapi/deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"sourceProvider":"anyapi"},"anyapi/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"sourceProvider":"anyapi"},"anyapi/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"sourceProvider":"anyapi"},"anyapi/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"anyapi"},"anyapi/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"anyapi"},"anyapi/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"anyapi"},"anyapi/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"anyapi"},"anyapi/google/gemini-3-pro-preview":{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"anyapi"},"anyapi/mistralai/devstral-2512":{"id":"mistralai/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","sourceProvider":"anyapi"},"anyapi/mistralai/mistral-large-2512":{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"anyapi"},"anyapi/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"sourceProvider":"anyapi"},"anyapi/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"sourceProvider":"anyapi"},"anyapi/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"anyapi"},"anyapi/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"anyapi"},"anyapi/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"anyapi"},"anyapi/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"anyapi"},"anyapi/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"sourceProvider":"anyapi"},"anyapi/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"sourceProvider":"anyapi"},"anyapi/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"sourceProvider":"anyapi"},"anyapi/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"sourceProvider":"anyapi"},"anyapi/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"sourceProvider":"anyapi"},"anyapi/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"sourceProvider":"anyapi"},"anyapi/xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"sourceProvider":"anyapi"},"arcee/deepseek/deepseek-v4-flash-latest":{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"status":"beta","cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"arcee"},"arcee/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":384000},"status":"beta","cost":{"input":1.74,"output":3.48,"cache_read":0.2},"sourceProvider":"arcee"},"arcee/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"status":"beta","cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"arcee"},"arcee/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"beta","cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"arcee"},"arcee/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"arcee"},"arcee/trinity-large-thinking":{"id":"arcee/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0.25,"output":0.8,"cache_read":0.06},"sourceProvider":"arcee"},"arcee/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"status":"beta","cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"arcee"},"atomic-chat/gemma-4-E4B-it-IQ4_XS":{"id":"atomic-chat/gemma-4-E4B-it-IQ4_XS","name":"Gemma 4 E4B Instruct (IQ4_XS)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"atomic-chat"},"atomic-chat/gemma-4-E4B-it-MLX-4bit":{"id":"atomic-chat/gemma-4-E4B-it-MLX-4bit","name":"Gemma 4 E4B Instruct (MLX 4-bit)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"atomic-chat"},"atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF":{"id":"atomic-chat/Meta-Llama-3_1-8B-Instruct-GGUF","name":"Meta Llama 3.1 8B Instruct (GGUF)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"atomic-chat"},"atomic-chat/Qwen3_5-9B-MLX-4bit":{"id":"atomic-chat/Qwen3_5-9B-MLX-4bit","name":"Qwen 3.5 9B (MLX 4-bit)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"atomic-chat"},"atomic-chat/Qwen3_5-9B-Q4_K_M":{"id":"atomic-chat/Qwen3_5-9B-Q4_K_M","name":"Qwen 3.5 9B (Q4_K_M)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"atomic-chat"},"auriko/claude-opus-4-6":{"id":"auriko/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"auriko"},"auriko/claude-opus-4-7":{"id":"auriko/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"auriko"},"auriko/claude-sonnet-4-6":{"id":"auriko/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"auriko"},"auriko/deepseek-v4-flash":{"id":"auriko/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"auriko"},"auriko/deepseek-v4-pro":{"id":"auriko/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"auriko"},"auriko/gemini-2.5-flash":{"id":"auriko/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"auriko"},"auriko/gemini-2.5-pro":{"id":"auriko/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"auriko"},"auriko/gemini-3.1-pro-preview":{"id":"auriko/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"auriko"},"auriko/glm-5.1":{"id":"auriko/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"auriko"},"auriko/grok-4.3":{"id":"auriko/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"auriko"},"auriko/kimi-k2.5":{"id":"auriko/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8},"sourceProvider":"auriko"},"auriko/kimi-k2.6":{"id":"auriko/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"auriko"},"auriko/minimax-m2-7":{"id":"auriko/minimax-m2-7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_write":0.375},"sourceProvider":"auriko"},"auriko/minimax-m2-7-highspeed":{"id":"auriko/minimax-m2-7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_write":0.375},"sourceProvider":"auriko"},"auriko/qwen-3.6-plus":{"id":"auriko/qwen-3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"auriko"},"azure-cognitive-services/claude-fable-5":{"id":"azure-cognitive-services/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-haiku-4-5":{"id":"azure-cognitive-services/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-mythos-5":{"id":"azure-cognitive-services/claude-mythos-5","name":"Claude Mythos 5","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","family":"claude-mythos","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-4-1":{"id":"azure-cognitive-services/claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-4-5":{"id":"azure-cognitive-services/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-4-6":{"id":"azure-cognitive-services/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-07-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-4-7":{"id":"azure-cognitive-services/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-4-8":{"id":"azure-cognitive-services/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-opus-5":{"id":"azure-cognitive-services/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-sonnet-4-5":{"id":"azure-cognitive-services/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-sonnet-4-6":{"id":"azure-cognitive-services/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/claude-sonnet-5":{"id":"azure-cognitive-services/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/codestral-2501":{"id":"azure-cognitive-services/codestral-2501","name":"Codestral 25.01","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/codex-mini":{"id":"azure-cognitive-services/codex-mini","name":"Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-04","release_date":"2025-05-16","last_updated":"2025-05-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.5,"output":6,"cache_read":0.375},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/cohere-command-a":{"id":"azure-cognitive-services/cohere-command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.5,"output":10},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/cohere-embed-v-4-0":{"id":"azure-cognitive-services/cohere-embed-v-4-0","name":"Embed v4","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":1536},"cost":{"input":0.12,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/cohere-embed-v3-english":{"id":"azure-cognitive-services/cohere-embed-v3-english","name":"Embed v3 English","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/cohere-embed-v3-multilingual":{"id":"azure-cognitive-services/cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/deepseek-r1":{"id":"azure-cognitive-services/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"status":"deprecated","cost":{"input":1.35,"output":5.4},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/deepseek-v3.2":{"id":"azure-cognitive-services/deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/deepseek-v3.2-speciale":{"id":"azure-cognitive-services/deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-3.5-turbo-0125":{"id":"azure-cognitive-services/gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"status":"deprecated","cost":{"input":0.5,"output":1.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-3.5-turbo-1106":{"id":"azure-cognitive-services/gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"status":"deprecated","cost":{"input":1,"output":2},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-3.5-turbo-instruct":{"id":"azure-cognitive-services/gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-09-21","last_updated":"2023-09-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"status":"deprecated","cost":{"input":1.5,"output":2},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4-turbo":{"id":"azure-cognitive-services/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4-turbo-vision":{"id":"azure-cognitive-services/gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4.1":{"id":"azure-cognitive-services/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4.1-mini":{"id":"azure-cognitive-services/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4.1-nano":{"id":"azure-cognitive-services/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4o":{"id":"azure-cognitive-services/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-4o-mini":{"id":"azure-cognitive-services/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5":{"id":"azure-cognitive-services/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5-codex":{"id":"azure-cognitive-services/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5-mini":{"id":"azure-cognitive-services/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5-nano":{"id":"azure-cognitive-services/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5-pro":{"id":"azure-cognitive-services/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.1":{"id":"azure-cognitive-services/gpt-5.1","name":"GPT-5.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.1-codex":{"id":"azure-cognitive-services/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.1-codex-mini":{"id":"azure-cognitive-services/gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.2":{"id":"azure-cognitive-services/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.125},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.2-codex":{"id":"azure-cognitive-services/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.3-codex":{"id":"azure-cognitive-services/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.4":{"id":"azure-cognitive-services/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.4-mini":{"id":"azure-cognitive-services/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.4-nano":{"id":"azure-cognitive-services/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.4-pro":{"id":"azure-cognitive-services/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.5":{"id":"azure-cognitive-services/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.6-luna":{"id":"azure-cognitive-services/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"tiers":[{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.6-sol":{"id":"azure-cognitive-services/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-5.6-terra":{"id":"azure-cognitive-services/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/gpt-chat-latest":{"id":"azure-cognitive-services/gpt-chat-latest","name":"GPT Chat Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/kimi-k2.5":{"id":"azure-cognitive-services/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.6,"output":3},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/kimi-k2.6":{"id":"azure-cognitive-services/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/llama-3.3-70b-instruct":{"id":"azure-cognitive-services/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.71,"output":0.71},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8":{"id":"azure-cognitive-services/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.25,"output":1},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/llama-4-scout-17b-16e-instruct":{"id":"azure-cognitive-services/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.78},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/ministral-3b":{"id":"azure-cognitive-services/ministral-3b","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.04,"output":0.04},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/mistral-medium-2505":{"id":"azure-cognitive-services/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/mistral-small-2503":{"id":"azure-cognitive-services/mistral-small-2503","name":"Mistral Small 3.1","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.1,"output":0.3},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/model-router":{"id":"azure-cognitive-services/model-router","name":"Model Router","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2025-05-19","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"cost":{"input":0.14,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/o1":{"id":"azure-cognitive-services/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/o3":{"id":"azure-cognitive-services/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/o3-mini":{"id":"azure-cognitive-services/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/o4-mini":{"id":"azure-cognitive-services/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4":{"id":"azure-cognitive-services/phi-4","name":"Phi-4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4-mini":{"id":"azure-cognitive-services/phi-4-mini","name":"Phi-4-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4-mini-reasoning":{"id":"azure-cognitive-services/phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4-multimodal":{"id":"azure-cognitive-services/phi-4-multimodal","name":"Phi-4-multimodal","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.08,"output":0.32,"input_audio":4},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4-reasoning":{"id":"azure-cognitive-services/phi-4-reasoning","name":"Phi-4-reasoning","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/phi-4-reasoning-plus":{"id":"azure-cognitive-services/phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/text-embedding-3-large":{"id":"azure-cognitive-services/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.13,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/text-embedding-3-small":{"id":"azure-cognitive-services/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"sourceProvider":"azure-cognitive-services"},"azure-cognitive-services/text-embedding-ada-002":{"id":"azure-cognitive-services/text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"sourceProvider":"azure-cognitive-services"},"azure/claude-fable-5":{"id":"azure/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"azure"},"azure/claude-haiku-4-5":{"id":"azure/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"azure"},"azure/claude-mythos-5":{"id":"azure/claude-mythos-5","name":"Claude Mythos 5","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","family":"claude-mythos","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"azure"},"azure/claude-opus-4-1":{"id":"azure/claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"azure"},"azure/claude-opus-4-5":{"id":"azure/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-08-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure"},"azure/claude-opus-4-6":{"id":"azure/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-07-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"azure"},"azure/claude-opus-4-7":{"id":"azure/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure"},"azure/claude-opus-4-8":{"id":"azure/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"azure"},"azure/claude-opus-5":{"id":"azure/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"azure"},"azure/claude-sonnet-4-5":{"id":"azure/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"azure"},"azure/claude-sonnet-4-6":{"id":"azure/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"azure"},"azure/claude-sonnet-5":{"id":"azure/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","provider":{"npm":"@ai-sdk/anthropic","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"azure"},"azure/codestral-2501":{"id":"azure/codestral-2501","name":"Codestral 25.01","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"sourceProvider":"azure"},"azure/codex-mini":{"id":"azure/codex-mini","name":"Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-04","release_date":"2025-05-16","last_updated":"2025-05-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.5,"output":6,"cache_read":0.375},"sourceProvider":"azure"},"azure/cohere-command-a":{"id":"azure/cohere-command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":2.5,"output":10},"sourceProvider":"azure"},"azure/cohere-embed-v-4-0":{"id":"azure/cohere-embed-v-4-0","name":"Embed v4","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":1536},"cost":{"input":0.12,"output":0},"sourceProvider":"azure"},"azure/cohere-embed-v3-english":{"id":"azure/cohere-embed-v3-english","name":"Embed v3 English","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"sourceProvider":"azure"},"azure/cohere-embed-v3-multilingual":{"id":"azure/cohere-embed-v3-multilingual","name":"Embed v3 Multilingual","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-11-07","last_updated":"2023-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.1,"output":0},"sourceProvider":"azure"},"azure/deepseek-r1":{"id":"azure/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"status":"deprecated","cost":{"input":1.35,"output":5.4},"sourceProvider":"azure"},"azure/deepseek-v3.2":{"id":"azure/deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"sourceProvider":"azure"},"azure/deepseek-v3.2-speciale":{"id":"azure/deepseek-v3.2-speciale","name":"DeepSeek-V3.2-Speciale","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.58,"output":1.68},"sourceProvider":"azure"},"azure/deepseek-v4-flash":{"id":"azure/deepseek-v4-flash","name":"DeepSeek-V4-Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.19,"output":0.51},"sourceProvider":"azure"},"azure/deepseek-v4-pro":{"id":"azure/deepseek-v4-pro","name":"DeepSeek-V4-Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":1.74,"output":3.48},"sourceProvider":"azure"},"azure/gpt-3.5-turbo-0125":{"id":"azure/gpt-3.5-turbo-0125","name":"GPT-3.5 Turbo 0125","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"status":"deprecated","cost":{"input":0.5,"output":1.5},"sourceProvider":"azure"},"azure/gpt-3.5-turbo-1106":{"id":"azure/gpt-3.5-turbo-1106","name":"GPT-3.5 Turbo 1106","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"status":"deprecated","cost":{"input":1,"output":2},"sourceProvider":"azure"},"azure/gpt-3.5-turbo-instruct":{"id":"azure/gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2021-08","release_date":"2023-09-21","last_updated":"2023-09-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"status":"deprecated","cost":{"input":1.5,"output":2},"sourceProvider":"azure"},"azure/gpt-4-turbo":{"id":"azure/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"azure"},"azure/gpt-4-turbo-vision":{"id":"azure/gpt-4-turbo-vision","name":"GPT-4 Turbo Vision","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"azure"},"azure/gpt-4.1":{"id":"azure/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"azure"},"azure/gpt-4.1-mini":{"id":"azure/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"azure"},"azure/gpt-4.1-nano":{"id":"azure/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"azure"},"azure/gpt-4o":{"id":"azure/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"azure"},"azure/gpt-4o-mini":{"id":"azure/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"azure"},"azure/gpt-5":{"id":"azure/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"azure"},"azure/gpt-5-codex":{"id":"azure/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"azure"},"azure/gpt-5-mini":{"id":"azure/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"azure"},"azure/gpt-5-nano":{"id":"azure/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"sourceProvider":"azure"},"azure/gpt-5-pro":{"id":"azure/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"azure"},"azure/gpt-5.1":{"id":"azure/gpt-5.1","name":"GPT-5.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"azure"},"azure/gpt-5.1-codex":{"id":"azure/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"azure"},"azure/gpt-5.1-codex-max":{"id":"azure/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"azure"},"azure/gpt-5.1-codex-mini":{"id":"azure/gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"azure"},"azure/gpt-5.2":{"id":"azure/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.125},"sourceProvider":"azure"},"azure/gpt-5.2-codex":{"id":"azure/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"azure"},"azure/gpt-5.3-codex":{"id":"azure/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"azure"},"azure/gpt-5.4":{"id":"azure/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"azure"},"azure/gpt-5.4-mini":{"id":"azure/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"azure"},"azure/gpt-5.4-nano":{"id":"azure/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"azure"},"azure/gpt-5.4-pro":{"id":"azure/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"azure"},"azure/gpt-5.5":{"id":"azure/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"azure"},"azure/gpt-5.6-luna":{"id":"azure/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"azure"},"azure/gpt-5.6-sol":{"id":"azure/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"azure"},"azure/gpt-5.6-terra":{"id":"azure/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"azure"},"azure/gpt-chat-latest":{"id":"azure/gpt-chat-latest","name":"GPT Chat Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"status":"beta","cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"azure"},"azure/gpt-image-1":{"id":"azure/gpt-image-1","name":"GPT-Image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":40,"cache_read":1.25},"sourceProvider":"azure"},"azure/gpt-image-1.5":{"id":"azure/gpt-image-1.5","name":"GPT-Image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":32,"cache_read":1.25},"sourceProvider":"azure"},"azure/gpt-image-2":{"id":"azure/gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":30,"cache_read":1.25},"sourceProvider":"azure"},"azure/grok-4-1-fast-non-reasoning":{"id":"azure/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"status":"beta","cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"azure"},"azure/grok-4-1-fast-reasoning":{"id":"azure/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"status":"beta","cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"azure"},"azure/grok-4-20-non-reasoning":{"id":"azure/grok-4-20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":8192},"status":"beta","cost":{"input":2,"output":6},"sourceProvider":"azure"},"azure/grok-4-20-reasoning":{"id":"azure/grok-4-20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":8192},"status":"beta","cost":{"input":2,"output":6},"sourceProvider":"azure"},"azure/kimi-k2.5":{"id":"azure/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.6,"output":3},"sourceProvider":"azure"},"azure/kimi-k2.6":{"id":"azure/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4},"sourceProvider":"azure"},"azure/kimi-k2.7-code":{"id":"azure/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models","shape":"completions"},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"azure"},"azure/llama-3.3-70b-instruct":{"id":"azure/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.71,"output":0.71},"sourceProvider":"azure"},"azure/llama-4-maverick-17b-128e-instruct-fp8":{"id":"azure/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.25,"output":1},"sourceProvider":"azure"},"azure/llama-4-scout-17b-16e-instruct":{"id":"azure/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.78},"sourceProvider":"azure"},"azure/ministral-3b":{"id":"azure/ministral-3b","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.04,"output":0.04},"sourceProvider":"azure"},"azure/mistral-medium-2505":{"id":"azure/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2},"sourceProvider":"azure"},"azure/mistral-small-2503":{"id":"azure/mistral-small-2503","name":"Mistral Small 3.1","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.1,"output":0.3},"sourceProvider":"azure"},"azure/model-router":{"id":"azure/model-router","name":"Model Router","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"model-router","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2025-05-19","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"cost":{"input":0.14,"output":0},"sourceProvider":"azure"},"azure/o1":{"id":"azure/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"azure"},"azure/o3":{"id":"azure/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"azure"},"azure/o3-mini":{"id":"azure/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"azure"},"azure/o4-mini":{"id":"azure/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"azure"},"azure/phi-4":{"id":"azure/phi-4","name":"Phi-4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure"},"azure/phi-4-mini":{"id":"azure/phi-4-mini","name":"Phi-4-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"sourceProvider":"azure"},"azure/phi-4-mini-reasoning":{"id":"azure/phi-4-mini-reasoning","name":"Phi-4-mini-reasoning","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.075,"output":0.3},"sourceProvider":"azure"},"azure/phi-4-multimodal":{"id":"azure/phi-4-multimodal","name":"Phi-4-multimodal","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"phi","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.08,"output":0.32,"input_audio":4},"sourceProvider":"azure"},"azure/phi-4-reasoning":{"id":"azure/phi-4-reasoning","name":"Phi-4-reasoning","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure"},"azure/phi-4-reasoning-plus":{"id":"azure/phi-4-reasoning-plus","name":"Phi-4-reasoning-plus","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"phi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2023-10","release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.125,"output":0.5},"sourceProvider":"azure"},"azure/text-embedding-3-large":{"id":"azure/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.13,"output":0},"sourceProvider":"azure"},"azure/text-embedding-3-small":{"id":"azure/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"sourceProvider":"azure"},"azure/text-embedding-ada-002":{"id":"azure/text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"sourceProvider":"azure"},"bailing/Ling-1T":{"id":"bailing/Ling-1T","name":"Ling-1T","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-10","last_updated":"2025-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.57,"output":2.29},"sourceProvider":"bailing"},"bailing/Ring-1T":{"id":"bailing/Ring-1T","name":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-10","last_updated":"2025-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.57,"output":2.29},"sourceProvider":"bailing"},"baseten/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":131000},"status":"deprecated","cost":{"input":0.5,"output":1.5},"sourceProvider":"baseten"},"baseten/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"sourceProvider":"baseten"},"baseten/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"baseten"},"baseten/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.32,"output":3.96},"sourceProvider":"baseten"},"baseten/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204000,"output":204000},"status":"deprecated","cost":{"input":0.3,"output":1.2},"sourceProvider":"baseten"},"baseten/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-30","last_updated":"2026-02-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.6,"output":3,"cache_read":0.12},"sourceProvider":"baseten"},"baseten/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"baseten"},"baseten/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"baseten"},"baseten/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":3,"output":15},"sourceProvider":"baseten"},"baseten/nvidia/Nemotron-120B-A12B":{"id":"nvidia/Nemotron-120B-A12B","name":"Nemotron Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.3,"output":0.75,"cache_read":0.06},"sourceProvider":"baseten"},"baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"sourceProvider":"baseten"},"baseten/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128072,"output":128072},"cost":{"input":0.1,"output":0.5},"sourceProvider":"baseten"},"baseten/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":1,"output":4.05},"sourceProvider":"baseten"},"baseten/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"baseten"},"baseten/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":200000},"cost":{"input":0.6,"output":2.2,"cache_read":0.12},"sourceProvider":"baseten"},"baseten/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":0.95,"output":3.15,"cache_read":0.2},"sourceProvider":"baseten"},"baseten/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":202800},"cost":{"input":1.3,"output":4.3,"cache_read":0.26},"sourceProvider":"baseten"},"baseten/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.4,"output":4.4,"cache_read":0.3},"sourceProvider":"baseten"},"baseten/zai-org/GLM-5.2-Fast":{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"sourceProvider":"baseten"},"berget/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["audio","image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.275,"output":0.55},"sourceProvider":"berget"},"berget/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-04-27","last_updated":"2025-04-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.99,"output":0.99},"sourceProvider":"berget"},"berget/mistralai/Mistral-Medium-3.5-128B":{"id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral Medium 3.5 128B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-04","release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.65,"output":5.5},"sourceProvider":"berget"},"berget/mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral Small 3.2 24B Instruct 2506","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.33,"output":0.33},"sourceProvider":"berget"},"berget/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.83,"output":3.85,"cache_read":0.16},"sourceProvider":"berget"},"berget/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"output":32768},"cost":{"input":3,"output":15},"sourceProvider":"berget"},"berget/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.22,"output":0.83},"sourceProvider":"berget"},"berget/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.77,"output":2.75},"sourceProvider":"berget"},"berget/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":32768},"cost":{"input":1.54,"output":4.84},"sourceProvider":"berget"},"blueclaw/Qwen/Qwen3.6-35B-A3B-FP8":{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"status":"beta","sourceProvider":"blueclaw"},"blueclaw/Qwen3.6-27B":{"id":"blueclaw/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":65536},"status":"beta","sourceProvider":"blueclaw"},"cerebras/gemma-4-31b":{"id":"cerebras/gemma-4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-07-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"status":"beta","cost":{"input":0.99,"output":1.49},"sourceProvider":"cerebras"},"cerebras/gpt-oss-120b":{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":40960},"cost":{"input":0.35,"output":0.75},"sourceProvider":"cerebras"},"chutes/deepseek-ai/DeepSeek-V3.2-TEE":{"id":"deepseek-ai/DeepSeek-V3.2-TEE","name":"DeepSeek V3.2 TEE","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12","last_updated":"2026-06-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":1,"output":1,"cache_read":0.09999999999999998},"sourceProvider":"chutes"},"chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731-TEE","name":"DeepSeek V4 Flash 0731 TEE","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.013999999999999999},"sourceProvider":"chutes"},"chutes/google/gemma-4-31B-turbo-TEE":{"id":"google/gemma-4-31B-turbo-TEE","name":"gemma 4 31B turbo TEE","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.12,"output":0.37,"cache_read":0.011999999999999997},"sourceProvider":"chutes"},"chutes/moonshotai/Kimi-K2.6-TEE":{"id":"moonshotai/Kimi-K2.6-TEE","name":"Kimi K2.6 TEE","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65535},"cost":{"input":0.58,"output":3.4,"cache_read":0.05799999999999998},"sourceProvider":"chutes"},"chutes/moonshotai/Kimi-K3-TEE":{"id":"moonshotai/Kimi-K3-TEE","name":"Kimi K3 TEE","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65535},"cost":{"input":3,"output":15,"cache_read":0.29999999999999993},"sourceProvider":"chutes"},"chutes/Nemotron-3-Nano-Omni-30B-TEE":{"id":"chutes/Nemotron-3-Nano-Omni-30B-TEE","name":"Nemotron 3 Nano Omni 30B TEE","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":0},"cost":{"input":0.0245,"output":0.0978,"cache_read":0.0024499999999999995},"sourceProvider":"chutes"},"chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","name":"Qwen3 235B A22B Thinking 2507 TEE","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07","last_updated":"2026-06-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2989,"output":1.1957,"cache_read":0.029889999999999993},"sourceProvider":"chutes"},"chutes/Qwen/Qwen3-32B-TEE":{"id":"Qwen/Qwen3-32B-TEE","name":"Qwen3 32B TEE","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.104,"output":0.416,"cache_read":0.010399999999999998},"sourceProvider":"chutes"},"chutes/Qwen/Qwen3.5-397B-A17B-TEE":{"id":"Qwen/Qwen3.5-397B-A17B-TEE","name":"Qwen3.5 397B A17B TEE","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3,"cache_read":0.04499999999999999},"sourceProvider":"chutes"},"chutes/Qwen/Qwen3.6-27B-TEE":{"id":"Qwen/Qwen3.6-27B-TEE","name":"Qwen3.6 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2,"cache_read":0.029999999999999992},"sourceProvider":"chutes"},"chutes/Qwen/Qwen3.8-27B-TEE":{"id":"Qwen/Qwen3.8-27B-TEE","name":"Qwen3.8 27B TEE","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-16","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.35,"output":2.75,"cache_read":0.03499999999999999},"sourceProvider":"chutes"},"chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE":{"id":"unsloth/Mistral-Nemo-Instruct-2407-TEE","name":"Mistral Nemo Instruct 2407 TEE","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0245,"output":0.0978,"cache_read":0.0024499999999999995},"sourceProvider":"chutes"},"chutes/zai-org/GLM-5.1-TEE":{"id":"zai-org/GLM-5.1-TEE","name":"GLM 5.1 TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":65535},"cost":{"input":0.98,"output":3.08,"cache_read":0.09799999999999998},"sourceProvider":"chutes"},"chutes/zai-org/GLM-5.2-TEE":{"id":"zai-org/GLM-5.2-TEE","name":"GLM 5.2 TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65535},"cost":{"input":1.25,"output":3.95,"cache_read":0.12499999999999997},"sourceProvider":"chutes"},"clarifai/arcee_ai/AFM/models/trinity-mini":{"id":"arcee_ai/AFM/models/trinity-mini","name":"Trinity Mini","description":"Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-01","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.045,"output":0.15},"sourceProvider":"clarifai"},"clarifai/deepseek-ai/deepseek-ocr/models/DeepSeek-OCR":{"id":"deepseek-ai/deepseek-ocr/models/DeepSeek-OCR","name":"DeepSeek OCR","description":"OCR model for extracting structured text from documents and screenshots","family":"deepseek","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2026-02-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.2,"output":0.7},"sourceProvider":"clarifai"},"clarifai/main/models/mm-poly-8b":{"id":"clarifai/main/models/mm-poly-8b","name":"MM Poly 8B","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"mm-poly","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-06","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.658,"output":1.11},"sourceProvider":"clarifai"},"clarifai/minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput":{"id":"minimaxai/chat-completion/models/MiniMax-M2_5-high-throughput","name":"MiniMax-M2.5 High Throughput","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"clarifai"},"clarifai/mistralai/completion/models/Ministral-3-14B-Reasoning-2512":{"id":"mistralai/completion/models/Ministral-3-14B-Reasoning-2512","name":"Ministral 3 14B Reasoning 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-01","last_updated":"2025-12-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.5,"output":1.7},"sourceProvider":"clarifai"},"clarifai/mistralai/completion/models/Ministral-3-3B-Reasoning-2512":{"id":"mistralai/completion/models/Ministral-3-3B-Reasoning-2512","name":"Ministral 3 3B Reasoning 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12","last_updated":"2026-02-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.039,"output":0.54825},"sourceProvider":"clarifai"},"clarifai/moonshotai/chat-completion/models/Kimi-K2_6":{"id":"moonshotai/chat-completion/models/Kimi-K2_6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"sourceProvider":"clarifai"},"clarifai/openai/chat-completion/models/gpt-oss-120b-high-throughput":{"id":"openai/chat-completion/models/gpt-oss-120b-high-throughput","name":"GPT OSS 120B High Throughput","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.09,"output":0.36},"sourceProvider":"clarifai"},"clarifai/openai/chat-completion/models/gpt-oss-20b":{"id":"openai/chat-completion/models/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-12-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.045,"output":0.18},"sourceProvider":"clarifai"},"clarifai/qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct":{"id":"qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.11458,"output":0.74812},"sourceProvider":"clarifai"},"clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507":{"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.5},"sourceProvider":"clarifai"},"clarifai/qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507":{"id":"qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.36,"output":1.3},"sourceProvider":"clarifai"},"claudinio/claudinio":{"id":"claudinio/claudinio","name":"Claudinio","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"knowledge":"2026-05","release_date":"2026-05-12","last_updated":"2026-06-02","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.5,"output":2,"cache_read":0.15},"sourceProvider":"claudinio"},"claudinio/claudius":{"id":"claudinio/claudius","name":"Claudius","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"knowledge":"2026-05","release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":3,"output":8,"cache_read":0.9},"sourceProvider":"claudinio"},"cline-pass/deepseek-v4-flash":{"id":"cline-pass/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"cline-pass"},"cline-pass/deepseek-v4-pro":{"id":"cline-pass/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.0145},"sourceProvider":"cline-pass"},"cline-pass/glm-5.2":{"id":"cline-pass/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"cline-pass"},"cline-pass/kimi-k2.6":{"id":"cline-pass/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"cline-pass"},"cline-pass/kimi-k2.7-code":{"id":"cline-pass/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"cline-pass"},"cline-pass/kimi-k3":{"id":"cline-pass/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"cline-pass"},"cline-pass/mimo-v2.5":{"id":"cline-pass/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"cline-pass"},"cline-pass/mimo-v2.5-pro":{"id":"cline-pass/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.74,"output":3.48,"cache_read":0.0145},"sourceProvider":"cline-pass"},"cline-pass/minimax-m3":{"id":"cline-pass/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"cline-pass"},"cline-pass/qwen3.7-max":{"id":"cline-pass/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"cline-pass"},"cline-pass/qwen3.7-plus":{"id":"cline-pass/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"sourceProvider":"cline-pass"},"cloudferro-sherlock/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10-09","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":70000,"output":70000},"cost":{"input":2.92,"output":2.92},"sourceProvider":"cloudferro-sherlock"},"cloudferro-sherlock/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"input":180000,"output":16000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"cloudferro-sherlock"},"cloudferro-sherlock/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":2.92,"output":2.92},"sourceProvider":"cloudferro-sherlock"},"cloudferro-sherlock/speakleash/Bielik-11B-v2.6-Instruct":{"id":"speakleash/Bielik-11B-v2.6-Instruct","name":"Bielik 11B v2.6 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.67,"output":0.67},"sourceProvider":"cloudferro-sherlock"},"cloudferro-sherlock/speakleash/Bielik-11B-v3.0-Instruct":{"id":"speakleash/Bielik-11B-v3.0-Instruct","name":"Bielik 11B v3.0 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.67,"output":0.67},"sourceProvider":"cloudferro-sherlock"},"cloudflare-ai-gateway/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-07","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-04","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-14","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"ai-gateway-provider"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-29","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"status":"deprecated","cost":{"input":0.5,"output":1.5,"cache_read":0},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","cost":{"input":30,"output":60},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":5,"cache_read":0.625},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.2-chat-latest":{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.3-chat-latest":{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"ai-gateway-provider"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.3-codex-spark":{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":100000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"ai-gateway-provider"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.6":{"id":"openai/gpt-5.6","name":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":150,"output":600},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"id":"workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"id":"workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","name":"Deepseek R1 Distill Qwen 32B","description":"R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.497,"output":4.881},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/google/gemma-4-26b-a4b-it":{"id":"workers-ai/@cf/google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/ibm-granite/granite-4.0-h-micro":{"id":"workers-ai/@cf/ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.017,"output":0.112},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8":{"id":"workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8","name":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.152,"output":0.287},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-11b-vision-instruct":{"id":"workers-ai/@cf/meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.0485,"output":0.676},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-1b-instruct":{"id":"workers-ai/@cf/meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":60000},"cost":{"input":0.027,"output":0.201},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.2-3b-instruct":{"id":"workers-ai/@cf/meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.0509,"output":0.335},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"id":"workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast","name":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.293,"output":2.253},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct":{"id":"workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":16384},"cost":{"input":0.27,"output":0.85},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/meta/llama-guard-3-8b":{"id":"workers-ai/@cf/meta/llama-guard-3-8b","name":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.484,"output":0.03},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct":{"id":"workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.6":{"id":"workers-ai/@cf/moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/moonshotai/kimi-k2.7-code":{"id":"workers-ai/@cf/moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/nvidia/nemotron-3-120b-a12b":{"id":"workers-ai/@cf/nvidia/nemotron-3-120b-a12b","name":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-120b":{"id":"workers-ai/@cf/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.35,"output":0.75},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/openai/gpt-oss-20b":{"id":"workers-ai/@cf/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.3},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct":{"id":"workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.66,"output":1},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/qwen/qwen3-30b-a3b-fp8":{"id":"workers-ai/@cf/qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.0509,"output":0.335},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/qwen/qwq-32b":{"id":"workers-ai/@cf/qwen/qwq-32b","name":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.66,"output":1},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-4.7-flash":{"id":"workers-ai/@cf/zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0605,"output":0.4},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-ai-gateway/workers-ai/@cf/zai-org/glm-5.2":{"id":"workers-ai/@cf/zai-org/glm-5.2","name":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"cloudflare-ai-gateway"},"cloudflare-workers-ai/@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"id":"@cf/aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma Sea Lion V4 27B It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/deepseek-ai/deepseek-r1-distill-qwen-32b":{"id":"@cf/deepseek-ai/deepseek-r1-distill-qwen-32b","name":"Deepseek R1 Distill Qwen 32B","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.497,"output":4.881},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-flash-0731":{"id":"@cf/deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1310720,"output":1048576},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/deepseek-ai/deepseek-v4-pro-0813":{"id":"@cf/deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/google/gemma-4-26b-a4b-it":{"id":"@cf/google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/ibm-granite/granite-4.0-h-micro":{"id":"@cf/ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 H Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.017,"output":0.112},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-3.1-8b-instruct-fp8":{"id":"@cf/meta/llama-3.1-8b-instruct-fp8","name":"Llama 3.1 8B Instruct fp8","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.152,"output":0.287},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-3.2-11b-vision-instruct":{"id":"@cf/meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.0485,"output":0.676},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-3.2-1b-instruct":{"id":"@cf/meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":60000},"cost":{"input":0.027,"output":0.201},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-3.2-3b-instruct":{"id":"@cf/meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":80000,"output":80000},"cost":{"input":0.0509,"output":0.335},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-3.3-70b-instruct-fp8-fast":{"id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","name":"Llama 3.3 70B Instruct fp8 Fast","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.293,"output":2.253},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-4-scout-17b-16e-instruct":{"id":"@cf/meta/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout 17B 16E Instruct","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":16384},"cost":{"input":0.27,"output":0.85},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/meta/llama-guard-3-8b":{"id":"@cf/meta/llama-guard-3-8b","name":"Llama Guard 3 8B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.484,"output":0.03},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct":{"id":"@cf/mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/moonshotai/kimi-k2.6":{"id":"@cf/moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/moonshotai/kimi-k2.7-code":{"id":"@cf/moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/nvidia/nemotron-3-120b-a12b":{"id":"@cf/nvidia/nemotron-3-120b-a12b","name":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/openai/gpt-oss-120b":{"id":"@cf/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.35,"output":0.75},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/openai/gpt-oss-20b":{"id":"@cf/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.3},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct":{"id":"@cf/qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.66,"output":1},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/qwen/qwen3-30b-a3b-fp8":{"id":"@cf/qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3b fp8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.0509,"output":0.335},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/qwen/qwen3.8-27b":{"id":"@cf/qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":3.2,"cache_read":0.05},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/qwen/qwq-32b":{"id":"@cf/qwen/qwq-32b","name":"Qwq 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":24000,"output":24000},"cost":{"input":0.66,"output":1},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/zai-org/glm-4.7-flash":{"id":"@cf/zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0605,"output":0.4},"sourceProvider":"cloudflare-workers-ai"},"cloudflare-workers-ai/@cf/zai-org/glm-5.2":{"id":"@cf/zai-org/glm-5.2","name":"Glm 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"cloudflare-workers-ai"},"cohere/c4ai-aya-expanse-32b":{"id":"cohere/c4ai-aya-expanse-32b","name":"Aya Expanse 32B","description":"Open multilingual model optimized for generation across 23 languages","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-24","last_updated":"2024-10-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"sourceProvider":"cohere"},"cohere/c4ai-aya-expanse-8b":{"id":"cohere/c4ai-aya-expanse-8b","name":"Aya Expanse 8B","description":"Compact open multilingual model optimized for generation across 23 languages","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-24","last_updated":"2024-10-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":4000},"sourceProvider":"cohere"},"cohere/c4ai-aya-vision-32b":{"id":"cohere/c4ai-aya-vision-32b","name":"Aya Vision 32B","description":"Open multilingual vision model for OCR, visual reasoning, and image question answering","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-04","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4000},"sourceProvider":"cohere"},"cohere/c4ai-aya-vision-8b":{"id":"cohere/c4ai-aya-vision-8b","name":"Aya Vision 8B","description":"Compact open multilingual vision model for OCR and visual question answering","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-04","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4000},"sourceProvider":"cohere"},"cohere/command-a-03-2025":{"id":"cohere/command-a-03-2025","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-a-plus-05-2026":{"id":"cohere/command-a-plus-05-2026","name":"Command A Plus","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","family":"command-a","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04-01","release_date":"2026-05-20","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-a-reasoning-08-2025":{"id":"cohere/command-a-reasoning-08-2025","name":"Command A Reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-a-translate-08-2025":{"id":"cohere/command-a-translate-08-2025","name":"Command A Translate","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"command-a","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-a-vision-07-2025":{"id":"cohere/command-a-vision-07-2025","name":"Command A Vision","description":"Cohere vision model for multilingual document analysis, OCR, and image understanding","family":"command-a","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"cohere"},"cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"sourceProvider":"cohere"},"cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"cohere"},"cohere/command-r7b-arabic-02-2025":{"id":"cohere/command-r7b-arabic-02-2025","name":"Command R7B Arabic","description":"Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"cohere"},"cohere/north-mini-code-1-0":{"id":"cohere/north-mini-code-1-0","name":"North Mini Code","description":"Cohere coding model for practical software engineering and agentic edits","family":"north","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09-23","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.cohere.ai/compatibility/v1"},"cost":{"input":0,"output":0},"sourceProvider":"cohere"},"coralbricks/glm-5.2-fp4":{"id":"coralbricks/glm-5.2-fp4","name":"GLM 5.2 FP4","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.12,"output":4.4,"cache_read":0},"sourceProvider":"coralbricks"},"coralbricks/gpt-oss-120b":{"id":"coralbricks/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.12,"output":0.6,"cache_read":0},"sourceProvider":"coralbricks"},"coralbricks/kimi-k3":{"id":"coralbricks/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0},"sourceProvider":"coralbricks"},"cortecs/apertus-70b":{"id":"cortecs/apertus-70b","name":"Apertus 70B","description":"Apertus 70B is an open, multilingual language model designed for research, long-context reasoning, and sovereignty-focused AI systems.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":1.393,"output":2.228},"sourceProvider":"cortecs"},"cortecs/claude-4-5-sonnet":{"id":"cortecs/claude-4-5-sonnet","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"cost":{"input":2.989,"output":14.945,"cache_read":0.326,"cache_write":4.078},"sourceProvider":"cortecs"},"cortecs/claude-4-6-sonnet":{"id":"cortecs/claude-4-6-sonnet","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":3.196,"output":15.94,"cache_read":0.32,"cache_write":3.999},"sourceProvider":"cortecs"},"cortecs/claude-haiku-4-5":{"id":"cortecs/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"cost":{"input":0.996,"output":4.982,"cache_read":0.099,"cache_write":1.186},"sourceProvider":"cortecs"},"cortecs/claude-opus-5":{"id":"cortecs/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5.5,"output":27.498,"cache_read":0.55,"cache_write":6.874},"sourceProvider":"cortecs"},"cortecs/claude-opus4-5":{"id":"cortecs/claude-opus4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"cost":{"input":5.313,"output":26.568,"cache_read":0.531,"cache_write":6.645},"sourceProvider":"cortecs"},"cortecs/claude-opus4-6":{"id":"cortecs/claude-opus4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5.313,"output":26.561,"cache_read":0.531,"cache_write":6.645},"sourceProvider":"cortecs"},"cortecs/claude-opus4-7":{"id":"cortecs/claude-opus4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797},"sourceProvider":"cortecs"},"cortecs/claude-opus4-8":{"id":"cortecs/claude-opus4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5.437,"output":27.186,"cache_read":0.544,"cache_write":6.797},"sourceProvider":"cortecs"},"cortecs/claude-sonnet-4":{"id":"cortecs/claude-sonnet-4","name":"Claude Sonnet 4 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"cost":{"input":2.898,"output":14.493,"cache_read":0.29,"cache_write":3.624},"sourceProvider":"cortecs"},"cortecs/claude-sonnet-5":{"id":"cortecs/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2.2,"output":11,"cache_read":0.219,"cache_write":2.749},"sourceProvider":"cortecs"},"cortecs/codestral-2508":{"id":"cortecs/codestral-2508","name":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.334,"output":1.003,"cache_read":0.033},"sourceProvider":"cortecs"},"cortecs/cosmos3-super-reasoner":{"id":"cortecs/cosmos3-super-reasoner","name":"cosmos3-super-reasoner","description":"Cosmos3 Super Reasoner is a high-capacity reasoning model designed for complex multi-agent tasks and advanced physical AI understanding.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.099,"output":0.296},"sourceProvider":"cortecs"},"cortecs/deepseek-r1-0528":{"id":"cortecs/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.652,"output":2.57,"cache_read":0.163},"sourceProvider":"cortecs"},"cortecs/deepseek-v3.2":{"id":"cortecs/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.296,"output":0.495,"cache_read":0.075},"sourceProvider":"cortecs"},"cortecs/deepseek-v4-flash-0731":{"id":"cortecs/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.13,"output":0.28,"cache_read":0.03},"sourceProvider":"cortecs"},"cortecs/deepseek-v4-pro":{"id":"cortecs/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.73,"output":3.46,"cache_read":0.432},"sourceProvider":"cortecs"},"cortecs/devstral-2512":{"id":"cortecs/devstral-2512","name":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.446,"output":2.228,"cache_read":0.045},"sourceProvider":"cortecs"},"cortecs/gemini-2.5-flash":{"id":"cortecs/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.299,"output":2.491,"cache_read":0.029,"cache_write":0.097},"sourceProvider":"cortecs"},"cortecs/gemini-2.5-pro":{"id":"cortecs/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.495,"output":9.964,"cache_read":0.242,"cache_write":0.434},"sourceProvider":"cortecs"},"cortecs/gemini-3.1-flash-lite":{"id":"cortecs/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.272,"output":1.631,"cache_read":0.025,"cache_write":0.082},"sourceProvider":"cortecs"},"cortecs/gemini-3.5-flash":{"id":"cortecs/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.649,"output":9.899,"cache_read":0.165,"cache_write":1},"sourceProvider":"cortecs"},"cortecs/gemini-3.5-flash-lite":{"id":"cortecs/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.33,"output":2.749,"cache_read":0.033},"sourceProvider":"cortecs"},"cortecs/gemini-3.6-flash":{"id":"cortecs/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038},"sourceProvider":"cortecs"},"cortecs/gemini-3.7-flash":{"id":"cortecs/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.038},"sourceProvider":"cortecs"},"cortecs/gemma-3-27b-it":{"id":"cortecs/gemma-3-27b-it","name":"gemma-3-27b-it","description":"Gemma 3 is a family of lightweight, multimodal models from Google, supporting text and image inputs, multilingual capabilities, and a 131K context window.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.099,"output":0.299},"sourceProvider":"cortecs"},"cortecs/gemma-4-26b-a4b-it":{"id":"cortecs/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.111,"output":0.557},"sourceProvider":"cortecs"},"cortecs/gemma-4-31b-it":{"id":"cortecs/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.223,"output":0.39},"sourceProvider":"cortecs"},"cortecs/glm-4.7":{"id":"cortecs/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":198000},"cost":{"input":0.78,"output":2.785},"sourceProvider":"cortecs"},"cortecs/glm-4.7-flash":{"id":"cortecs/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":203000},"cost":{"input":0.08,"output":0.478},"sourceProvider":"cortecs"},"cortecs/glm-5":{"id":"cortecs/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":0.988,"output":3.164,"cache_read":0.247},"sourceProvider":"cortecs"},"cortecs/glm-5-turbo":{"id":"cortecs/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":202752},"cost":{"input":1.186,"output":3.955,"cache_read":0.296,"cache_write":1.544},"sourceProvider":"cortecs"},"cortecs/glm-5.1":{"id":"cortecs/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.384,"output":4.348,"cache_read":0.346},"sourceProvider":"cortecs"},"cortecs/glm-5.2":{"id":"cortecs/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"sourceProvider":"cortecs"},"cortecs/glm-5v-turbo":{"id":"cortecs/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":202752},"cost":{"input":1.186,"output":3.955,"cache_read":0.296,"cache_write":1.544},"sourceProvider":"cortecs"},"cortecs/gpt-4.1":{"id":"cortecs/gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":1047576},"cost":{"input":2.192,"output":8.769,"cache_read":0.546},"sourceProvider":"cortecs"},"cortecs/gpt-4.1-mini":{"id":"cortecs/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":1047576},"cost":{"input":0.434,"output":1.704,"cache_read":0.134},"sourceProvider":"cortecs"},"cortecs/gpt-4.1-nano":{"id":"cortecs/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":1047576},"cost":{"input":0.111,"output":0.434,"cache_read":0.056},"sourceProvider":"cortecs"},"cortecs/gpt-4o":{"id":"cortecs/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2.659,"output":10.635,"cache_read":1.33},"sourceProvider":"cortecs"},"cortecs/gpt-4o-mini":{"id":"cortecs/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.159,"output":0.638,"cache_read":0.081},"sourceProvider":"cortecs"},"cortecs/gpt-5":{"id":"cortecs/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":400000},"cost":{"input":1.375,"output":10.96,"cache_read":0.156},"sourceProvider":"cortecs"},"cortecs/gpt-5-mini":{"id":"cortecs/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":400000},"cost":{"input":0.279,"output":2.192,"cache_read":0.056},"sourceProvider":"cortecs"},"cortecs/gpt-5-nano":{"id":"cortecs/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":400000},"cost":{"input":0.06,"output":0.439,"cache_read":0.019},"sourceProvider":"cortecs"},"cortecs/gpt-5.1":{"id":"cortecs/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":400000},"cost":{"input":1.375,"output":10.96,"cache_read":0.156},"sourceProvider":"cortecs"},"cortecs/gpt-5.4":{"id":"cortecs/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":1050000},"cost":{"input":2.898,"output":15.453,"cache_read":0.242},"sourceProvider":"cortecs"},"cortecs/gpt-5.6-luna":{"id":"cortecs/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":1050000},"cost":{"input":0.219,"output":1.32,"cache_read":0.022,"cache_write":0.275},"sourceProvider":"cortecs"},"cortecs/gpt-5.6-sol":{"id":"cortecs/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":1050000},"cost":{"input":5.5,"output":32.998,"cache_read":0.55,"cache_write":6.879},"sourceProvider":"cortecs"},"cortecs/gpt-5.6-terra":{"id":"cortecs/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":1050000},"cost":{"input":2.2,"output":13.199,"cache_read":0.219,"cache_write":2.749},"sourceProvider":"cortecs"},"cortecs/gpt-oss-120b":{"id":"cortecs/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":128000},"cost":{"input":0.089,"output":0.446,"cache_read":0.01},"sourceProvider":"cortecs"},"cortecs/gpt-oss-20b":{"id":"cortecs/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.045,"output":0.167},"sourceProvider":"cortecs"},"cortecs/gpt-oss-safeguard-120b":{"id":"cortecs/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.179,"output":0.697},"sourceProvider":"cortecs"},"cortecs/hermes-4-405b":{"id":"cortecs/hermes-4-405b","name":"hermes-4-405b","description":"Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-08-13","last_updated":"2024-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.996,"output":2.989},"sourceProvider":"cortecs"},"cortecs/hermes-4-70b":{"id":"cortecs/hermes-4-70b","name":"Hermes 4 70B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.129,"output":0.399},"sourceProvider":"cortecs"},"cortecs/kimi-k2.5":{"id":"cortecs/kimi-k2.5","name":"Kimi K2.5","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.495,"output":2.768,"cache_read":0.124},"sourceProvider":"cortecs"},"cortecs/kimi-k2.6":{"id":"cortecs/kimi-k2.6","name":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.773,"output":3.38,"cache_read":0.193},"sourceProvider":"cortecs"},"cortecs/kimi-k2.7-code":{"id":"cortecs/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":3.5,"cache_read":0.201},"sourceProvider":"cortecs"},"cortecs/kimi-k3":{"id":"cortecs/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":14.999},"sourceProvider":"cortecs"},"cortecs/llama-3.1-405b-instruct":{"id":"cortecs/llama-3.1-405b-instruct","name":"Llama 3.1 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":1.95,"output":1.95},"sourceProvider":"cortecs"},"cortecs/llama-3.1-8b-instruct":{"id":"cortecs/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","description":"Optimized for dialogue, this LLM by Meta outperforms other open-source chat models in benchmarks while prioritizing helpfulness and safety.","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.167,"output":0.167},"sourceProvider":"cortecs"},"cortecs/llama-3.1-nemotron-ultra-253b-v1":{"id":"cortecs/llama-3.1-nemotron-ultra-253b-v1","name":"llama-3.1-nemotron-ultra-253b-v1","description":"A reasoning-optimized LLM based on Llama 3.1, Nemotron Ultra 253B delivers strong performance in tasks like RAG and tool use, with high efficiency and reduced latency.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.598,"output":1.794},"sourceProvider":"cortecs"},"cortecs/llama-3.3-70b-instruct":{"id":"cortecs/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.129,"output":0.399},"sourceProvider":"cortecs"},"cortecs/minicpm-v-4.5":{"id":"cortecs/minicpm-v-4.5","name":"minicpm-v-4.5","description":"MiniCPM-V 4.5 is a compact, high-performance vision-language model excelling in video understanding, OCR, and multimodal reasoning with efficient deployment.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.651,"output":1.097},"sourceProvider":"cortecs"},"cortecs/minimax-m2":{"id":"cortecs/minimax-m2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":400000,"output":400000},"cost":{"input":0.349,"output":1.405},"sourceProvider":"cortecs"},"cortecs/minimax-m2.1":{"id":"cortecs/minimax-m2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"output":196000},"cost":{"input":0.359,"output":1.435},"sourceProvider":"cortecs"},"cortecs/minimax-m2.5":{"id":"cortecs/minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196680,"output":196608},"cost":{"input":0.296,"output":1.186,"cache_read":0.075},"sourceProvider":"cortecs"},"cortecs/minimax-m2.7":{"id":"cortecs/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196072},"cost":{"input":0.668,"output":2.674},"sourceProvider":"cortecs"},"cortecs/minimax-m3":{"id":"cortecs/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.395,"output":1.977,"cache_read":0.099},"sourceProvider":"cortecs"},"cortecs/ministral-14b-2512":{"id":"cortecs/ministral-14b-2512","name":"ministral-14b-2512","description":"Ministral 3 14B is a frontier-level 14B multimodal model optimized for local deployment, delivering state-of-the-art text and vision reasoning with a 256K context window and strong agentic capabilities.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.223,"output":0.223,"cache_read":0.022},"sourceProvider":"cortecs"},"cortecs/ministral-3b-2512":{"id":"cortecs/ministral-3b-2512","name":"ministral-3b-2512","description":"Ministral 3 3B is a compact, efficient multimodal model with strong language, vision capabilities, and ideal for custom fine-tuning.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.111,"output":0.111,"cache_read":0.011},"sourceProvider":"cortecs"},"cortecs/ministral-8b-2512":{"id":"cortecs/ministral-8b-2512","name":"ministral-8b-2512","description":"Ministral 3 8B is a balanced, efficient multimodal model offering strong text and vision capabilities, optimized for edge and local deployment.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.167,"output":0.167,"cache_read":0.017},"sourceProvider":"cortecs"},"cortecs/mistral-7b-instruct-v0.2":{"id":"cortecs/mistral-7b-instruct-v0.2","name":"mistral-7b-instruct-v0.2","description":"Mistral 7B Instruct is a compact, 7B parameter model optimized for fast and efficient text and code generation with a 32K token context window.","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.159,"output":0.219},"sourceProvider":"cortecs"},"cortecs/mistral-7b-instruct-v0.3":{"id":"cortecs/mistral-7b-instruct-v0.3","name":"mistral-7b-instruct-v0.3","description":"Mistral-7B-Instruct-v0.3 model is a fine-tuned version of the Mistral 7B base model, optimized for instruction-following tasks. Released in 2023, it is intended for demonstration purposes and does not include built-in guardrails or moderation features.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":127000},"cost":{"input":0.111,"output":0.111},"sourceProvider":"cortecs"},"cortecs/mistral-large-2402":{"id":"cortecs/mistral-large-2402","name":"mistral-large-2402","description":"Mistral Large (24.02) is Mistral AI’s most advanced language model, built for complex multilingual reasoning, code generation, and deep text understanding.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":4.284,"output":12.952},"sourceProvider":"cortecs"},"cortecs/mistral-large-2512":{"id":"cortecs/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.557,"output":1.671,"cache_read":0.056},"sourceProvider":"cortecs"},"cortecs/mistral-medium-2508":{"id":"cortecs/mistral-medium-2508","name":"mistral-medium-2508","description":"Mistral Medium 2508 is a frontier-class multimodal LLM with a 128,000 token context window, optimized for reasoning, coding, and multimodal tasks.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-08-07","last_updated":"2024-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.446,"output":2.228,"cache_read":0.045},"sourceProvider":"cortecs"},"cortecs/mistral-medium-3.5":{"id":"cortecs/mistral-medium-3.5","name":"mistral-medium-3.5","description":"Mistral Medium 3.5 is a frontier multimodal 128B model combining reasoning, coding, and instruction-following with strong agentic performance and efficient deployment.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1.671,"output":5.57},"sourceProvider":"cortecs"},"cortecs/mistral-nemo-instruct-2407":{"id":"cortecs/mistral-nemo-instruct-2407","name":"mistral-nemo-instruct-2407","description":"A 12B parameter, instruct-tuned language model by Mistral AI and NVIDIA, designed for advanced instruction following, multi-turn conversations, and generating text and code across multiple languages.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-08-07","last_updated":"2024-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":131072},"cost":{"input":0.145,"output":0.145,"cache_read":0.014},"sourceProvider":"cortecs"},"cortecs/mistral-small-2503":{"id":"cortecs/mistral-small-2503","name":"mistral-small-2503","description":"Combines advanced text and vision capabilities with 24 billion parameters, supporting multilingual tasks and long contexts up to 131k tokens, making it versatile for various applications without sacrificing performance.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.111,"output":0.334},"sourceProvider":"cortecs"},"cortecs/mistral-small-2603":{"id":"cortecs/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.143,"output":0.568,"cache_read":0.014},"sourceProvider":"cortecs"},"cortecs/mistral-small-3.2-24b-instruct-2506":{"id":"cortecs/mistral-small-3.2-24b-instruct-2506","name":"mistral-small-3.2-24b-instruct-2506","description":"Mistral-Small-3.2-24B-Instruct-2506 is a 24B parameter instruction-tuned model with enhanced long-context support (128k) and state-of-the-art vision understanding.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.1,"output":0.312},"sourceProvider":"cortecs"},"cortecs/mixtral-8x7B-instruct-v0.1":{"id":"cortecs/mixtral-8x7B-instruct-v0.1","name":"Mixtral 8x7B Instruct v0.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.488,"output":0.758},"sourceProvider":"cortecs"},"cortecs/nemotron-nano-v2-12b":{"id":"cortecs/nemotron-nano-v2-12b","name":"nemotron-nano-v2-12b","description":"NVIDIA Nemotron Nano v2 12B is a 12-billion-parameter multimodal reasoning model designed for advanced video understanding, document intelligence, and visual reasoning, built with a hybrid Transformer-Mamba architecture for high efficiency and low latency.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-10-31","last_updated":"2025-10-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.24,"output":0.707},"sourceProvider":"cortecs"},"cortecs/nova-2-lite":{"id":"cortecs/nova-2-lite","name":"nova-2-lite","description":"Nova 2 Lite is an advanced multimodal reasoning model that combines efficiency and performance, delivering reliable AI for agentic workflows and enterprise applications.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.373,"output":3.144},"sourceProvider":"cortecs"},"cortecs/nova-lite-v1":{"id":"cortecs/nova-lite-v1","name":"nova-lite-v1","description":"Nova Lite is a fast, low-cost multimodal foundation model capable of reasoning over text, images, and video in 200+ languages.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.069,"output":0.275},"sourceProvider":"cortecs"},"cortecs/nova-micro-v1":{"id":"cortecs/nova-micro-v1","name":"nova-micro-v1","description":"Nova Micro is a multilingual text-to-text foundation model with strong reasoning capabilities and broad language coverage across 200+ languages.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.04,"output":0.159},"sourceProvider":"cortecs"},"cortecs/nova-pro-v1":{"id":"cortecs/nova-pro-v1","name":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5000},"cost":{"input":0.918,"output":3.671},"sourceProvider":"cortecs"},"cortecs/nvidia-nemotron-3-nano-30b-a3b":{"id":"cortecs/nvidia-nemotron-3-nano-30b-a3b","name":"nvidia-nemotron-3-nano-30b-a3b","description":"Nemotron-Nano-3-30B-A3B is a compact Mixture-of-Experts model optimized for efficient reasoning, chat, and coding, with strong multilingual support and long-context RAG and agent workflows.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-01-12","last_updated":"2026-01-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.06,"output":0.24},"sourceProvider":"cortecs"},"cortecs/nvidia-nemotron-3-nano-omni":{"id":"cortecs/nvidia-nemotron-3-nano-omni","name":"nvidia-nemotron-3-nano-omni","description":"Nemotron-3-Nano-Omni is an open, efficient omni-modal reasoning model that unifies text, image, audio, and video for agentic AI workflows.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.059,"output":0.237},"sourceProvider":"cortecs"},"cortecs/pixtral-12b-2409":{"id":"cortecs/pixtral-12b-2409","name":"pixtral-12b-2409","description":"Pixtral 2409 12B is a state-of-the-art multimodal model with 12B parameters and a 400M vision encoder, natively trained on interleaved text and image data. It excels in tasks spanning vision-language reasoning, instruction following, and pure text understanding, making it highly effective for real-world multimodal applications.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2024-11-09","last_updated":"2024-11-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.223,"output":0.223},"sourceProvider":"cortecs"},"cortecs/pixtral-large-2502":{"id":"cortecs/pixtral-large-2502","name":"pixtral-large-2502","description":"Pixtral Large (25.02) is a 124B open-weight multimodal model built on Mistral Large 2, offering advanced image understanding and strong performance across text and code tasks.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-05-26","last_updated":"2025-05-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":1.993,"output":5.978},"sourceProvider":"cortecs"},"cortecs/qwen2.5-vl-72b-instruct":{"id":"cortecs/qwen2.5-vl-72b-instruct","name":"qwen2.5-vl-72b-instruct","description":"Qwen2.5-VL is a powerful vision-language model with advanced capabilities in visual understanding, long video reasoning, and structured output generation.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.25,"output":0.747},"sourceProvider":"cortecs"},"cortecs/qwen3-235b-a22b-instruct-2507":{"id":"cortecs/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":131000},"cost":{"input":0.069,"output":0.455,"cache_read":0.018},"sourceProvider":"cortecs"},"cortecs/qwen3-30b-a3b-instruct-2507":{"id":"cortecs/qwen3-30b-a3b-instruct-2507","name":"qwen3-30b-a3b-instruct-2507","description":"Qwen3-30B-A3B-Instruct-2507 is an advanced Mixture-of-Experts model optimized for reasoning, coding, and multilingual instruction following.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.099,"output":0.299},"sourceProvider":"cortecs"},"cortecs/qwen3-32b":{"id":"cortecs/qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40000,"output":40000},"cost":{"input":0.099,"output":0.299},"sourceProvider":"cortecs"},"cortecs/qwen3-coder-30b-a3b-instruct":{"id":"cortecs/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262000},"cost":{"input":0.067,"output":0.245,"cache_read":0.014},"sourceProvider":"cortecs"},"cortecs/qwen3-coder-next":{"id":"cortecs/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.167,"output":0.891},"sourceProvider":"cortecs"},"cortecs/qwen3-next-80b-a3b-thinking":{"id":"cortecs/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.149,"output":1.195},"sourceProvider":"cortecs"},"cortecs/qwen3-vl-235b-a22b":{"id":"cortecs/qwen3-vl-235b-a22b","name":"qwen3-vl-235b-a22b","description":"Qwen3 VL 235B A22B is a 235B-parameter MoE vision-language flagship model (≈22B active) designed for frontier-level multimodal understanding across text, images, documents, and long videos.","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-01-13","last_updated":"2026-01-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.617,"output":3.119,"cache_read":0.052},"sourceProvider":"cortecs"},"cortecs/qwen3.5-122b-a10b":{"id":"cortecs/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.495,"output":3.46,"cache_read":0.124},"sourceProvider":"cortecs"},"cortecs/qwen3.5-397b-a17b":{"id":"cortecs/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":250000},"cost":{"input":0.668,"output":4.01},"sourceProvider":"cortecs"},"cortecs/qwen3.5-9b":{"id":"cortecs/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.111,"output":0.167},"sourceProvider":"cortecs"},"cortecs/qwen3.6-27b":{"id":"cortecs/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.446,"output":3.008},"sourceProvider":"cortecs"},"cortecs/qwen3.6-35b-a3b":{"id":"cortecs/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.167,"output":0.557},"sourceProvider":"cortecs"},"cortecs/qwen3.8-2.4t-a95b":{"id":"cortecs/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.5,"output":6,"cache_read":0.625},"sourceProvider":"cortecs"},"cortecs/qwen3.8-27b":{"id":"cortecs/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.334,"output":2.451,"cache_read":0.111},"sourceProvider":"cortecs"},"cortecs/qwen3guard-gen-0.6b":{"id":"cortecs/qwen3guard-gen-0.6b","name":"qwen3guard-gen-0.6b","description":"Qwen3Guard-Gen-0.6B is a lightweight multilingual safety moderation model that classifies prompts and responses into safe, controversial, or unsafe categories.","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"cortecs"},"cortecs/qwen3guard-gen-8b":{"id":"cortecs/qwen3guard-gen-8b","name":"qwen3guard-gen-8b","description":"Qwen3Guard-Gen-8B is a large-scale multilingual safety moderation model designed for high-accuracy prompt and response classification.","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"cortecs"},"cortecs/voxtral-small-2507":{"id":"cortecs/voxtral-small-2507","name":"voxtral-small-2507","description":"Voxtral Small is a multimodal model with audio input, combining advanced speech capabilities with strong text performance for transcription, translation, and audio understanding.","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.111,"output":0.334,"cache_read":0.011},"sourceProvider":"cortecs"},"crof/deepseek-v3.2":{"id":"crof/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":0.18,"output":0.35,"cache_read":0.04},"sourceProvider":"crof"},"crof/deepseek-v4-flash":{"id":"crof/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.12,"output":0.21,"cache_read":0.003},"sourceProvider":"crof"},"crof/deepseek-v4-flash-0731":{"id":"crof/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash (New)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.12,"output":0.21,"cache_read":0.003},"sourceProvider":"crof"},"crof/deepseek-v4-pro":{"id":"crof/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.35,"output":0.8,"cache_read":0.003},"sourceProvider":"crof"},"crof/deepseek-v4-pro-lightning":{"id":"crof/deepseek-v4-pro-lightning","name":"DeepSeek V4 Pro Lightning","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.8,"output":1.6,"cache_read":0.02},"sourceProvider":"crof"},"crof/gemma-4-31b-it":{"id":"crof/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"crof"},"crof/glm-5.1":{"id":"crof/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.45,"output":2.15,"cache_read":0.08,"cache_write":0},"sourceProvider":"crof"},"crof/glm-5.2":{"id":"crof/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.3,"output":1.05,"cache_read":0.05},"sourceProvider":"crof"},"crof/greg-1-mini":{"id":"crof/greg-1-mini","name":"Greg 1 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":0.07,"output":0.15,"cache_read":0.01},"sourceProvider":"crof"},"crof/greg-2-super":{"id":"crof/greg-2-super","name":"Greg 2 Super","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-06-14","last_updated":"2026-06-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":1.5,"output":5,"cache_read":0.25},"sourceProvider":"crof"},"crof/greg-2-ultra":{"id":"crof/greg-2-ultra","name":"Greg 2 Ultra","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-06-14","last_updated":"2026-06-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":3,"output":10,"cache_read":0.5},"sourceProvider":"crof"},"crof/greg-rp":{"id":"crof/greg-rp","name":"Greg (Roleplay)","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"output":229376},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"crof"},"crof/kimi-k2.6":{"id":"crof/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.5,"output":1.99,"cache_read":0.05},"sourceProvider":"crof"},"crof/kimi-k2.7-code":{"id":"crof/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.55,"output":2.25,"cache_read":0.05},"sourceProvider":"crof"},"crof/kimi-k3":{"id":"crof/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2,"output":8,"cache_read":0.25},"sourceProvider":"crof"},"crof/kimi-k3-eco":{"id":"crof/kimi-k3-eco","name":"Kimi K3 Eco","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":1,"output":4,"cache_read":0.1},"sourceProvider":"crof"},"crof/mimo-v2.5-pro":{"id":"crof/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.4,"output":0.8,"cache_read":0.003,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"crof"},"crof/qwen3.5-397b-a17b":{"id":"crof/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.35,"output":1.75,"cache_read":0.07},"sourceProvider":"crof"},"crof/qwen3.5-9b":{"id":"crof/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-13","last_updated":"2026-03-13","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.04,"output":0.15,"cache_read":0.008},"sourceProvider":"crof"},"crof/qwen3.6-27b":{"id":"crof/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.2,"output":1.5,"cache_read":0.04},"sourceProvider":"crof"},"crof/qwen3.8-27b":{"id":"crof/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.25,"output":2.1,"cache_read":0.06},"sourceProvider":"crof"},"crossmodel/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"crossmodel"},"crossmodel/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"crossmodel"},"crossmodel/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.405,"output":1.215,"cache_read":0.0135,"cache_write":0.405},"sourceProvider":"crossmodel"},"crossmodel/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"cost":{"input":0.405,"output":1.215,"cache_read":0.0135,"cache_write":0.405},"sourceProvider":"crossmodel"},"crossmodel/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.215,"output":3.645,"cache_read":0.0405,"cache_write":1.215},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-2.5-flash":{"id":"gemini/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-2.5-flash-lite":{"id":"gemini/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.1},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-2.5-pro":{"id":"gemini/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5}},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3-flash-preview":{"id":"gemini/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.5},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3.1-pro-preview":{"id":"gemini/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":4}},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3.5-flash":{"id":"gemini/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":1.5},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3.5-flash-lite":{"id":"gemini/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3.6-flash":{"id":"gemini/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.5},"sourceProvider":"crossmodel"},"crossmodel/gemini/gemini-3.7-flash":{"id":"gemini/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.75},"sourceProvider":"crossmodel"},"crossmodel/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.42},"sourceProvider":"crossmodel"},"crossmodel/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":512000},"cost":{"input":0.33,"output":1.32,"cache_read":0.066,"cache_write":0.33,"tiers":[{"input":0.66,"output":2.63,"cache_read":0.132,"cache_write":0.66,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.66,"output":2.63,"cache_read":0.132,"cache_write":0.66}},"sourceProvider":"crossmodel"},"crossmodel/moonshot/kimi-k2.5":{"id":"moonshot/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.62,"output":3.3,"cache_read":0.11,"cache_write":0.62},"sourceProvider":"crossmodel"},"crossmodel/moonshot/kimi-k2.6":{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1,"output":4.16,"cache_read":0.18,"cache_write":1},"sourceProvider":"crossmodel"},"crossmodel/moonshot/kimi-k2.7-code":{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1,"output":4.16,"cache_read":0.18,"cache_write":1},"sourceProvider":"crossmodel"},"crossmodel/moonshot/kimi-k3":{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":5}},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":10}},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"crossmodel"},"crossmodel/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.19,"output":1.13,"cache_read":0.019,"cache_write":0.24,"tiers":[{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.94,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.94}},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.32,"output":1.88,"cache_read":0.032,"cache_write":0.4,"tiers":[{"input":1.25,"output":7.5,"cache_read":0.124,"cache_write":1.57,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.25,"output":7.5,"cache_read":0.124,"cache_write":1.57}},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.7-flash":{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.04,"output":0.13,"cache_read":0.01,"cache_write":0.04,"tiers":[{"input":0.1,"output":0.37,"cache_read":0.02,"cache_write":0.12,"tier":{"type":"context","size":32000}},{"input":0.19,"output":0.74,"cache_read":0.04,"cache_write":0.24,"tier":{"type":"context","size":256000}}]},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.504,"output":4.504,"cache_read":0.3,"cache_write":1.88},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.288,"output":1.125,"cache_read":0.0288,"cache_write":0.36,"tiers":[{"input":0.864,"output":3.375,"cache_read":0.0864,"cache_write":1.08,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.864,"output":3.375,"cache_read":0.0864,"cache_write":1.08}},"sourceProvider":"crossmodel"},"crossmodel/qwen/qwen3.8-max":{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.88,"output":5.63,"cache_read":0.23,"cache_write":2.35},"sourceProvider":"crossmodel"},"crossmodel/tencent/hy3":{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.16,"output":0.64,"cache_read":0.04,"cache_write":0.16},"sourceProvider":"crossmodel"},"crossmodel/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"cache_write":1.25,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4,"cache_write":2.5}},"sourceProvider":"crossmodel"},"crossmodel/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":0.6,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6,"cache_write":4}},"sourceProvider":"crossmodel"},"crossmodel/x-ai/grok-4.6":{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2,"tiers":[{"input":4,"output":12,"cache_read":1,"cache_write":4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1,"cache_write":4}},"sourceProvider":"crossmodel"},"crossmodel/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"cache_write":1,"tiers":[{"input":2,"output":4,"cache_read":0.4,"cache_write":2,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4,"cache_write":2}},"sourceProvider":"crossmodel"},"crossmodel/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.16,"output":0.32,"cache_read":0.004,"cache_write":0.16},"sourceProvider":"crossmodel"},"crossmodel/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.47,"output":0.94,"cache_read":0.005,"cache_write":0.47},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.47,"output":2.16,"cache_read":0.1,"cache_write":0.47,"tiers":[{"input":0.62,"output":2.47,"cache_read":0.13,"cache_write":0.62,"tier":{"type":"context","size":32000}}]},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":3,"cache_read":0.16,"cache_write":0.6,"tiers":[{"input":0.8,"output":3.4,"cache_read":0.2,"cache_write":0.8,"tier":{"type":"context","size":32000}}]},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.9,"output":3.7,"cache_read":0.18,"cache_write":0.9,"tiers":[{"input":1.1,"output":4.3,"cache_read":0.27,"cache_write":1.1,"tier":{"type":"context","size":32000}}]},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1,"output":3.8,"cache_read":0.2,"cache_write":1,"tiers":[{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2,"tier":{"type":"context","size":32000}}]},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2},"sourceProvider":"crossmodel"},"crossmodel/z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.4,"cache_read":0.3,"cache_write":1.2},"sourceProvider":"crossmodel"},"crusoe/deepseek-ai/DeepSeek-V3-0324":{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.5,"output":1.5,"cache_read":0.25},"sourceProvider":"crusoe"},"crusoe/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4,"cache_read":0.14},"sourceProvider":"crusoe"},"crusoe/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.25,"output":0.75,"cache_read":0.13},"sourceProvider":"crusoe"},"crusoe/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7,"output":3.5,"cache_read":0.35},"sourceProvider":"crusoe"},"crusoe/nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B":{"id":"nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.3,"output":1.83,"cache_read":0.3,"input_audio":0.5},"sourceProvider":"crusoe"},"crusoe/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2,"cache_read":0.05},"sourceProvider":"crusoe"},"crusoe/zai/GLM-5.1":{"id":"zai/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4.4,"cache_read":0.25},"sourceProvider":"crusoe"},"crusoe/zai/GLM-5.2":{"id":"zai/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"crusoe"},"daoxe/claude-haiku-4-5-20251001":{"id":"daoxe/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":5},"sourceProvider":"daoxe"},"daoxe/claude-opus-4-8":{"id":"daoxe/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"daoxe"},"daoxe/claude-sonnet-4-6":{"id":"daoxe/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"daoxe"},"daoxe/gemini-3.1-pro-preview":{"id":"daoxe/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"daoxe"},"daoxe/gpt-5.4":{"id":"daoxe/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"daoxe"},"daoxe/gpt-5.5":{"id":"daoxe/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"daoxe"},"daoxe/grok-4.3":{"id":"daoxe/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"daoxe"},"daoxe/grok-4.5":{"id":"daoxe/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"daoxe"},"daoxe/kimi-k2.5":{"id":"daoxe/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"daoxe"},"databricks/databricks-claude-haiku-4-5":{"id":"databricks/databricks-claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"databricks"},"databricks/databricks-claude-opus-4-1":{"id":"databricks/databricks-claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"databricks"},"databricks/databricks-claude-opus-4-5":{"id":"databricks/databricks-claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"databricks"},"databricks/databricks-claude-opus-4-6":{"id":"databricks/databricks-claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"databricks"},"databricks/databricks-claude-opus-4-7":{"id":"databricks/databricks-claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"databricks"},"databricks/databricks-claude-sonnet-4":{"id":"databricks/databricks-claude-sonnet-4","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"databricks"},"databricks/databricks-claude-sonnet-4-5":{"id":"databricks/databricks-claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"databricks"},"databricks/databricks-claude-sonnet-4-6":{"id":"databricks/databricks-claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"databricks"},"databricks/databricks-gemini-2-5-flash":{"id":"databricks/databricks-gemini-2-5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"databricks"},"databricks/databricks-gemini-2-5-pro":{"id":"databricks/databricks-gemini-2-5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"databricks"},"databricks/databricks-gemini-3-1-flash-lite":{"id":"databricks/databricks-gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"databricks"},"databricks/databricks-gemini-3-1-pro":{"id":"databricks/databricks-gemini-3-1-pro","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"databricks"},"databricks/databricks-gemini-3-flash":{"id":"databricks/databricks-gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"databricks"},"databricks/databricks-gemini-3-pro":{"id":"databricks/databricks-gemini-3-pro","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"databricks"},"databricks/databricks-glm-5-2":{"id":"databricks/databricks-glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"databricks"},"databricks/databricks-gpt-5":{"id":"databricks/databricks-gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-1":{"id":"databricks/databricks-gpt-5-1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-2":{"id":"databricks/databricks-gpt-5-2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-4":{"id":"databricks/databricks-gpt-5-4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-4-mini":{"id":"databricks/databricks-gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-4-nano":{"id":"databricks/databricks-gpt-5-4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-5":{"id":"databricks/databricks-gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-6-luna":{"id":"databricks/databricks-gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"tiers":[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2}},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-6-sol":{"id":"databricks/databricks-gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-6-terra":{"id":"databricks/databricks-gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-mini":{"id":"databricks/databricks-gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"databricks"},"databricks/databricks-gpt-5-nano":{"id":"databricks/databricks-gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"databricks"},"databricks/databricks-gpt-oss-120b":{"id":"databricks/databricks-gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.072,"output":0.28},"sourceProvider":"databricks"},"databricks/databricks-gpt-oss-20b":{"id":"databricks/databricks-gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2},"sourceProvider":"databricks"},"databricks/databricks-kimi-k2-7-code":{"id":"databricks/databricks-kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"databricks"},"deepinfra/ByteDance/Seed-2.0-code":{"id":"ByteDance/Seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":1,"output":6,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"sourceProvider":"deepinfra"},"deepinfra/ByteDance/Seed-2.0-mini":{"id":"ByteDance/Seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.1,"output":0.4,"cache_read":0.02,"tiers":[{"input":0.2,"output":0.8,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"sourceProvider":"deepinfra"},"deepinfra/ByteDance/Seed-2.0-pro":{"id":"ByteDance/Seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.5,"output":3,"cache_read":0.1,"tiers":[{"input":1,"output":6,"cache_read":0.2,"tier":{"type":"context","size":128000}}]},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":64000},"cost":{"input":0.5,"output":2.15,"cache_read":0.35},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.32,"output":0.89},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V3-0324":{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.24,"output":0.9,"cache_read":0.135},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.25,"output":0.95,"cache_read":0.13},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":64000},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.09,"output":0.18,"cache_read":0.018},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.08,"output":0.18,"cache_read":0.016},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"sourceProvider":"deepinfra"},"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"sourceProvider":"deepinfra"},"deepinfra/google/gemma-4-26B-A4B-it":{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"sourceProvider":"deepinfra"},"deepinfra/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38},"sourceProvider":"deepinfra"},"deepinfra/google/gemma-4-E4B-it":{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.02,"output":0.1},"sourceProvider":"deepinfra"},"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Llama 3.3 70B Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.32},"sourceProvider":"deepinfra"},"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.2,"output":0.8},"sourceProvider":"deepinfra"},"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct":{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"Llama 4 Scout 17B","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":327680,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"deepinfra"},"deepinfra/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"status":"deprecated","cost":{"input":0.15,"output":1.15,"cache_read":0.03},"sourceProvider":"deepinfra"},"deepinfra/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.25,"output":1,"cache_read":0.05},"sourceProvider":"deepinfra"},"deepinfra/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":128000},"cost":{"input":0.28,"output":1.1,"cache_read":0.056},"sourceProvider":"deepinfra"},"deepinfra/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"deepinfra"},"deepinfra/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.75,"output":3.5,"cache_read":0.15},"sourceProvider":"deepinfra"},"deepinfra/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.68,"output":3.4,"cache_read":0.136},"sourceProvider":"deepinfra"},"deepinfra/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.85,"output":14.25,"cache_read":0.285},"sourceProvider":"deepinfra"},"deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5":{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0.4,"output":0.4},"sourceProvider":"deepinfra"},"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B":{"id":"nvidia/Nemotron-3-Nano-30B-A3B","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.025},"sourceProvider":"deepinfra"},"deepinfra/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning":{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.2,"output":0.8},"sourceProvider":"deepinfra"},"deepinfra/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.037,"output":0.17},"sourceProvider":"deepinfra"},"deepinfra/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.03,"output":0.14},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":0.55},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-30B-A3B":{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.08,"output":0.28},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","name":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.3,"output":1,"cache_read":0.1},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-Max":{"id":"Qwen/Qwen3-Max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6,"cache_read":0.24,"tiers":[{"input":2.4,"output":12,"cache_read":0.48,"tier":{"type":"context","size":32000}},{"input":3,"output":15,"cache_read":0.6,"tier":{"type":"context","size":128000}}]},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":1.1},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.5-122B-A10B":{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":2.4},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.5-27B":{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.26,"output":2.6},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.5-35B-A3B":{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-01","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.14,"output":1,"cache_read":0.05},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen 3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-01","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.45,"output":3,"cache_read":0.22},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.15},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.32,"output":3.2},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.1,"output":0.95},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.7-Max":{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"tiers":[{"input":5,"output":15,"cache_read":1,"tier":{"type":"context","size":32000}},{"input":6.25,"output":18.5,"cache_read":1.25,"tier":{"type":"context","size":128000}}]},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.8-2.4T-A95B":{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.8-27B":{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":3,"cache_read":0.04},"sourceProvider":"deepinfra"},"deepinfra/Qwen/Qwen3.8-Max":{"id":"Qwen/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":1.65,"output":4.951,"cache_read":0.206},"sourceProvider":"deepinfra"},"deepinfra/stepfun-ai/Step-3.7-Flash":{"id":"stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"deepinfra"},"deepinfra/tencent/Hy3":{"id":"tencent/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"sourceProvider":"deepinfra"},"deepinfra/thinkingmachines/Inkling":{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"sourceProvider":"deepinfra"},"deepinfra/thinkingmachines/Inkling-Small":{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"sourceProvider":"deepinfra"},"deepinfra/XiaomiMiMo/MiMo-V2.5":{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.4,"output":2,"cache_read":0.08},"sourceProvider":"deepinfra"},"deepinfra/XiaomiMiMo/MiMo-V2.5-Pro":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":1,"output":3,"cache_read":0.2},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-4.6":{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.1},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.4,"output":1.75,"cache_read":0.08},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-4.7-Flash":{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.6,"output":2.08,"cache_read":0.12},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":1.05,"output":3.5,"cache_read":0.205},"sourceProvider":"deepinfra"},"deepinfra/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.75,"output":2.4,"cache_read":0.14},"sourceProvider":"deepinfra"},"deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"deepseek"},"deepseek/deepseek-reasoner":{"id":"deepseek/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"reasoning":0.28,"cache_read":0.0028},"sourceProvider":"deepseek"},"deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"reasoning":0.28,"cache_read":0.0028},"sourceProvider":"deepseek"},"deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"status":"beta","cost":{"input":0.14,"output":0.28,"reasoning":0.28,"cache_read":0.0028},"sourceProvider":"deepseek"},"deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"reasoning":0.87,"cache_read":0.003625},"sourceProvider":"deepseek"},"digitalocean/alibaba-qwen3-32b":{"id":"digitalocean/alibaba-qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.25,"output":0.55},"sourceProvider":"digitalocean"},"digitalocean/all-mini-lm-l6-v2":{"id":"digitalocean/all-mini-lm-l6-v2","name":"All-MiniLM-L6-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256,"output":384},"cost":{"input":0.009,"output":0},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-3-opus":{"id":"digitalocean/anthropic-claude-3-opus","name":"Claude 3 Opus","description":"Legacy model retained for compatibility with older integrations","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-08","release_date":"2024-02-29","last_updated":"2024-02-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-3.5-haiku":{"id":"digitalocean/anthropic-claude-3.5-haiku","name":"Claude 3.5 Haiku","description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-11-05","last_updated":"2024-11-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":0.8,"output":4,"cache_read":0.08,"cache_write":1},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-3.5-sonnet":{"id":"digitalocean/anthropic-claude-3.5-sonnet","name":"Claude 3.5 Sonnet","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-06-20","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-3.7-sonnet":{"id":"digitalocean/anthropic-claude-3.7-sonnet","name":"Claude 3.7 Sonnet","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-02-24","last_updated":"2025-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-4.1-opus":{"id":"digitalocean/anthropic-claude-4.1-opus","name":"Anthropic Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-4.5-haiku":{"id":"digitalocean/anthropic-claude-4.5-haiku","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":1,"cache_write":1.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-4.5-sonnet":{"id":"digitalocean/anthropic-claude-4.5-sonnet","name":"Anthropic Claude 4.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-4.6-sonnet":{"id":"digitalocean/anthropic-claude-4.6-sonnet","name":"Anthropic Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-5-sonnet":{"id":"digitalocean/anthropic-claude-5-sonnet","name":"Anthropic Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-fable-5":{"id":"digitalocean/anthropic-claude-fable-5","name":"Anthropic Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-06-09","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-haiku-4.5":{"id":"digitalocean/anthropic-claude-haiku-4.5","name":"Anthropic Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-4":{"id":"digitalocean/anthropic-claude-opus-4","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-4.5":{"id":"digitalocean/anthropic-claude-opus-4.5","name":"Anthropic Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-4.6":{"id":"digitalocean/anthropic-claude-opus-4.6","name":"Anthropic Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-4.7":{"id":"digitalocean/anthropic-claude-opus-4.7","name":"Anthropic Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-4.8":{"id":"digitalocean/anthropic-claude-opus-4.8","name":"Anthropic Claude Opus 4.8","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-opus-5":{"id":"digitalocean/anthropic-claude-opus-5","name":"Anthropic Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"digitalocean"},"digitalocean/anthropic-claude-sonnet-4":{"id":"digitalocean/anthropic-claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.3,"cache_write":3.75}},"sourceProvider":"digitalocean"},"digitalocean/arcee-trinity-large-thinking":{"id":"digitalocean/arcee-trinity-large-thinking","name":"Arcee Trinity Large Thinking (Public Preview)","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.25,"output":0.9,"cache_read":0.06},"sourceProvider":"digitalocean"},"digitalocean/bge-m3":{"id":"digitalocean/bge-m3","name":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-01-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0.02,"output":0},"sourceProvider":"digitalocean"},"digitalocean/bge-reranker-v2-m3":{"id":"digitalocean/bge-reranker-v2-m3","name":"BGE Reranker v2 M3","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"bge","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-03-12","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1},"cost":{"input":0.01,"output":0},"sourceProvider":"digitalocean"},"digitalocean/deepseek-3.2":{"id":"digitalocean/deepseek-3.2","name":"Deepseek 3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-12-02","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":0.8,"cache_read":0.075},"sourceProvider":"digitalocean"},"digitalocean/deepseek-4-flash":{"id":"digitalocean/deepseek-4-flash","name":"Deepseek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-05-27","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":384000},"cost":{"input":0.0679,"output":0.168,"cache_read":0.0168},"sourceProvider":"digitalocean"},"digitalocean/deepseek-r1-distill-llama-70b":{"id":"digitalocean/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32678,"output":8192},"cost":{"input":0.99,"output":0.99},"sourceProvider":"digitalocean"},"digitalocean/deepseek-v3":{"id":"digitalocean/deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":131072},"sourceProvider":"digitalocean"},"digitalocean/deepseek-v4-flash-0731":{"id":"digitalocean/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.08,"output":0.252,"cache_read":0.0252},"sourceProvider":"digitalocean"},"digitalocean/deepseek-v4-pro":{"id":"digitalocean/deepseek-v4-pro","name":"Deepseek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.87,"output":1.74,"cache_read":0.174},"sourceProvider":"digitalocean"},"digitalocean/deepseek-v4-pro-0813":{"id":"digitalocean/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"digitalocean"},"digitalocean/e5-large-v2":{"id":"digitalocean/e5-large-v2","name":"E5 Large v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-05-19","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":1024},"cost":{"input":0.02,"output":0},"sourceProvider":"digitalocean"},"digitalocean/fal-ai/elevenlabs/tts/multilingual-v2":{"id":"fal-ai/elevenlabs/tts/multilingual-v2","name":"ElevenLabs Multilingual TTS v2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-08-22","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"digitalocean"},"digitalocean/fal-ai/fast-sdxl":{"id":"fal-ai/fast-sdxl","name":"Fast SDXL","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-07-26","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":0,"output":0},"sourceProvider":"digitalocean"},"digitalocean/fal-ai/flux/schnell":{"id":"fal-ai/flux/schnell","name":"FLUX.1 [schnell]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-08-01","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":0,"output":0},"sourceProvider":"digitalocean"},"digitalocean/fal-ai/stable-audio-25/text-to-audio":{"id":"fal-ai/stable-audio-25/text-to-audio","name":"Stable Audio 2.5 (Text-to-Audio)","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-10-08","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"digitalocean"},"digitalocean/gemma-4-31B-it":{"id":"digitalocean/gemma-4-31B-it","name":"Gemma 4","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.18,"output":0.5,"cache_read":0.036},"sourceProvider":"digitalocean"},"digitalocean/glm-5":{"id":"digitalocean/glm-5","name":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":64000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"digitalocean"},"digitalocean/glm-5.1":{"id":"digitalocean/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":1.3,"output":4.3,"cache_read":0.26},"sourceProvider":"digitalocean"},"digitalocean/glm-5.2":{"id":"digitalocean/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7,"output":2.2,"cache_read":0.105},"sourceProvider":"digitalocean"},"digitalocean/gte-large-en-v1.5":{"id":"digitalocean/gte-large-en-v1.5","name":"GTE Large (v1.5)","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-03-27","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0.09,"output":0},"sourceProvider":"digitalocean"},"digitalocean/kimi-k2.5":{"id":"digitalocean/kimi-k2.5","name":"Kimi K2.5","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.7,"cache_read":0.203},"sourceProvider":"digitalocean"},"digitalocean/kimi-k2.6":{"id":"digitalocean/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"digitalocean"},"digitalocean/kimi-k3":{"id":"digitalocean/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2.85,"output":14.25,"cache_read":0.285},"sourceProvider":"digitalocean"},"digitalocean/llama-4-maverick":{"id":"digitalocean/llama-4-maverick","name":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.696},"sourceProvider":"digitalocean"},"digitalocean/llama3-8b-instruct":{"id":"digitalocean/llama3-8b-instruct","name":"Llama 3.1 Instruct (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.198,"output":0.198},"sourceProvider":"digitalocean"},"digitalocean/llama3.3-70b-instruct":{"id":"digitalocean/llama3.3-70b-instruct","name":"Llama 3.3 Instruct (70B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.65,"output":0.65},"sourceProvider":"digitalocean"},"digitalocean/mimo-v2.5-pro":{"id":"digitalocean/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":1.5,"cache_read":0.08},"sourceProvider":"digitalocean"},"digitalocean/minimax-m2.5":{"id":"digitalocean/minimax-m2.5","name":"MiniMax M2.5 (Public Preview)","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-12","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"digitalocean"},"digitalocean/ministral-3-8b-instruct-2512":{"id":"digitalocean/ministral-3-8b-instruct-2512","name":"Ministral 3 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"digitalocean"},"digitalocean/mistral-3-14B":{"id":"digitalocean/mistral-3-14B","name":"Ministral 3 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.2,"output":0.2},"sourceProvider":"digitalocean"},"digitalocean/mistral-7b-instruct-v0.3":{"id":"digitalocean/mistral-7b-instruct-v0.3","name":"Mistral 7B Instruct v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-05-22","last_updated":"2024-05-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"sourceProvider":"digitalocean"},"digitalocean/mistral-nemo-instruct-2407":{"id":"digitalocean/mistral-nemo-instruct-2407","name":"Mistral Nemo Instruct","description":"Legacy model retained for compatibility with older integrations","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"status":"deprecated","cost":{"input":0.3,"output":0.3},"sourceProvider":"digitalocean"},"digitalocean/multi-qa-mpnet-base-dot-v1":{"id":"digitalocean/multi-qa-mpnet-base-dot-v1","name":"Multi-QA-mpnet-base-dot-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":768},"cost":{"input":0.009,"output":0},"sourceProvider":"digitalocean"},"digitalocean/nemotron-3-nano-30b":{"id":"digitalocean/nemotron-3-nano-30b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"digitalocean"},"digitalocean/nemotron-3-nano-omni":{"id":"digitalocean/nemotron-3-nano-omni","name":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":0.9},"sourceProvider":"digitalocean"},"digitalocean/nemotron-3-ultra-550b":{"id":"digitalocean/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.9,"output":1.7},"sourceProvider":"digitalocean"},"digitalocean/nemotron-nano-12b-v2-vl":{"id":"digitalocean/nemotron-nano-12b-v2-vl","name":"Nemotron-nano 12b v2-vl","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.2,"output":0.6},"sourceProvider":"digitalocean"},"digitalocean/nvidia-nemotron-3-super-120b":{"id":"digitalocean/nvidia-nemotron-3-super-120b","name":"NVIDIA Nemotron 3 Super 120B  (Public Preview)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.3,"output":0.65,"cache_read":0.06},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-4.1":{"id":"digitalocean/openai-gpt-4.1","name":"OpenAI GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-4o":{"id":"digitalocean/openai-gpt-4o","name":"OpenAI GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-4o-mini":{"id":"digitalocean/openai-gpt-4o-mini","name":"OpenAI GPT-4o mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5":{"id":"digitalocean/openai-gpt-5","name":"OpenAI GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5-mini":{"id":"digitalocean/openai-gpt-5-mini","name":"OpenAI GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5-nano":{"id":"digitalocean/openai-gpt-5-nano","name":"OpenAI GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.1-codex-max":{"id":"digitalocean/openai-gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.2":{"id":"digitalocean/openai-gpt-5.2","name":"OpenAI GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.2-pro":{"id":"digitalocean/openai-gpt-5.2-pro","name":"OpenAI GPT-5.2 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.3-codex":{"id":"digitalocean/openai-gpt-5.3-codex","name":"OpenAI GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.4":{"id":"digitalocean/openai-gpt-5.4","name":"OpenAI GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.4-mini":{"id":"digitalocean/openai-gpt-5.4-mini","name":"OpenAI GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.4-nano":{"id":"digitalocean/openai-gpt-5.4-nano","name":"OpenAI GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.4-pro":{"id":"digitalocean/openai-gpt-5.4-pro","name":"OpenAI GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.5":{"id":"digitalocean/openai-gpt-5.5","name":"OpenAI GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.6-luna":{"id":"digitalocean/openai-gpt-5.6-luna","name":"OpenAI GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.6-sol":{"id":"digitalocean/openai-gpt-5.6-sol","name":"OpenAI GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-5.6-terra":{"id":"digitalocean/openai-gpt-5.6-terra","name":"OpenAI GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-image-1":{"id":"digitalocean/openai-gpt-image-1","name":"GPT Image 1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":40,"cache_read":1.25},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-image-1.5":{"id":"digitalocean/openai-gpt-image-1.5","name":"OpenAI GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["image","text"]},"open_weights":false,"limit":{"context":0,"output":16384},"cost":{"input":5,"output":10,"cache_read":1},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-image-2":{"id":"digitalocean/openai-gpt-image-2","name":"OpenAI GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image","text"]},"open_weights":false,"limit":{"context":0,"output":16384},"cost":{"input":8,"output":30},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-oss-120b":{"id":"digitalocean/openai-gpt-oss-120b","name":"OpenAI GPT-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.055,"output":0.385,"cache_read":0.02},"sourceProvider":"digitalocean"},"digitalocean/openai-gpt-oss-20b":{"id":"digitalocean/openai-gpt-oss-20b","name":"OpenAI GPT-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.45},"sourceProvider":"digitalocean"},"digitalocean/openai-o1":{"id":"digitalocean/openai-o1","name":"OpenAI o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"digitalocean"},"digitalocean/openai-o3":{"id":"digitalocean/openai-o3","name":"OpenAI o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"digitalocean"},"digitalocean/openai-o3-mini":{"id":"digitalocean/openai-o3-mini","name":"OpenAI o3 mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"digitalocean"},"digitalocean/qwen-2.5-14b-instruct":{"id":"digitalocean/qwen-2.5-14b-instruct","name":"Qwen 2.5 14B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"sourceProvider":"digitalocean"},"digitalocean/qwen3-coder-flash":{"id":"digitalocean/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":1.7,"cache_read":0.09},"sourceProvider":"digitalocean"},"digitalocean/qwen3-embedding-0.6b":{"id":"digitalocean/qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":1024},"status":"beta","cost":{"input":0.04,"output":0},"sourceProvider":"digitalocean"},"digitalocean/qwen3-tts-voicedesign":{"id":"digitalocean/qwen3-tts-voicedesign","name":"Qwen3 TTS VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":32768,"output":1},"sourceProvider":"digitalocean"},"digitalocean/qwen3.5-397b-a17b":{"id":"digitalocean/qwen3.5-397b-a17b","name":"Qwen 3.5 397B A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.55,"output":3.5,"cache_read":0.111},"sourceProvider":"digitalocean"},"digitalocean/qwen3.8-max":{"id":"digitalocean/qwen3.8-max","name":"Qwen3.8-Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":262144},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"digitalocean"},"digitalocean/stable-diffusion-3.5-large":{"id":"digitalocean/stable-diffusion-3.5-large","name":"Stable Diffusion 3.5 Large","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-10-22","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":256,"output":1},"cost":{"input":0.08,"output":0},"sourceProvider":"digitalocean"},"digitalocean/wan2-2-t2v-a14b":{"id":"digitalocean/wan2-2-t2v-a14b","name":"Wan2.2-T2V-A14B","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-07-28","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["video"]},"open_weights":true,"limit":{"context":100,"output":1},"cost":{"input":0.6,"output":0},"sourceProvider":"digitalocean"},"dinference/glm-4.7":{"id":"dinference/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.45,"output":1.65},"sourceProvider":"dinference"},"dinference/glm-5":{"id":"dinference/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.75,"output":2.4},"sourceProvider":"dinference"},"dinference/glm-5.1":{"id":"dinference/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.25,"output":3.89},"sourceProvider":"dinference"},"dinference/glm-5.2":{"id":"dinference/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.25,"output":3.89},"sourceProvider":"dinference"},"dinference/gpt-oss-120b":{"id":"dinference/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08","last_updated":"2025-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.0675,"output":0.27},"sourceProvider":"dinference"},"dinference/minimax-m2.5":{"id":"dinference/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.22,"output":0.88},"sourceProvider":"dinference"},"drun/public/deepseek-r1":{"id":"public/deepseek-r1","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32000},"cost":{"input":0.55,"output":2.2},"sourceProvider":"drun"},"drun/public/deepseek-v3":{"id":"public/deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.28,"output":1.1},"sourceProvider":"drun"},"drun/public/minimax-m25":{"id":"public/minimax-m25","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"temperature":true,"release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.29,"output":1.16},"sourceProvider":"drun"},"ebcloud/DeepSeek-V4-Flash":{"id":"ebcloud/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.143,"output":0.2857},"sourceProvider":"ebcloud"},"ebcloud/DeepSeek-V4-Pro":{"id":"ebcloud/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.4286,"output":0.8571},"sourceProvider":"ebcloud"},"ebcloud/GLM-5.1":{"id":"ebcloud/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.8571,"output":3.4286},"sourceProvider":"ebcloud"},"ebcloud/Kimi-K2.6":{"id":"ebcloud/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.9286,"output":3.8571},"sourceProvider":"ebcloud"},"echo/echo":{"id":"echo/echo","name":"Echo","description":"Adaptive model for coding, reasoning, and tool-driven agent workflows through one OpenAI-compatible endpoint","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"status":"beta","cost":{"input":10,"output":50},"sourceProvider":"echo"},"edenai/amazon/moonshot.kimi-k2-thinking":{"id":"amazon/moonshot.kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":262144},"cost":{"input":0.6,"output":2.5},"sourceProvider":"edenai"},"edenai/amazon/moonshotai.kimi-k2.5":{"id":"amazon/moonshotai.kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3},"sourceProvider":"edenai"},"edenai/amazon/nvidia.nemotron-nano-9b-v2":{"id":"amazon/nvidia.nemotron-nano-9b-v2","name":"Nemotron Nano 9B v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.06,"output":0.23},"sourceProvider":"edenai"},"edenai/amazon/nvidia.nemotron-nano-9b-v2@us":{"id":"amazon/nvidia.nemotron-nano-9b-v2@us","name":"Nemotron Nano 9B v2 (US)","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":131072},"cost":{"input":0.06,"output":0.23},"sourceProvider":"edenai"},"edenai/amazon/zai.glm-4.7-flash":{"id":"amazon/zai.glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4},"sourceProvider":"edenai"},"edenai/amazon/zai.glm-4.7-flash@us":{"id":"amazon/zai.glm-4.7-flash@us","name":"GLM-4.7-Flash (US)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4},"sourceProvider":"edenai"},"edenai/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"edenai"},"edenai/anthropic/claude-fable-latest":{"id":"anthropic/claude-fable-latest","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-4-5":{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-4-5-20251101":{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-opus-latest":{"id":"anthropic/claude-opus-latest","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"edenai"},"edenai/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"edenai"},"edenai/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"edenai"},"edenai/anthropic/claude-sonnet-latest":{"id":"anthropic/claude-sonnet-latest","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"edenai"},"edenai/azure/gpt-5.1-codex":{"id":"azure/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"edenai"},"edenai/azure/gpt-5.1-codex-max":{"id":"azure/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"edenai"},"edenai/azure/gpt-5.1-codex-mini":{"id":"azure/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"edenai"},"edenai/azure/gpt-5.2-codex":{"id":"azure/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"edenai"},"edenai/cerebras/gpt-oss-120b":{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75,"cache_read":0.35},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it":{"id":"cloudflare/@cf/aisingapore/gemma-sea-lion-v4-27b-it","name":"Gemma-SEA-LION-v4-27B-IT","description":"Gemma 3 27B tuned by AI Singapore for Southeast Asian languages and instruction following","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731":{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1310720,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813":{"id":"cloudflare/@cf/deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/meta/llama-guard-3-8b":{"id":"cloudflare/@cf/meta/llama-guard-3-8b","name":"Llama-Guard-3-8B","description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.484,"output":0.03},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/openai/gpt-oss-120b":{"id":"cloudflare/@cf/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.35,"output":0.75},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/openai/gpt-oss-20b":{"id":"cloudflare/@cf/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.2,"output":0.3},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct":{"id":"cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.66,"output":1},"sourceProvider":"edenai"},"edenai/cloudflare/@cf/zai-org/glm-4.7-flash":{"id":"cloudflare/@cf/zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0605,"output":0.4},"sourceProvider":"edenai"},"edenai/cohere/command-a-03-2025":{"id":"cohere/command-a-03-2025","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":288000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"edenai"},"edenai/cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"edenai"},"edenai/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"sourceProvider":"edenai"},"edenai/cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":132000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"edenai"},"edenai/databricks/databricks-gpt-oss-120b":{"id":"databricks/databricks-gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15001,"output":0.59997},"sourceProvider":"edenai"},"edenai/databricks/databricks-gpt-oss-20b":{"id":"databricks/databricks-gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.30002},"sourceProvider":"edenai"},"edenai/deepinfra/ByteDance/Seed-2.0-code":{"id":"deepinfra/ByteDance/Seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/deepinfra/ByteDance/Seed-2.0-mini":{"id":"deepinfra/ByteDance/Seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.1,"output":0.4,"cache_read":0.02},"sourceProvider":"edenai"},"edenai/deepinfra/deepseek-ai/DeepSeek-R1":{"id":"deepinfra/deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.4},"sourceProvider":"edenai"},"edenai/deepinfra/deepseek-ai/DeepSeek-V3":{"id":"deepinfra/deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.32,"output":0.89},"sourceProvider":"edenai"},"edenai/deepinfra/deepseek-ai/DeepSeek-V3-0324":{"id":"deepinfra/deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.24,"output":0.9,"cache_read":0.135},"sourceProvider":"edenai"},"edenai/deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.08,"output":0.18,"cache_read":0.016},"sourceProvider":"edenai"},"edenai/deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct":{"id":"deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct","name":"Llama-3.2-11B-Vision-Instruct","description":"Open multimodal Llama model for image understanding, captioning, and visual QA","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.345,"output":0.345},"sourceProvider":"edenai"},"edenai/deepinfra/meta-llama/Llama-3.3-70B-Instruct":{"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.1,"output":0.32},"sourceProvider":"edenai"},"edenai/deepinfra/meta-llama/Llama-Guard-3-8B":{"id":"deepinfra/meta-llama/Llama-Guard-3-8B","name":"Llama-Guard-3-8B","description":"Llama 3.1-based safety classifier for moderating prompts and model responses","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.055,"output":0.055},"sourceProvider":"edenai"},"edenai/deepinfra/meta-models/Muse-Glimmer-30B":{"id":"deepinfra/meta-models/Muse-Glimmer-30B","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.04},"sourceProvider":"edenai"},"edenai/deepinfra/moonshotai/Kimi-K2.5":{"id":"deepinfra/moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"edenai"},"edenai/deepinfra/nemotron-3-ultra-550b-a55b":{"id":"deepinfra/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct":{"id":"deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct","name":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.6,"output":0.6},"sourceProvider":"edenai"},"edenai/deepinfra/nvidia/Nemotron-3-Nano-30B-A3B":{"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.025},"sourceProvider":"edenai"},"edenai/deepinfra/openai/gpt-oss-120b":{"id":"deepinfra/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.037,"output":0.17},"sourceProvider":"edenai"},"edenai/deepinfra/openai/gpt-oss-20b":{"id":"deepinfra/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.03,"output":0.14},"sourceProvider":"edenai"},"edenai/deepinfra/stepfun-ai/Step-3.5-Flash":{"id":"deepinfra/stepfun-ai/Step-3.5-Flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.09,"output":0.3,"cache_read":0.02},"sourceProvider":"edenai"},"edenai/deepinfra/stepfun-ai/Step-3.7-Flash":{"id":"deepinfra/stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"edenai"},"edenai/deepinfra/thinkingmachines/Inkling":{"id":"deepinfra/thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"sourceProvider":"edenai"},"edenai/deepinfra/thinkingmachines/Inkling-Small":{"id":"deepinfra/thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/deepinfra/zai-org/GLM-4.7-Flash":{"id":"deepinfra/zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"edenai"},"edenai/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":384000},"cost":{"input":0.28,"output":0.42,"cache_read":0.028},"sourceProvider":"edenai"},"edenai/deepseek/deepseek-reasoner":{"id":"deepseek/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":384000},"cost":{"input":0.28,"output":0.42,"cache_read":0.028},"sourceProvider":"edenai"},"edenai/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"edenai"},"edenai/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"edenai"},"edenai/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"edenai"},"edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731":{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"edenai"},"edenai/fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813":{"id":"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"edenai"},"edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-120b":{"id":"fireworks_ai/accounts/fireworks/models/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"edenai"},"edenai/fireworks_ai/accounts/fireworks/models/gpt-oss-20b":{"id":"fireworks_ai/accounts/fireworks/models/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"sourceProvider":"edenai"},"edenai/fireworks_ai/accounts/fireworks/models/muse-glimmer-30b":{"id":"fireworks_ai/accounts/fireworks/models/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"edenai"},"edenai/fireworks_ai/gpt-oss-120b":{"id":"fireworks_ai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.014},"sourceProvider":"edenai"},"edenai/fireworks_ai/gpt-oss-20b":{"id":"fireworks_ai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"sourceProvider":"edenai"},"edenai/flexai/deepseek-v4-flash-0731":{"id":"flexai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.08,"output":0.18},"sourceProvider":"edenai"},"edenai/flexai/DeepSeek-V4-Flash-0731":{"id":"flexai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.08,"output":0.18},"sourceProvider":"edenai"},"edenai/flexai/gpt-oss-120b":{"id":"flexai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.039,"output":0.1},"sourceProvider":"edenai"},"edenai/flexai/gpt-oss-20b":{"id":"flexai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.03,"output":0.13},"sourceProvider":"edenai"},"edenai/flexai/Muse-Glimmer-30B":{"id":"flexai/Muse-Glimmer-30B","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"edenai"},"edenai/flexai/Nemotron-3-Super-120B-A12B":{"id":"flexai/Nemotron-3-Super-120B-A12B","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.085,"output":0.4},"sourceProvider":"edenai"},"edenai/google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["audio","image","text","video"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":1},"sourceProvider":"edenai"},"edenai/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333,"input_audio":1},"sourceProvider":"edenai"},"edenai/google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"sourceProvider":"edenai"},"edenai/google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-flash-lite-image":{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333,"input_audio":0.5},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"sourceProvider":"edenai"},"edenai/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"sourceProvider":"edenai"},"edenai/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"sourceProvider":"edenai"},"edenai/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/google/gemini-flash-latest":{"id":"google/gemini-flash-latest","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/google/gemini-pro-latest":{"id":"google/gemini-pro-latest","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/google/lyria-3-clip-preview":{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"edenai"},"edenai/groq/openai/gpt-oss-120b":{"id":"groq/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"edenai"},"edenai/groq/openai/gpt-oss-20b":{"id":"groq/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"edenai"},"edenai/ionos/meta-llama/Llama-3.3-70B-Instruct":{"id":"ionos/meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.760435,"output":0.760435},"sourceProvider":"edenai"},"edenai/ionos/openai/gpt-oss-120b":{"id":"ionos/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.175485,"output":0.760435},"sourceProvider":"edenai"},"edenai/minimax/MiniMax-M2":{"id":"minimax/MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"edenai"},"edenai/minimax/MiniMax-M2.1":{"id":"minimax/MiniMax-M2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"edenai"},"edenai/minimax/MiniMax-M2.5":{"id":"minimax/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"edenai"},"edenai/minimax/MiniMax-M2.7":{"id":"minimax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"edenai"},"edenai/minimax/MiniMax-M3":{"id":"minimax/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"edenai"},"edenai/mistral/codestral-latest":{"id":"mistral/codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9},"sourceProvider":"edenai"},"edenai/mistral/devstral-2512":{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"edenai"},"edenai/mistral/devstral-medium-latest":{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"edenai"},"edenai/mistral/magistral-medium-latest":{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":2,"output":5},"sourceProvider":"edenai"},"edenai/mistral/mistral-large-2512":{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"sourceProvider":"edenai"},"edenai/mistral/mistral-large-latest":{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"edenai"},"edenai/mistral/mistral-medium-2505":{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.4,"output":2},"sourceProvider":"edenai"},"edenai/mistral/mistral-medium-2604":{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"edenai"},"edenai/mistral/mistral-medium-latest":{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"edenai"},"edenai/mistral/mistral-small-2603":{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"edenai"},"edenai/mistral/mistral-small-latest":{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"edenai"},"edenai/moonshot/kimi-k2.6":{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"edenai"},"edenai/moonshot/kimi-k2.7-code":{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"edenai"},"edenai/moonshot/kimi-k3":{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"edenai"},"edenai/nebius/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"nebius/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"sourceProvider":"edenai"},"edenai/nebius/meta-llama/Llama-3.3-70B-Instruct":{"id":"nebius/meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.13,"output":0.4,"cache_read":0.13},"sourceProvider":"edenai"},"edenai/nebius/nvidia/nemotron-3-super-120b-a12b":{"id":"nebius/nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9,"cache_read":0.3},"sourceProvider":"edenai"},"edenai/nebius/nvidia/Nemotron-3-Ultra-550b-a55b":{"id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":1,"output":3,"cache_read":1},"sourceProvider":"edenai"},"edenai/nebius/openai/gpt-oss-120b":{"id":"nebius/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.15},"sourceProvider":"edenai"},"edenai/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"edenai"},"edenai/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"edenai"},"edenai/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"edenai"},"edenai/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"edenai"},"edenai/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"edenai"},"edenai/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"edenai"},"edenai/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"edenai"},"edenai/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"edenai"},"edenai/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"edenai"},"edenai/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"edenai"},"edenai/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"edenai"},"edenai/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"edenai"},"edenai/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"edenai"},"edenai/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"edenai"},"edenai/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"edenai"},"edenai/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"edenai"},"edenai/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"edenai"},"edenai/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"edenai"},"edenai/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"edenai"},"edenai/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":6,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":6}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":6,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":6}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"sourceProvider":"edenai"},"edenai/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"edenai"},"edenai/openai/gpt-latest":{"id":"openai/gpt-latest","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5,"tiers":[{"input":8,"output":30,"cache_read":0.8,"cache_write":10,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":8,"output":30,"cache_read":0.8,"cache_write":10}},"sourceProvider":"edenai"},"edenai/openai/gpt-mini-latest":{"id":"openai/gpt-mini-latest","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"edenai"},"edenai/openai/gpt-pro-latest":{"id":"openai/gpt-pro-latest","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":6,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":6}},"sourceProvider":"edenai"},"edenai/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"edenai"},"edenai/openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":150,"output":600},"sourceProvider":"edenai"},"edenai/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"edenai"},"edenai/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"edenai"},"edenai/openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","pdf","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"edenai"},"edenai/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"edenai"},"edenai/ovhcloud/gpt-oss-120b":{"id":"ovhcloud/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.09,"output":0.47},"sourceProvider":"edenai"},"edenai/ovhcloud/gpt-oss-20b":{"id":"ovhcloud/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.18},"sourceProvider":"edenai"},"edenai/perplexityai/sonar":{"id":"perplexityai/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127072,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"edenai"},"edenai/perplexityai/sonar-deep-research":{"id":"perplexityai/sonar-deep-research","name":"Sonar Deep Research","description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"edenai"},"edenai/perplexityai/sonar-pro":{"id":"perplexityai/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"edenai"},"edenai/perplexityai/sonar-reasoning-pro":{"id":"perplexityai/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"edenai"},"edenai/qwen/deepseek-v4-flash-0731":{"id":"qwen/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.176,"output":0.528},"sourceProvider":"edenai"},"edenai/qwen/deepseek-v4-pro-0813":{"id":"qwen/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.627,"output":1.881},"sourceProvider":"edenai"},"edenai/qwen/qwen-max":{"id":"qwen/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4,"cache_read":0.32},"sourceProvider":"edenai"},"edenai/qwen/qwen-vl-max":{"id":"qwen/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":3.2,"cache_read":0.16},"sourceProvider":"edenai"},"edenai/qwen/qwen-vl-plus":{"id":"qwen/qwen-vl-plus","name":"Qwen-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-08-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.21,"output":0.63,"cache_read":0.042},"sourceProvider":"edenai"},"edenai/qwen/qwen3-235b-a22b-instruct-2507":{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.23,"output":0.92},"sourceProvider":"edenai"},"edenai/qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":2.25},"sourceProvider":"edenai"},"edenai/qwen/qwen3-coder-480b-a35b-instruct":{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":1.5,"output":7.5},"sourceProvider":"edenai"},"edenai/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"edenai"},"edenai/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":1.5},"sourceProvider":"edenai"},"edenai/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1,"output":5,"cache_read":0.2,"cache_write":1.25},"sourceProvider":"edenai"},"edenai/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.2,"output":6,"cache_read":0.24,"cache_write":1.5},"sourceProvider":"edenai"},"edenai/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"edenai"},"edenai/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"edenai"},"edenai/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":1.6},"sourceProvider":"edenai"},"edenai/qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":4},"sourceProvider":"edenai"},"edenai/qwen/qwen3.8-2.4t-a95b":{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"edenai"},"edenai/qwen/qwen3.8-27b":{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625},"sourceProvider":"edenai"},"edenai/qwen/qwen3.8-max":{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"edenai"},"edenai/qwen/qwq-plus":{"id":"qwen/qwq-plus","name":"QwQ Plus","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.8,"output":2.4},"sourceProvider":"edenai"},"edenai/scaleway/deepseek-v4-flash-0731":{"id":"scaleway/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":384000},"cost":{"input":0.46796,"output":0.93592},"sourceProvider":"edenai"},"edenai/scaleway/gpt-oss-120b":{"id":"scaleway/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.175485,"output":0.70194},"sourceProvider":"edenai"},"edenai/scaleway/llama-3.3-70b-instruct":{"id":"scaleway/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":1.05291,"output":1.05291},"sourceProvider":"edenai"},"edenai/tensorx/deepseek/deepseek-v4-flash-0731":{"id":"tensorx/deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.25,"output":0.3,"cache_read":0.0625},"sourceProvider":"edenai"},"edenai/tensorx/moonshotai/kimi-k2.5":{"id":"tensorx/moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8,"cache_read":0.125},"sourceProvider":"edenai"},"edenai/together_ai/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"sourceProvider":"edenai"},"edenai/together_ai/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"sourceProvider":"edenai"},"edenai/together_ai/meta-models/Muse-Glimmer-30B":{"id":"together_ai/meta-models/Muse-Glimmer-30B","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"edenai"},"edenai/together_ai/nvidia/nemotron-3-ultra-550b-a55b":{"id":"together_ai/nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512288,"output":128000},"cost":{"input":0.6,"output":3.6,"cache_read":0.2},"sourceProvider":"edenai"},"edenai/together_ai/openai/gpt-oss-120b":{"id":"together_ai/openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"edenai"},"edenai/together_ai/openai/gpt-oss-20b":{"id":"together_ai/openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2},"sourceProvider":"edenai"},"edenai/together_ai/thinkingmachines/Inkling":{"id":"together_ai/thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"edenai"},"edenai/together_ai/thinkingmachines/Inkling-Small":{"id":"together_ai/thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"edenai"},"edenai/vertex/gemini-2.5-flash-image":{"id":"vertex/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":1},"sourceProvider":"edenai"},"edenai/vertex/gemini-3-flash-preview":{"id":"vertex/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333,"input_audio":1},"sourceProvider":"edenai"},"edenai/vertex/gemini-3-pro-image":{"id":"vertex/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.1-flash-image":{"id":"vertex/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.1-flash-lite-image":{"id":"vertex/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.1-pro-preview":{"id":"vertex/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25}},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash":{"id":"vertex/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash-lite":{"id":"vertex/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash-lite@eu":{"id":"vertex/gemini-3.5-flash-lite@eu","name":"Gemini 3.5 Flash Lite (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash-lite@us":{"id":"vertex/gemini-3.5-flash-lite@us","name":"Gemini 3.5 Flash Lite (US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333,"input_audio":0.3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash@eu":{"id":"vertex/gemini-3.5-flash@eu","name":"Gemini 3.5 Flash (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.5-flash@us":{"id":"vertex/gemini-3.5-flash@us","name":"Gemini 3.5 Flash (US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333,"input_audio":3},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.6-flash":{"id":"vertex/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.6-flash@eu":{"id":"vertex/gemini-3.6-flash@eu","name":"Gemini 3.6 Flash (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.6-flash@us":{"id":"vertex/gemini-3.6-flash@us","name":"Gemini 3.6 Flash (US)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667,"input_audio":0.75},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.7-flash":{"id":"vertex/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.7-flash@eu":{"id":"vertex/gemini-3.7-flash@eu","name":"Gemini 3.7 Flash (EU)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/vertex/gemini-3.7-flash@us":{"id":"vertex/gemini-3.7-flash@us","name":"Gemini 3.7 Flash (US)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/vertex/gemini-flash-latest":{"id":"vertex/gemini-flash-latest","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333,"input_audio":1.5},"sourceProvider":"edenai"},"edenai/vertex/gemini-pro-latest":{"id":"vertex/gemini-pro-latest","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"input_audio":2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":0.25}},"sourceProvider":"edenai"},"edenai/xai/grok-4.20-0309-non-reasoning":{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/xai/grok-4.20-0309-reasoning":{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/xai/grok-4.5":{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"sourceProvider":"edenai"},"edenai/xai/grok-4.6":{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"edenai"},"edenai/xai/grok-build-0.1":{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"edenai"},"edenai/xai/grok-latest":{"id":"xai/grok-latest","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"edenai"},"edenai/zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"edenai"},"edenai/zai/glm-4.6v":{"id":"zai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"sourceProvider":"edenai"},"edenai/zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"edenai"},"edenai/zai/glm-5":{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"edenai"},"edenai/zai/glm-5-turbo":{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"edenai"},"edenai/zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"edenai"},"edenai/zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"edenai"},"edenai/zai/glm-5.3":{"id":"zai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"edenai"},"edenai/zai/glm-5v-turbo":{"id":"zai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"edenai"},"empiriolabs/deepseek-v3-2":{"id":"empiriolabs/deepseek-v3-2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.57,"output":1.71,"cache_read":0.57},"sourceProvider":"empiriolabs"},"empiriolabs/deepseek-v4-flash":{"id":"empiriolabs/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"sourceProvider":"empiriolabs"},"empiriolabs/deepseek-v4-flash-0731":{"id":"empiriolabs/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.424,"output":1.272,"cache_read":0.424},"sourceProvider":"empiriolabs"},"empiriolabs/deepseek-v4-pro":{"id":"empiriolabs/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.65,"output":3.3,"cache_read":1.65},"sourceProvider":"empiriolabs"},"empiriolabs/deepseek-v4-pro-0813":{"id":"empiriolabs/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":1.32},"sourceProvider":"empiriolabs"},"empiriolabs/fugu-ultra-v1-0":{"id":"empiriolabs/fugu-ultra-v1-0","name":"Fugu Ultra v1.0","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":7.5,"output":45,"cache_read":1.5,"tiers":[{"input":15,"output":67.5,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":15,"output":67.5,"cache_read":3}},"sourceProvider":"empiriolabs"},"empiriolabs/fugu-ultra-v1-1":{"id":"empiriolabs/fugu-ultra-v1-1","name":"Fugu Ultra v1.1","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"empiriolabs"},"empiriolabs/gemma-4-26b-a4b":{"id":"empiriolabs/gemma-4-26b-a4b","name":"Gemma 4 26B-A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.29,"cache_read":0.025},"sourceProvider":"empiriolabs"},"empiriolabs/glm-4-5-flash":{"id":"empiriolabs/glm-4-5-flash","name":"GLM 4.5 Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":98304},"cost":{"input":0,"output":0},"sourceProvider":"empiriolabs"},"empiriolabs/glm-4-6v-flash":{"id":"empiriolabs/glm-4-6v-flash","name":"GLM 4.6V Flash","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"empiriolabs"},"empiriolabs/glm-4-7-flash":{"id":"empiriolabs/glm-4-7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"empiriolabs"},"empiriolabs/glm-5-1":{"id":"empiriolabs/glm-5-1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":38912}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":128000},"cost":{"input":0.825,"output":3.301,"cache_read":0.165,"tiers":[{"input":1.1,"output":3.851,"cache_read":0.22,"tier":{"type":"context","size":32000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/glm-5-2":{"id":"empiriolabs/glm-5-2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"sourceProvider":"empiriolabs"},"empiriolabs/glm-5-3":{"id":"empiriolabs/glm-5-3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"sourceProvider":"empiriolabs"},"empiriolabs/kimi-k2-6":{"id":"empiriolabs/kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16000},"cost":{"input":0.8939,"output":3.7131,"cache_read":0.1788},"sourceProvider":"empiriolabs"},"empiriolabs/kimi-k2-7-code":{"id":"empiriolabs/kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.95,"output":4,"cache_read":0.95},"sourceProvider":"empiriolabs"},"empiriolabs/kimi-k2-7-code-highspeed":{"id":"empiriolabs/kimi-k2-7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":1.9,"output":8,"cache_read":1.9},"sourceProvider":"empiriolabs"},"empiriolabs/kimi-k3":{"id":"empiriolabs/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":3},"sourceProvider":"empiriolabs"},"empiriolabs/mimo-v2-5":{"id":"empiriolabs/mimo-v2-5","name":"MiMo V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.7,"output":1.4,"cache_read":0.014},"sourceProvider":"empiriolabs"},"empiriolabs/mimo-v2-5-pro":{"id":"empiriolabs/mimo-v2-5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.175,"output":4.35,"cache_read":0.018},"sourceProvider":"empiriolabs"},"empiriolabs/minimax-m2-7":{"id":"empiriolabs/minimax-m2-7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"sourceProvider":"empiriolabs"},"empiriolabs/minimax-m2-7-highspeed":{"id":"empiriolabs/minimax-m2-7-highspeed","name":"MiniMax M2.7 Highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"empiriolabs"},"empiriolabs/minimax-m3":{"id":"empiriolabs/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":524288},"cost":{"input":0.225,"output":0.9,"cache_read":0.045,"tiers":[{"input":0.45,"output":1.8,"cache_read":0.09,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.45,"output":1.8,"cache_read":0.09}},"sourceProvider":"empiriolabs"},"empiriolabs/mistral-medium-3":{"id":"empiriolabs/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":40000},"cost":{"input":0,"output":0},"sourceProvider":"empiriolabs"},"empiriolabs/mistral-small-4":{"id":"empiriolabs/mistral-small-4","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.15},"sourceProvider":"empiriolabs"},"empiriolabs/muse-glimmer-30b":{"id":"empiriolabs/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"sourceProvider":"empiriolabs"},"empiriolabs/muse-spark-1-1":{"id":"empiriolabs/muse-spark-1-1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1},"sourceProvider":"empiriolabs"},"empiriolabs/muse-spark-1-2":{"id":"empiriolabs/muse-spark-1-2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":1},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-122b-a10b":{"id":"empiriolabs/qwen3-5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.115,"output":0.917,"cache_read":0.115,"tiers":[{"input":0.287,"output":2.294,"cache_read":0.287,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-27b":{"id":"empiriolabs/qwen3-5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.086,"output":0.688,"cache_read":0.086,"tiers":[{"input":0.258,"output":2.064,"cache_read":0.258,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-35b-a3b":{"id":"empiriolabs/qwen3-5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.057,"output":0.459,"cache_read":0.057,"tiers":[{"input":0.229,"output":1.835,"cache_read":0.229,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-397b-a17b":{"id":"empiriolabs/qwen3-5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.172,"output":1.032,"cache_read":0.172,"tiers":[{"input":0.43,"output":2.58,"cache_read":0.43,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-4b":{"id":"empiriolabs/qwen3-5-4b","name":"Qwen3.5 4B","description":"Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-02","last_updated":"2026-03-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.04,"output":0.07,"cache_read":0.02},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-9b":{"id":"empiriolabs/qwen3-5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":0.13,"cache_read":0.045},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-flash":{"id":"empiriolabs/qwen3-5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.09,"output":0.368,"cache_read":0.09},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-5-plus":{"id":"empiriolabs/qwen3-5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.36,"output":2.21,"cache_read":0.36,"tiers":[{"input":1.08,"output":6.62,"cache_read":1.08,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.08,"output":6.62,"cache_read":1.08}},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-6-27b":{"id":"empiriolabs/qwen3-6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":80000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.412564,"output":2.475384,"cache_read":0.412564},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-6-35b-a3b":{"id":"empiriolabs/qwen3-6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.07,"output":0.42,"cache_read":0.035},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-6-flash":{"id":"empiriolabs/qwen3-6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":64000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.25,"tiers":[{"input":1,"output":4,"cache_read":1,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1,"output":4,"cache_read":1}},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-6-max-preview":{"id":"empiriolabs/qwen3-6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":393216}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.31,"output":7.88,"cache_read":1.31,"tiers":[{"input":1.97,"output":11.82,"cache_read":1.97,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-6-plus":{"id":"empiriolabs/qwen3-6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.5,"tiers":[{"input":2,"output":6,"cache_read":2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":2}},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-7-flash":{"id":"empiriolabs/qwen3-7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.02,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.04,"tier":{"type":"context","size":256000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-7-max":{"id":"empiriolabs/qwen3-7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":64000}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":2.5},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-7-plus":{"id":"empiriolabs/qwen3-7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":256000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.4,"tiers":[{"input":1.2,"output":4.8,"cache_read":1.2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":1.2}},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-8-27b":{"id":"empiriolabs/qwen3-8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.17,"output":0.5,"cache_read":0.08},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-8-max":{"id":"empiriolabs/qwen3-8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":2},"sourceProvider":"empiriolabs"},"empiriolabs/qwen3-max":{"id":"empiriolabs/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.08,"output":5.52,"cache_read":1.08,"tiers":[{"input":2.16,"output":11.04,"cache_read":2.16,"tier":{"type":"context","size":32000}},{"input":2.7,"output":13.8,"cache_read":2.7,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/seed-2-0-code":{"id":"empiriolabs/seed-2-0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.4,"output":2.4,"cache_read":0.4,"tiers":[{"input":0.8,"output":4.8,"cache_read":0.8,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/seed-2-0-lite":{"id":"empiriolabs/seed-2-0-lite","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.31,"output":2.5,"cache_read":0.31,"tiers":[{"input":0.62,"output":5,"cache_read":0.62,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/seed-2-0-mini":{"id":"empiriolabs/seed-2-0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.12,"output":0.5,"cache_read":0.12,"tiers":[{"input":0.24,"output":1,"cache_read":0.24,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/seed-2-0-pro":{"id":"empiriolabs/seed-2-0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.63,"output":3.79,"cache_read":0.63,"tiers":[{"input":1.26,"output":7.58,"cache_read":1.26,"tier":{"type":"context","size":128000}}]},"sourceProvider":"empiriolabs"},"empiriolabs/seed-2-1-turbo":{"id":"empiriolabs/seed-2-1-turbo","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.63,"output":3.13,"cache_read":0.63},"sourceProvider":"empiriolabs"},"empiriolabs/step-3-5-flash":{"id":"empiriolabs/step-3-5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"empiriolabs"},"empiriolabs/step-3-5-flash-2603":{"id":"empiriolabs/step-3-5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"empiriolabs"},"empiriolabs/step-3-7-flash":{"id":"empiriolabs/step-3-7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":131072},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"empiriolabs"},"evroc/google/gemma-4-26B-A4B-it":{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.144,"output":0.575},"sourceProvider":"evroc"},"evroc/intfloat/multilingual-e5-large-instruct":{"id":"intfloat/multilingual-e5-large-instruct","name":"E5 Multi-Lingual Large Embeddings 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"cost":{"input":0.114,"output":0.114},"sourceProvider":"evroc"},"evroc/KBLab/kb-whisper-large":{"id":"KBLab/kb-whisper-large","name":"KB Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"sourceProvider":"evroc"},"evroc/mistralai/Mistral-Medium-3.5-128B":{"id":"mistralai/Mistral-Medium-3.5-128B","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.725,"output":6.9},"sourceProvider":"evroc"},"evroc/mistralai/Voxtral-Small-24B-2507":{"id":"mistralai/Voxtral-Small-24B-2507","name":"Voxtral Small 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"voxtral","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-03-01","last_updated":"2025-03-01","modalities":{"input":["audio","text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"sourceProvider":"evroc"},"evroc/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.4375,"output":5.75},"sourceProvider":"evroc"},"evroc/nvidia/Llama-3.3-70B-Instruct-FP8":{"id":"nvidia/Llama-3.3-70B-Instruct-FP8","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":1.15,"output":1.15},"sourceProvider":"evroc"},"evroc/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.23,"output":0.92},"sourceProvider":"evroc"},"evroc/openai/whisper-large-v3":{"id":"openai/whisper-large-v3","name":"Whisper 3 Large","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"sourceProvider":"evroc"},"evroc/openai/whisper-large-v3-turbo":{"id":"openai/whisper-large-v3-turbo","name":"Whisper Large v3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.0023,"output":0.0023,"output_audio":2.3},"sourceProvider":"evroc"},"evroc/Qwen/Qwen3-Embedding-8B":{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":4096},"cost":{"input":0.115,"output":0.115},"sourceProvider":"evroc"},"evroc/Qwen/Qwen3-Reranker-4B":{"id":"Qwen/Qwen3-Reranker-4B","name":"Qwen3 Reranker 4B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.0575,"output":0},"sourceProvider":"evroc"},"evroc/Qwen/Qwen3.6-35B-A3B-FP8":{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.345,"output":1.38},"sourceProvider":"evroc"},"evroc/roc":{"id":"evroc/roc","name":"roc","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-06-06","last_updated":"2026-06-06","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":2.875,"output":11.516},"sourceProvider":"evroc"},"evroc/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":1.4375,"output":5.75},"sourceProvider":"evroc"},"fastrouter/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"fastrouter"},"fastrouter/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"fastrouter"},"fastrouter/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"fastrouter"},"fastrouter/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"fastrouter"},"fastrouter/bytedance/seedance-2":{"id":"bytedance/seedance-2","name":"Seedance 2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":4096,"output":0},"sourceProvider":"fastrouter"},"fastrouter/deepseek-ai/deepseek-r1-distill-llama-70b":{"id":"deepseek-ai/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.14},"sourceProvider":"fastrouter"},"fastrouter/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.0375},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.31},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12},"sourceProvider":"fastrouter"},"fastrouter/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9},"sourceProvider":"fastrouter"},"fastrouter/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38},"sourceProvider":"fastrouter"},"fastrouter/google/imagen-4.0-fast":{"id":"google/imagen-4.0-fast","name":"Imagen 4 Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"fastrouter"},"fastrouter/google/imagen-4.0-ultra":{"id":"google/imagen-4.0-ultra","name":"Imagen 4 Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"fastrouter"},"fastrouter/google/veo3.1":{"id":"google/veo3.1","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":0},"sourceProvider":"fastrouter"},"fastrouter/google/veo3.1-fast":{"id":"google/veo3.1-fast","name":"Veo 3.1 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":0},"sourceProvider":"fastrouter"},"fastrouter/google/veo3.1-lite":{"id":"google/veo3.1-lite","name":"Veo 3.1 Lite","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":400000,"output":0},"sourceProvider":"fastrouter"},"fastrouter/leonardo-ai/lucid-origin":{"id":"leonardo-ai/lucid-origin","name":"Lucid Origin","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":0},"sourceProvider":"fastrouter"},"fastrouter/leonardo-ai/lucid-realism":{"id":"leonardo-ai/lucid-realism","name":"Lucid Realism","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"lucid","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":0},"sourceProvider":"fastrouter"},"fastrouter/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"fastrouter"},"fastrouter/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4},"sourceProvider":"fastrouter"},"fastrouter/moonshotai/kimi-k2":{"id":"moonshotai/kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.55,"output":2.2},"sourceProvider":"fastrouter"},"fastrouter/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":3.5},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-image-2":{"id":"openai/gpt-image-2","name":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":0},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.05,"output":0.2},"sourceProvider":"fastrouter"},"fastrouter/openai/gpt-realtime-1.5":{"id":"openai/gpt-realtime-1.5","name":"GPT Realtime 1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","audio","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32000,"output":4096},"cost":{"input":4,"output":16},"sourceProvider":"fastrouter"},"fastrouter/qwen/qwen3-coder":{"id":"qwen/qwen3-coder","name":"Qwen3 Coder","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.3,"output":1.2},"sourceProvider":"fastrouter"},"fastrouter/sarvam/sarvam-105b":{"id":"sarvam/sarvam-105b","name":"Sarvam 105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.04,"output":0.16},"sourceProvider":"fastrouter"},"fastrouter/sarvam/sarvam-30b":{"id":"sarvam/sarvam-30b","name":"Sarvam 30B","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.1},"sourceProvider":"fastrouter"},"fastrouter/wanx/wan-v2-6":{"id":"wanx/wan-v2-6","name":"Wan 2.6","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":true,"limit":{"context":400000,"output":0},"sourceProvider":"fastrouter"},"fastrouter/x-ai/grok-4":{"id":"x-ai/grok-4","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.75,"cache_write":15},"sourceProvider":"fastrouter"},"fastrouter/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5},"sourceProvider":"fastrouter"},"fastrouter/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2},"sourceProvider":"fastrouter"},"fastrouter/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.95,"output":3.15},"sourceProvider":"fastrouter"},"fastrouter/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.05,"output":3.5},"sourceProvider":"fastrouter"},"fireworks-ai/accounts/fireworks/models/deepseek-v4-flash":{"id":"accounts/fireworks/models/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/deepseek-v4-flash-0731":{"id":"accounts/fireworks/models/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/deepseek-v4-pro":{"id":"accounts/fireworks/models/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/deepseek-v4-pro-0813":{"id":"accounts/fireworks/models/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/glm-5p2":{"id":"accounts/fireworks/models/glm-5p2","name":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/gpt-oss-120b":{"id":"accounts/fireworks/models/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/gpt-oss-20b":{"id":"accounts/fireworks/models/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/inkling":{"id":"accounts/fireworks/models/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/kimi-k2p6":{"id":"accounts/fireworks/models/kimi-k2p6","name":"Kimi K2.6","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/kimi-k2p7-code":{"id":"accounts/fireworks/models/kimi-k2p7-code","name":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/kimi-k3":{"id":"accounts/fireworks/models/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/minimax-m2p7":{"id":"accounts/fireworks/models/minimax-m2p7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-12","last_updated":"2026-04-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/minimax-m3":{"id":"accounts/fireworks/models/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/muse-glimmer-30b":{"id":"accounts/fireworks/models/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/nemotron-3-ultra-nvfp4":{"id":"accounts/fireworks/models/nemotron-3-ultra-nvfp4","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.119},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b":{"id":"accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/qwen3p7-plus":{"id":"accounts/fireworks/models/qwen3p7-plus","name":"Qwen 3.7 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/models/qwen3p8-max":{"id":"accounts/fireworks/models/qwen3p8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/routers/glm-5p2-fast":{"id":"accounts/fireworks/routers/glm-5p2-fast","name":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-26","last_updated":"2026-06-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":131072},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/routers/kimi-k2p6-fast":{"id":"accounts/fireworks/routers/kimi-k2p6-fast","name":"Kimi K2.6 Fast","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-17","last_updated":"2026-06-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":2,"output":8,"cache_read":0.3},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/routers/kimi-k2p6-turbo":{"id":"accounts/fireworks/routers/kimi-k2p6-turbo","name":"Kimi K2.6 Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":2,"output":8,"cache_read":0.3},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/routers/kimi-k2p7-code-fast":{"id":"accounts/fireworks/routers/kimi-k2p7-code-fast","name":"Kimi K2.7 Code Fast","description":"Kimi coding model for software agents, refactors, and repository reasoning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"fireworks-ai"},"fireworks-ai/accounts/fireworks/routers/kimi-k3-fast":{"id":"accounts/fireworks/routers/kimi-k3-fast","name":"Kimi K3 Fast","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"fireworks-ai"},"freemodel/claude-fable-5":{"id":"freemodel/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"freemodel"},"freemodel/claude-haiku-4-5-20251001":{"id":"freemodel/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"freemodel"},"freemodel/claude-opus-4-6":{"id":"freemodel/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"freemodel"},"freemodel/claude-opus-4-7":{"id":"freemodel/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"freemodel"},"freemodel/claude-opus-4-8":{"id":"freemodel/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"freemodel"},"freemodel/claude-sonnet-4-6":{"id":"freemodel/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"freemodel"},"freemodel/gpt-5.3-codex":{"id":"freemodel/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75},"sourceProvider":"freemodel"},"freemodel/gpt-5.4":{"id":"freemodel/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"freemodel"},"freemodel/gpt-5.4-mini":{"id":"freemodel/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"sourceProvider":"freemodel"},"freemodel/gpt-5.5":{"id":"freemodel/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://api.freemodel.dev/v1"},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"sourceProvider":"freemodel"},"friendli/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.5,"output":1.5,"cache_read":0.25},"sourceProvider":"friendli"},"friendli/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"sourceProvider":"friendli"},"friendli/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"friendli"},"friendli/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"friendli"},"friendli/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"friendli"},"frogbot/claude-haiku-4-5":{"id":"frogbot/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"frogbot"},"frogbot/claude-opus-4-6":{"id":"frogbot/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"frogbot"},"frogbot/claude-opus-4-7":{"id":"frogbot/claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"frogbot"},"frogbot/claude-sonnet-4-6":{"id":"frogbot/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"frogbot"},"frogbot/deepseek-v4-pro":{"id":"frogbot/deepseek-v4-pro","name":"DeepSeek v4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":1.74,"output":3.48,"cache_read":0.14},"sourceProvider":"frogbot"},"frogbot/gemini-2.5-flash":{"id":"frogbot/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-07-17","last_updated":"2025-07-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.075},"sourceProvider":"frogbot"},"frogbot/gemini-2.5-pro":{"id":"frogbot/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.31},"sourceProvider":"frogbot"},"frogbot/gemini-3-1-pro-preview":{"id":"frogbot/gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"frogbot"},"frogbot/gemini-3-flash-preview":{"id":"frogbot/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"frogbot"},"frogbot/gpt-4o":{"id":"frogbot/gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"frogbot"},"frogbot/gpt-5-3-codex":{"id":"frogbot/gpt-5-3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"frogbot"},"frogbot/gpt-5-4-mini":{"id":"frogbot/gpt-5-4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"frogbot"},"frogbot/gpt-5-4-nano":{"id":"frogbot/gpt-5-4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"frogbot"},"frogbot/gpt-5-5":{"id":"frogbot/gpt-5-5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"frogbot"},"frogbot/gpt-oss-120b":{"id":"frogbot/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"frogbot"},"frogbot/gpt-oss-20b":{"id":"frogbot/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.2},"sourceProvider":"frogbot"},"frogbot/grok-4-1-fast-non-reasoning":{"id":"frogbot/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"frogbot"},"frogbot/grok-4-1-fast-reasoning":{"id":"frogbot/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"frogbot"},"frogbot/grok-4-3":{"id":"frogbot/grok-4-3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"frogbot"},"frogbot/grok-code-fast-1":{"id":"frogbot/grok-code-fast-1","name":"Grok 4.1 Fast (Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2023-10","release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.2,"output":1.5,"cache_read":0.02},"sourceProvider":"frogbot"},"frogbot/kimi-k2-6":{"id":"frogbot/kimi-k2-6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"frogbot"},"frogbot/kimi-k2.5":{"id":"frogbot/kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"frogbot"},"frogbot/minimax-m2-5":{"id":"frogbot/minimax-m2-5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-01-15","last_updated":"2025-02-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"frogbot"},"frogbot/minimax-m2-7":{"id":"frogbot/minimax-m2-7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"frogbot"},"frogbot/qwen-3-6-plus":{"id":"frogbot/qwen-3-6-plus","name":"Qwen 3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.1},"sourceProvider":"frogbot"},"frogbot/zai-glm-5-1":{"id":"frogbot/zai-glm-5-1","name":"Z.AI GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-01-20","last_updated":"2025-02-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":8192},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"frogbot"},"github-copilot/claude-fable-5":{"id":"github-copilot/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"github-copilot"},"github-copilot/claude-haiku-4.5":{"id":"github-copilot/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":136000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"github-copilot"},"github-copilot/claude-opus-4.5":{"id":"github-copilot/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"github-copilot"},"github-copilot/claude-opus-4.6":{"id":"github-copilot/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"github-copilot"},"github-copilot/claude-opus-4.7":{"id":"github-copilot/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"github-copilot"},"github-copilot/claude-opus-4.8":{"id":"github-copilot/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":64000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"github-copilot"},"github-copilot/claude-opus-5":{"id":"github-copilot/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"github-copilot"},"github-copilot/claude-sonnet-4":{"id":"github-copilot/claude-sonnet-4","name":"Claude Sonnet 4 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":216000,"input":128000,"output":16000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"github-copilot"},"github-copilot/claude-sonnet-4.5":{"id":"github-copilot/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"github-copilot"},"github-copilot/claude-sonnet-4.6":{"id":"github-copilot/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":32000}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":168000,"output":32000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"github-copilot"},"github-copilot/claude-sonnet-5":{"id":"github-copilot/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"github-copilot"},"github-copilot/gemini-3.1-pro-preview":{"id":"github-copilot/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":256,"max":32000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"github-copilot"},"github-copilot/gemini-3.5-flash":{"id":"github-copilot/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":256,"max":24000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":128000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"github-copilot"},"github-copilot/gemini-3.6-flash":{"id":"github-copilot/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":256,"max":32000}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"sourceProvider":"github-copilot"},"github-copilot/gemini-3.7-flash":{"id":"github-copilot/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":936000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"github-copilot"},"github-copilot/gpt-4.1":{"id":"github-copilot/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"github-copilot"},"github-copilot/gpt-5-mini":{"id":"github-copilot/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":264000,"input":128000,"output":64000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.2":{"id":"github-copilot/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.2-codex":{"id":"github-copilot/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.3-codex":{"id":"github-copilot/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.4":{"id":"github-copilot/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.4-mini":{"id":"github-copilot/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.4-nano":{"id":"github-copilot/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.5":{"id":"github-copilot/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.6-luna":{"id":"github-copilot/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04}},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.6-sol":{"id":"github-copilot/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"sourceProvider":"github-copilot"},"github-copilot/gpt-5.6-terra":{"id":"github-copilot/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"github-copilot"},"github-copilot/grok-4.5":{"id":"github-copilot/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":372000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"github-copilot"},"github-copilot/grok-4.6":{"id":"github-copilot/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":372000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"github-copilot"},"github-copilot/kimi-k2.7-code":{"id":"github-copilot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":224000,"output":32000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"github-copilot"},"github-copilot/kimi-k3":{"id":"github-copilot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"github-copilot"},"github-copilot/mai-code-1-flash-picker":{"id":"github-copilot/mai-code-1-flash-picker","name":"MAI-Code-1-Flash","description":"Microsoft coding model built for fast, efficient assistance in everyday developer workflows","family":"mai","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-06-02","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":128000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"github-copilot"},"github-copilot/mai-code-1.1-flash":{"id":"github-copilot/mai-code-1.1-flash","name":"MAI-Code-1.1-Flash","description":"Microsoft coding model with native vision support, optimized for fast and efficient software development","family":"mai","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":128000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"sourceProvider":"github-copilot"},"gitlab/duo-chat-fable-5":{"id":"gitlab/duo-chat-fable-5","name":"Agentic Chat (Claude Fable 5)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-1":{"id":"gitlab/duo-chat-gpt-5-1","name":"Agentic Chat (GPT-5.1)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-2":{"id":"gitlab/duo-chat-gpt-5-2","name":"Agentic Chat (GPT-5.2)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-2-codex":{"id":"gitlab/duo-chat-gpt-5-2-codex","name":"Agentic Chat (GPT-5.2 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-3-codex":{"id":"gitlab/duo-chat-gpt-5-3-codex","name":"Agentic Chat (GPT-5.3 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-4":{"id":"gitlab/duo-chat-gpt-5-4","name":"Agentic Chat (GPT-5.4)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-4-mini":{"id":"gitlab/duo-chat-gpt-5-4-mini","name":"Agentic Chat (GPT-5.4 Mini)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-4-nano":{"id":"gitlab/duo-chat-gpt-5-4-nano","name":"Agentic Chat (GPT-5.4 Nano)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-5":{"id":"gitlab/duo-chat-gpt-5-5","name":"Agentic Chat (GPT-5.5)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-6-luna":{"id":"gitlab/duo-chat-gpt-5-6-luna","name":"Agentic Chat (GPT-5.6 Luna)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-6-sol":{"id":"gitlab/duo-chat-gpt-5-6-sol","name":"Agentic Chat (GPT-5.6 Sol)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-6-terra":{"id":"gitlab/duo-chat-gpt-5-6-terra","name":"Agentic Chat (GPT-5.6 Terra)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-codex":{"id":"gitlab/duo-chat-gpt-5-codex","name":"Agentic Chat (GPT-5 Codex)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-gpt-5-mini":{"id":"gitlab/duo-chat-gpt-5-mini","name":"Agentic Chat (GPT-5 Mini)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-haiku-4-5":{"id":"gitlab/duo-chat-haiku-4-5","name":"Agentic Chat (Claude Haiku 4.5)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-opus-4-5":{"id":"gitlab/duo-chat-opus-4-5","name":"Agentic Chat (Claude Opus 4.5)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-opus-4-6":{"id":"gitlab/duo-chat-opus-4-6","name":"Agentic Chat (Claude Opus 4.6)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-opus-4-7":{"id":"gitlab/duo-chat-opus-4-7","name":"Agentic Chat (Claude Opus 4.7)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-opus-4-8":{"id":"gitlab/duo-chat-opus-4-8","name":"Agentic Chat (Claude Opus 4.8)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-opus-5":{"id":"gitlab/duo-chat-opus-5","name":"Agentic Chat (Claude Opus 5)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-sonnet-4-5":{"id":"gitlab/duo-chat-sonnet-4-5","name":"Agentic Chat (Claude Sonnet 4.5)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2026-01-08","last_updated":"2026-01-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-sonnet-4-6":{"id":"gitlab/duo-chat-sonnet-4-6","name":"Agentic Chat (Claude Sonnet 4.6)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gitlab/duo-chat-sonnet-5":{"id":"gitlab/duo-chat-sonnet-5","name":"Agentic Chat (Claude Sonnet 5)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"gitlab"},"gmicloud/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"gmicloud"},"gmicloud/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"gmicloud"},"gmicloud/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"gmicloud"},"gmicloud/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":409600,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"gmicloud"},"gmicloud/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":384000},"cost":{"input":0.112,"output":0.224,"cache_read":0.022},"sourceProvider":"gmicloud"},"gmicloud/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.392,"output":2.784,"cache_read":0.116},"sourceProvider":"gmicloud"},"gmicloud/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.855,"output":3.6,"cache_read":0.144},"sourceProvider":"gmicloud"},"gmicloud/moonshotai/kimi-k2.7-code-highspeed":{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"gmicloud"},"gmicloud/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"gmicloud"},"gmicloud/Qwen/Qwen3.7-Max":{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"gmicloud"},"gmicloud/zai-org/GLM-5-FP8":{"id":"zai-org/GLM-5-FP8","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.6,"output":1.92,"cache_read":0.12},"sourceProvider":"gmicloud"},"gmicloud/zai-org/GLM-5.1-FP8":{"id":"zai-org/GLM-5.1-FP8","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.98,"output":3.08,"cache_read":0.182},"sourceProvider":"gmicloud"},"gmicloud/zai-org/GLM-5.2-FP8":{"id":"zai-org/GLM-5.2-FP8","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.979,"output":3.08,"cache_read":0.182},"sourceProvider":"gmicloud"},"google-vertex-anthropic/claude-fable-5@default":{"id":"google-vertex-anthropic/claude-fable-5@default","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-haiku-4-5@20251001":{"id":"google-vertex-anthropic/claude-haiku-4-5@20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4-1@20250805":{"id":"google-vertex-anthropic/claude-opus-4-1@20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4-5@20251101":{"id":"google-vertex-anthropic/claude-opus-4-5@20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4-6@default":{"id":"google-vertex-anthropic/claude-opus-4-6@default","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4-7@default":{"id":"google-vertex-anthropic/claude-opus-4-7@default","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4-8@default":{"id":"google-vertex-anthropic/claude-opus-4-8@default","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-4@20250514":{"id":"google-vertex-anthropic/claude-opus-4@20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-opus-5@default":{"id":"google-vertex-anthropic/claude-opus-5@default","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-sonnet-4-5@20250929":{"id":"google-vertex-anthropic/claude-sonnet-4-5@20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-sonnet-4-6@default":{"id":"google-vertex-anthropic/claude-sonnet-4-6@default","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-sonnet-4@20250514":{"id":"google-vertex-anthropic/claude-sonnet-4@20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"google-vertex-anthropic"},"google-vertex-anthropic/claude-sonnet-5@default":{"id":"google-vertex-anthropic/claude-sonnet-5@default","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"google-vertex-anthropic"},"google-vertex/claude-fable-5@default":{"id":"google-vertex/claude-fable-5@default","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"google-vertex"},"google-vertex/claude-haiku-4-5@20251001":{"id":"google-vertex/claude-haiku-4-5@20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4-1@20250805":{"id":"google-vertex/claude-opus-4-1@20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4-5@20251101":{"id":"google-vertex/claude-opus-4-5@20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4-6@default":{"id":"google-vertex/claude-opus-4-6@default","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4-7@default":{"id":"google-vertex/claude-opus-4-7@default","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4-8@default":{"id":"google-vertex/claude-opus-4-8@default","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-4@20250514":{"id":"google-vertex/claude-opus-4@20250514","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"google-vertex"},"google-vertex/claude-opus-5@default":{"id":"google-vertex/claude-opus-5@default","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"google-vertex"},"google-vertex/claude-sonnet-4-5@20250929":{"id":"google-vertex/claude-sonnet-4-5@20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"google-vertex"},"google-vertex/claude-sonnet-4-6@default":{"id":"google-vertex/claude-sonnet-4-6@default","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"google-vertex"},"google-vertex/claude-sonnet-4@20250514":{"id":"google-vertex/claude-sonnet-4@20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"google-vertex"},"google-vertex/claude-sonnet-5@default":{"id":"google-vertex/claude-sonnet-5@default","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"google-vertex"},"google-vertex/deepseek-ai/deepseek-v3.1-maas":{"id":"deepseek-ai/deepseek-v3.1-maas","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":1.7,"cache_read":0.06},"sourceProvider":"google-vertex"},"google-vertex/deepseek-ai/deepseek-v3.2-maas":{"id":"deepseek-ai/deepseek-v3.2-maas","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-17","last_updated":"2026-04-04","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.56,"output":1.68,"cache_read":0.056},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-flash":{"id":"google-vertex/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-flash-image":{"id":"google-vertex/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-flash-lite":{"id":"google-vertex/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-flash-tts":{"id":"google-vertex/gemini-2.5-flash-tts","name":"Gemini 2.5 Flash TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-09-30","last_updated":"2025-12-10","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.5,"output":10},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-pro":{"id":"google-vertex/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"google-vertex"},"google-vertex/gemini-2.5-pro-tts":{"id":"google-vertex/gemini-2.5-pro-tts","name":"Gemini 2.5 Pro TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-pro","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-09-30","last_updated":"2025-12-10","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":1,"output":20},"sourceProvider":"google-vertex"},"google-vertex/gemini-3-flash-preview":{"id":"google-vertex/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"google-vertex"},"google-vertex/gemini-3-pro-image":{"id":"google-vertex/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":120,"cache_read":0.2},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.1-flash-image":{"id":"google-vertex/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":60,"cache_read":0.05},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.1-flash-lite":{"id":"google-vertex/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.1-flash-lite-preview":{"id":"google-vertex/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.1-pro-preview":{"id":"google-vertex/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.1-pro-preview-customtools":{"id":"google-vertex/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.5-flash":{"id":"google-vertex/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.5-flash-lite":{"id":"google-vertex/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.6-flash":{"id":"google-vertex/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"sourceProvider":"google-vertex"},"google-vertex/gemini-3.7-flash":{"id":"google-vertex/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"sourceProvider":"google-vertex"},"google-vertex/gemini-embedding-001":{"id":"google-vertex/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"cost":{"input":0.15,"output":0},"sourceProvider":"google-vertex"},"google-vertex/gemini-flash-latest":{"id":"google-vertex/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"google-vertex"},"google-vertex/gemini-flash-lite-latest":{"id":"google-vertex/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"google-vertex"},"google-vertex/meta/llama-3.3-70b-instruct-maas":{"id":"meta/llama-3.3-70b-instruct-maas","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.72,"output":0.72},"sourceProvider":"google-vertex"},"google-vertex/meta/llama-4-maverick-17b-128e-instruct-maas":{"id":"meta/llama-4-maverick-17b-128e-instruct-maas","name":"Llama 4 Maverick 17B 128E Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":8192},"provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.35,"output":1.15},"sourceProvider":"google-vertex"},"google-vertex/moonshotai/kimi-k2-thinking-maas":{"id":"moonshotai/kimi-k2-thinking-maas","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"sourceProvider":"google-vertex"},"google-vertex/openai/gpt-oss-120b-maas":{"id":"openai/gpt-oss-120b-maas","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.09,"output":0.36},"sourceProvider":"google-vertex"},"google-vertex/openai/gpt-oss-20b-maas":{"id":"openai/gpt-oss-20b-maas","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"status":"deprecated","cost":{"input":0.07,"output":0.25,"cache_read":0.007},"sourceProvider":"google-vertex"},"google-vertex/qwen/qwen3-235b-a22b-instruct-2507-maas":{"id":"qwen/qwen3-235b-a22b-instruct-2507-maas","name":"Qwen3 235B A22B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.22,"output":0.88},"sourceProvider":"google-vertex"},"google-vertex/zai-org/glm-4.7-maas":{"id":"zai-org/glm-4.7-maas","name":"GLM-4.7","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-06","last_updated":"2026-01-06","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":0.6,"output":2.2,"cache_read":0.06},"sourceProvider":"google-vertex"},"google-vertex/zai-org/glm-5-maas":{"id":"zai-org/glm-5-maas","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/openai-compatible","api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi"},"cost":{"input":1,"output":3.2,"cache_read":0.1},"sourceProvider":"google-vertex"},"google/deep-research-max-preview-04-2026":{"id":"google/deep-research-max-preview-04-2026","name":"Deep Research Max Preview (Apr-21-2026)","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google"},"google/deep-research-preview-04-2026":{"id":"google/deep-research-preview-04-2026","name":"Deep Research Preview (Apr-21-2026)","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google"},"google/gemini-2.5-computer-use-preview-10-2025":{"id":"google/gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview 10-2025","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":1.25,"output":10,"tiers":[{"input":2.5,"output":15,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15}},"sourceProvider":"google"},"google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"google"},"google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":30,"cache_read":0.075},"sourceProvider":"google"},"google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"google"},"google/gemini-2.5-flash-preview-tts":{"id":"google/gemini-2.5-flash-preview-tts","name":"Gemini 2.5 Flash Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":0.5,"output":10},"sourceProvider":"google"},"google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"google"},"google/gemini-2.5-pro-preview-tts":{"id":"google/gemini-2.5-pro-preview-tts","name":"Gemini 2.5 Pro Preview TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":1,"output":20},"sourceProvider":"google"},"google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"google"},"google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":2,"output":120},"sourceProvider":"google"},"google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":2,"output":120},"sourceProvider":"google"},"google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":60},"sourceProvider":"google"},"google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":60},"sourceProvider":"google"},"google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"google"},"google/gemini-3.1-flash-lite-image":{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.25,"output":30},"sourceProvider":"google"},"google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Legacy model retained for compatibility with older integrations","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"google"},"google/gemini-3.1-flash-live-preview":{"id":"google/gemini-3.1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-26","last_updated":"2026-03-26","modalities":{"input":["text","image","video","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.75,"output":4.5,"input_audio":3,"output_audio":12},"sourceProvider":"google"},"google/gemini-3.1-flash-tts-preview":{"id":"google/gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","description":"Low-latency speech generation with steerable prompts and expressive audio tags","family":"gemini-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":1,"output":20},"sourceProvider":"google"},"google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google"},"google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"google"},"google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"google"},"google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"google"},"google/gemini-3.5-live-translate-preview":{"id":"google/gemini-3.5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","family":"gemini-pro","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["audio"],"output":["audio","text"]},"open_weights":false,"limit":{"context":16384,"output":32768},"cost":{"input":3.5,"output":21,"input_audio":3.5,"output_audio":21},"sourceProvider":"google"},"google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"sourceProvider":"google"},"google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"sourceProvider":"google"},"google/gemini-embedding-001":{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"cost":{"input":0.15,"output":0},"sourceProvider":"google"},"google/gemini-embedding-2":{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1},"cost":{"input":0.2,"output":0,"input_audio":6.5},"sourceProvider":"google"},"google/gemini-flash-latest":{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"input_audio":0.75},"sourceProvider":"google"},"google/gemini-flash-lite-latest":{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"google"},"google/gemini-omni-flash-preview":{"id":"google/gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":1.5,"output":17.5},"sourceProvider":"google"},"google/gemini-robotics-er-1.6-preview":{"id":"google/gemini-robotics-er-1.6-preview","name":"Gemini Robotics-ER 1.6 Preview","description":"Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":1,"output":5,"input_audio":2},"sourceProvider":"google"},"google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"sourceProvider":"google"},"google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"sourceProvider":"google"},"google/lyria-3-clip-preview":{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"google"},"google/lyria-3-pro-preview":{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","description":"Music generation model for full-length songs from text or images with vocals and structure","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"google"},"google/veo-3.1-fast-generate-preview":{"id":"google/veo-3.1-fast-generate-preview","name":"Veo 3.1 fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-10-15","last_updated":"2026-01-01","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"sourceProvider":"google"},"google/veo-3.1-generate-preview":{"id":"google/veo-3.1-generate-preview","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-10-15","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"status":"beta","sourceProvider":"google"},"google/veo-3.1-lite-generate-preview":{"id":"google/veo-3.1-lite-generate-preview","name":"Veo 3.1 lite","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":8192},"sourceProvider":"google"},"greenpt/deepseek-v4-flash-0731":{"id":"greenpt/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.1596,"output":0.399,"cache_read":0.0456},"sourceProvider":"greenpt"},"greenpt/devstral-2-123b-instruct-2512":{"id":"greenpt/devstral-2-123b-instruct-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":16384},"cost":{"input":0.57,"output":2.736},"sourceProvider":"greenpt"},"greenpt/gemma-3-27b-it":{"id":"greenpt/gemma-3-27b-it","name":"Gemma 3 27B","description":"Google Gemma 3 multimodal model for chat, reasoning, and image understanding","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":40000,"output":8192},"cost":{"input":0.342,"output":0.684},"sourceProvider":"greenpt"},"greenpt/gemma4":{"id":"greenpt/gemma4","name":"gemma4","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.57,"output":1.71},"sourceProvider":"greenpt"},"greenpt/glm-5.1":{"id":"greenpt/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"status":"deprecated","cost":{"input":1.756,"output":5.518},"sourceProvider":"greenpt"},"greenpt/glm-5.2":{"id":"greenpt/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-caveman":{"id":"greenpt/glm-5.2-caveman","name":"GLM-5.2 Caveman","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-caveman-lite":{"id":"greenpt/glm-5.2-caveman-lite","name":"GLM-5.2 Caveman Lite","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-caveman-ultra":{"id":"greenpt/glm-5.2-caveman-ultra","name":"GLM-5.2 Caveman Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses prose, keeping code and technical detail verbatim. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-honey":{"id":"greenpt/glm-5.2-honey","name":"GLM-5.2 Honey","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-honey-lite":{"id":"greenpt/glm-5.2-honey-lite","name":"GLM-5.2 Honey Lite","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-honey-ultra":{"id":"greenpt/glm-5.2-honey-ultra","name":"GLM-5.2 Honey Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses both generated code and prose. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-ponytail":{"id":"greenpt/glm-5.2-ponytail","name":"GLM-5.2 Ponytail","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The middle tier, and the ruleset as its authors wrote it. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-ponytail-lite":{"id":"greenpt/glm-5.2-ponytail-lite","name":"GLM-5.2 Ponytail Lite","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The gentlest tier: it cuts filler only and keeps the explanation intact. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/glm-5.2-ponytail-ultra":{"id":"greenpt/glm-5.2-ponytail-ultra","name":"GLM-5.2 Ponytail Ultra","description":"glm-5.2 carrying a built-in ruleset that compresses generated code, preferring platform features over custom code. The most aggressive tier, close to answer-only. Same upstream model and price per token as glm-5.2, with fewer output tokens.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.254,"output":5.016,"cache_read":0.3135},"sourceProvider":"greenpt"},"greenpt/gpt-oss-120b":{"id":"greenpt/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.228,"output":0.798},"sourceProvider":"greenpt"},"greenpt/green-l":{"id":"greenpt/green-l","name":"Green L","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":0.912},"sourceProvider":"greenpt"},"greenpt/green-l-raw":{"id":"greenpt/green-l-raw","name":"Green L Raw","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":0.912},"sourceProvider":"greenpt"},"greenpt/green-r":{"id":"greenpt/green-r","name":"Green R","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.399,"output":1.083},"sourceProvider":"greenpt"},"greenpt/green-r-raw":{"id":"greenpt/green-r-raw","name":"Green R Raw","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.399,"output":1.083},"sourceProvider":"greenpt"},"greenpt/green-s":{"id":"greenpt/green-s","name":"Green S","description":"GreenPT speech-to-text model for pre-recorded and live transcription","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-01","last_updated":"2025-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":8192},"cost":{"input":0.00437,"output":0},"sourceProvider":"greenpt"},"greenpt/green-s-pro":{"id":"greenpt/green-s-pro","name":"Green S Pro","description":"GreenPT advanced speech-to-text model with multilingual transcription support","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-02","last_updated":"2025-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":8192},"cost":{"input":0.00437,"output":0},"sourceProvider":"greenpt"},"greenpt/holo2-30b-a3b":{"id":"greenpt/holo2-30b-a3b","name":"Holo2 30B A3B","description":"H Company Holo2 vision model for GUI navigation and computer-use agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11","last_updated":"2025-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":22016,"output":16384},"cost":{"input":0.399,"output":0.969},"sourceProvider":"greenpt"},"greenpt/kimi-k2.6":{"id":"greenpt/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7524,"output":4.275,"cache_read":0.2508},"sourceProvider":"greenpt"},"greenpt/kimi-k2.6-fast":{"id":"greenpt/kimi-k2.6-fast","name":"Kimi K2.6 Fast","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":1.655,"output":8.778},"sourceProvider":"greenpt"},"greenpt/kimi-k2.7-code":{"id":"greenpt/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.9006,"output":4.389,"cache_read":0.1881},"sourceProvider":"greenpt"},"greenpt/kimi-k3":{"id":"greenpt/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3.762,"output":18.81,"cache_read":0.9405},"sourceProvider":"greenpt"},"greenpt/llama-3.3-70b-instruct":{"id":"greenpt/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":16384},"cost":{"input":1.254,"output":1.254},"sourceProvider":"greenpt"},"greenpt/minimax-m2.5":{"id":"greenpt/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.1938,"output":1.129,"cache_read":0.0627},"sourceProvider":"greenpt"},"greenpt/mistral-medium-3.5-128b":{"id":"greenpt/mistral-medium-3.5-128b","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":2.052,"output":10.26},"sourceProvider":"greenpt"},"greenpt/mistral-small-3.2-24b-instruct-2506":{"id":"greenpt/mistral-small-3.2-24b-instruct-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.228,"output":0.456},"sourceProvider":"greenpt"},"greenpt/pixtral-12b-2409":{"id":"greenpt/pixtral-12b-2409","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.285,"output":0.285},"sourceProvider":"greenpt"},"greenpt/qwen3-235b-a22b-instruct-2507":{"id":"greenpt/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen3 235B MoE instruct model for long-context multilingual chat and reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":1.026,"output":3.078},"sourceProvider":"greenpt"},"greenpt/qwen3-coder-30b-a3b-instruct":{"id":"greenpt/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.285,"output":1.083},"sourceProvider":"greenpt"},"greenpt/qwen3.5-397b-a17b":{"id":"greenpt/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.798,"output":4.959},"sourceProvider":"greenpt"},"greenpt/qwen3.6-35b-a3b":{"id":"greenpt/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.342,"output":2.052},"sourceProvider":"greenpt"},"greenpt/voxtral-small-24b-2507":{"id":"greenpt/voxtral-small-24b-2507","name":"Voxtral Small 24B","description":"Mistral Voxtral audio-understanding model for speech and transcription tasks","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.228,"output":0.513},"sourceProvider":"greenpt"},"groq/allam-2-7b":{"id":"groq/allam-2-7b","name":"ALLaM-2-7b","description":"ALLaM-2-7b instruction tuned model by SDAIA","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"groq"},"groq/canopylabs/orpheus-arabic-saudi":{"id":"canopylabs/orpheus-arabic-saudi","name":"Canopy Labs Orpheus Arabic Saudi","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":4000,"output":50000},"status":"beta","sourceProvider":"groq"},"groq/canopylabs/orpheus-v1-english":{"id":"canopylabs/orpheus-v1-english","name":"Canopy Labs Orpheus V1 English","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"canopylabs","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":4000,"output":50000},"status":"beta","sourceProvider":"groq"},"groq/compound":{"id":"groq/compound","name":"Compound","description":"General-purpose chat model for instruction following, writing, and analysis","family":"groq","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"sourceProvider":"groq"},"groq/compound-mini":{"id":"groq/compound-mini","name":"Compound Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"groq","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"sourceProvider":"groq"},"groq/llama-3.1-8b-instant":{"id":"groq/llama-3.1-8b-instant","name":"Llama 3.1 8B","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.08},"sourceProvider":"groq"},"groq/llama-3.3-70b-versatile":{"id":"groq/llama-3.3-70b-versatile","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.59,"output":0.79},"sourceProvider":"groq"},"groq/meta-llama/llama-prompt-guard-2-22m":{"id":"meta-llama/llama-prompt-guard-2-22m","name":"Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"status":"beta","cost":{"input":0.03,"output":0.03},"sourceProvider":"groq"},"groq/meta-llama/llama-prompt-guard-2-86m":{"id":"meta-llama/llama-prompt-guard-2-86m","name":"Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512,"output":512},"status":"beta","cost":{"input":0.04,"output":0.04},"sourceProvider":"groq"},"groq/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-10-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"groq"},"groq/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"groq"},"groq/openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"Safety GPT OSS 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2026-06-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"status":"beta","cost":{"input":0.075,"output":0.3},"sourceProvider":"groq"},"groq/qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","default"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.6,"output":3,"cache_read":0.3},"sourceProvider":"groq"},"groq/whisper-large-v3":{"id":"groq/whisper-large-v3","name":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2023-09-01","last_updated":"2025-09-05","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":0},"sourceProvider":"groq"},"groq/whisper-large-v3-turbo":{"id":"groq/whisper-large-v3-turbo","name":"Whisper Large V3 Turbo","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":0},"sourceProvider":"groq"},"helicone/chatgpt-4o-latest":{"id":"helicone/chatgpt-4o-latest","name":"OpenAI ChatGPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-14","last_updated":"2024-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":5,"output":20,"cache_read":2.5},"sourceProvider":"helicone"},"helicone/claude-3-haiku-20240307":{"id":"helicone/claude-3-haiku-20240307","name":"Anthropic: Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-03","release_date":"2024-03-07","last_updated":"2024-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"helicone"},"helicone/claude-3.5-haiku":{"id":"helicone/claude-3.5-haiku","name":"Anthropic: Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":0.7999999999999999,"output":4,"cache_read":0.08,"cache_write":1},"sourceProvider":"helicone"},"helicone/claude-3.5-sonnet-v2":{"id":"helicone/claude-3.5-sonnet-v2","name":"Anthropic: Claude 3.5 Sonnet v2","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"sourceProvider":"helicone"},"helicone/claude-3.7-sonnet":{"id":"helicone/claude-3.7-sonnet","name":"Anthropic: Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-02","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"sourceProvider":"helicone"},"helicone/claude-4.5-haiku":{"id":"helicone/claude-4.5-haiku","name":"Anthropic: Claude 4.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"sourceProvider":"helicone"},"helicone/claude-4.5-opus":{"id":"helicone/claude-4.5-opus","name":"Anthropic: Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"helicone"},"helicone/claude-4.5-sonnet":{"id":"helicone/claude-4.5-sonnet","name":"Anthropic: Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"sourceProvider":"helicone"},"helicone/claude-haiku-4-5-20251001":{"id":"helicone/claude-haiku-4-5-20251001","name":"Anthropic: Claude 4.5 Haiku (20251001)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-10","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"sourceProvider":"helicone"},"helicone/claude-opus-4":{"id":"helicone/claude-opus-4","name":"Anthropic: Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"helicone"},"helicone/claude-opus-4-1":{"id":"helicone/claude-opus-4-1","name":"Anthropic: Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"helicone"},"helicone/claude-opus-4-1-20250805":{"id":"helicone/claude-opus-4-1-20250805","name":"Anthropic: Claude Opus 4.1 (20250805)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"helicone"},"helicone/claude-sonnet-4":{"id":"helicone/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-14","last_updated":"2025-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"sourceProvider":"helicone"},"helicone/claude-sonnet-4-5-20250929":{"id":"helicone/claude-sonnet-4-5-20250929","name":"Anthropic: Claude Sonnet 4.5 (20250929)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.30000000000000004,"cache_write":3.75},"sourceProvider":"helicone"},"helicone/deepseek-r1-distill-llama-70b":{"id":"helicone/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.03,"output":0.13},"sourceProvider":"helicone"},"helicone/deepseek-reasoner":{"id":"helicone/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.56,"output":1.68,"cache_read":0.07},"sourceProvider":"helicone"},"helicone/deepseek-tng-r1t2-chimera":{"id":"helicone/deepseek-tng-r1t2-chimera","name":"DeepSeek TNG R1T2 Chimera","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-02","last_updated":"2025-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":163840},"cost":{"input":0.3,"output":1.2},"sourceProvider":"helicone"},"helicone/deepseek-v3":{"id":"helicone/deepseek-v3","name":"DeepSeek V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.56,"output":1.68,"cache_read":0.07},"sourceProvider":"helicone"},"helicone/deepseek-v3.1-terminus":{"id":"helicone/deepseek-v3.1-terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.27,"output":1,"cache_read":0.21600000000000003},"sourceProvider":"helicone"},"helicone/deepseek-v3.2":{"id":"helicone/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.41},"sourceProvider":"helicone"},"helicone/ernie-4.5-21b-a3b-thinking":{"id":"helicone/ernie-4.5-21b-a3b-thinking","name":"Baidu Ernie 4.5 21B A3B Thinking","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-03","release_date":"2025-03-16","last_updated":"2025-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"helicone"},"helicone/gemini-2.5-flash":{"id":"helicone/gemini-2.5-flash","name":"Google Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":0.3},"sourceProvider":"helicone"},"helicone/gemini-2.5-flash-lite":{"id":"helicone/gemini-2.5-flash-lite","name":"Google Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.024999999999999998,"cache_write":0.09999999999999999},"sourceProvider":"helicone"},"helicone/gemini-2.5-pro":{"id":"helicone/gemini-2.5-pro","name":"Google Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.3125,"cache_write":1.25},"sourceProvider":"helicone"},"helicone/gemini-3-pro-preview":{"id":"helicone/gemini-3-pro-preview","name":"Google Gemini 3 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.19999999999999998},"sourceProvider":"helicone"},"helicone/gemma-3-12b-it":{"id":"helicone/gemma-3-12b-it","name":"Google Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.049999999999999996,"output":0.09999999999999999},"sourceProvider":"helicone"},"helicone/gemma2-9b-it":{"id":"helicone/gemma2-9b-it","name":"Google Gemma 2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-25","last_updated":"2024-06-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.01,"output":0.03},"sourceProvider":"helicone"},"helicone/glm-4.6":{"id":"helicone/glm-4.6","name":"Zai GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.44999999999999996,"output":1.5},"sourceProvider":"helicone"},"helicone/gpt-4.1":{"id":"helicone/gpt-4.1","name":"OpenAI GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"helicone"},"helicone/gpt-4.1-mini":{"id":"helicone/gpt-4.1-mini","name":"OpenAI GPT-4.1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999},"sourceProvider":"helicone"},"helicone/gpt-4.1-mini-2025-04-14":{"id":"helicone/gpt-4.1-mini-2025-04-14","name":"OpenAI GPT-4.1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999},"sourceProvider":"helicone"},"helicone/gpt-4.1-nano":{"id":"helicone/gpt-4.1-nano","name":"OpenAI GPT-4.1 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.024999999999999998},"sourceProvider":"helicone"},"helicone/gpt-4o":{"id":"helicone/gpt-4o","name":"OpenAI GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"helicone"},"helicone/gpt-4o-mini":{"id":"helicone/gpt-4o-mini","name":"OpenAI GPT-4o-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"helicone"},"helicone/gpt-5":{"id":"helicone/gpt-5","name":"OpenAI GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5-chat-latest":{"id":"helicone/gpt-5-chat-latest","name":"OpenAI GPT-5 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2024-09","release_date":"2024-09-30","last_updated":"2024-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5-codex":{"id":"helicone/gpt-5-codex","name":"OpenAI: GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5-mini":{"id":"helicone/gpt-5-mini","name":"OpenAI GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.024999999999999998},"sourceProvider":"helicone"},"helicone/gpt-5-nano":{"id":"helicone/gpt-5-nano","name":"OpenAI GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.005},"sourceProvider":"helicone"},"helicone/gpt-5-pro":{"id":"helicone/gpt-5-pro","name":"OpenAI: GPT-5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":15,"output":120},"sourceProvider":"helicone"},"helicone/gpt-5.1":{"id":"helicone/gpt-5.1","name":"OpenAI GPT-5.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5.1-chat-latest":{"id":"helicone/gpt-5.1-chat-latest","name":"OpenAI GPT-5.1 Chat","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5.1-codex":{"id":"helicone/gpt-5.1-codex","name":"OpenAI: GPT-5.1 Codex","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.12500000000000003},"sourceProvider":"helicone"},"helicone/gpt-5.1-codex-mini":{"id":"helicone/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1 Codex Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-codex","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.024999999999999998},"sourceProvider":"helicone"},"helicone/gpt-oss-120b":{"id":"helicone/gpt-oss-120b","name":"OpenAI GPT-OSS 120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.04,"output":0.16},"sourceProvider":"helicone"},"helicone/gpt-oss-20b":{"id":"helicone/gpt-oss-20b","name":"OpenAI GPT-OSS 20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.049999999999999996,"output":0.19999999999999998},"sourceProvider":"helicone"},"helicone/grok-3":{"id":"helicone/grok-3","name":"xAI Grok 3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"helicone"},"helicone/grok-3-mini":{"id":"helicone/grok-3-mini","name":"xAI Grok 3 Mini","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":0.5,"cache_read":0.075},"sourceProvider":"helicone"},"helicone/grok-4":{"id":"helicone/grok-4","name":"xAI Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-09","last_updated":"2024-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"helicone"},"helicone/grok-4-1-fast-non-reasoning":{"id":"helicone/grok-4-1-fast-non-reasoning","name":"xAI Grok 4.1 Fast Non-Reasoning","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"sourceProvider":"helicone"},"helicone/grok-4-1-fast-reasoning":{"id":"helicone/grok-4-1-fast-reasoning","name":"xAI Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-17","last_updated":"2025-11-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"sourceProvider":"helicone"},"helicone/grok-4-fast-non-reasoning":{"id":"helicone/grok-4-fast-non-reasoning","name":"xAI Grok 4 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"sourceProvider":"helicone"},"helicone/grok-4-fast-reasoning":{"id":"helicone/grok-4-fast-reasoning","name":"xAI: Grok 4 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.19999999999999998,"output":0.5,"cache_read":0.049999999999999996},"sourceProvider":"helicone"},"helicone/grok-code-fast-1":{"id":"helicone/grok-code-fast-1","name":"xAI Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-25","last_updated":"2024-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"cost":{"input":0.19999999999999998,"output":1.5,"cache_read":0.02},"sourceProvider":"helicone"},"helicone/hermes-2-pro-llama-3-8b":{"id":"helicone/hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-05-27","last_updated":"2024-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.14,"output":0.14},"sourceProvider":"helicone"},"helicone/kimi-k2-0711":{"id":"helicone/kimi-k2-0711","name":"Kimi K2 (07/11)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.5700000000000001,"output":2.3},"sourceProvider":"helicone"},"helicone/kimi-k2-0905":{"id":"helicone/kimi-k2-0905","name":"Kimi K2 (09/05)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.5,"output":2,"cache_read":0.39999999999999997},"sourceProvider":"helicone"},"helicone/kimi-k2-thinking":{"id":"helicone/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":262144},"cost":{"input":0.48,"output":2},"sourceProvider":"helicone"},"helicone/llama-3.1-8b-instant":{"id":"helicone/llama-3.1-8b-instant","name":"Meta Llama 3.1 8B Instant","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32678},"cost":{"input":0.049999999999999996,"output":0.08},"sourceProvider":"helicone"},"helicone/llama-3.1-8b-instruct":{"id":"helicone/llama-3.1-8b-instruct","name":"Meta Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.049999999999999996},"sourceProvider":"helicone"},"helicone/llama-3.1-8b-instruct-turbo":{"id":"helicone/llama-3.1-8b-instruct-turbo","name":"Meta Llama 3.1 8B Instruct Turbo","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.03},"sourceProvider":"helicone"},"helicone/llama-3.3-70b-instruct":{"id":"helicone/llama-3.3-70b-instruct","name":"Meta Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16400},"cost":{"input":0.13,"output":0.39},"sourceProvider":"helicone"},"helicone/llama-3.3-70b-versatile":{"id":"helicone/llama-3.3-70b-versatile","name":"Meta Llama 3.3 70B Versatile","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32678},"cost":{"input":0.59,"output":0.7899999999999999},"sourceProvider":"helicone"},"helicone/llama-4-maverick":{"id":"helicone/llama-4-maverick","name":"Meta Llama 4 Maverick 17B 128E","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"helicone"},"helicone/llama-4-scout":{"id":"helicone/llama-4-scout","name":"Meta Llama 4 Scout 17B 16E","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.08,"output":0.3},"sourceProvider":"helicone"},"helicone/llama-guard-4":{"id":"helicone/llama-guard-4","name":"Meta Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":1024},"cost":{"input":0.21,"output":0.21},"sourceProvider":"helicone"},"helicone/llama-prompt-guard-2-22m":{"id":"helicone/llama-prompt-guard-2-22m","name":"Meta Llama Prompt Guard 2 22M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":512,"output":2},"cost":{"input":0.01,"output":0.01},"sourceProvider":"helicone"},"helicone/llama-prompt-guard-2-86m":{"id":"helicone/llama-prompt-guard-2-86m","name":"Meta Llama Prompt Guard 2 86M","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":512,"output":2},"cost":{"input":0.01,"output":0.01},"sourceProvider":"helicone"},"helicone/mistral-large-2411":{"id":"helicone/mistral-large-2411","name":"Mistral-Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-24","last_updated":"2024-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":6},"sourceProvider":"helicone"},"helicone/mistral-nemo":{"id":"helicone/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16400},"cost":{"input":20,"output":40},"sourceProvider":"helicone"},"helicone/mistral-small":{"id":"helicone/mistral-small","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.2},"sourceProvider":"helicone"},"helicone/o1":{"id":"helicone/o1","name":"OpenAI: o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"helicone"},"helicone/o1-mini":{"id":"helicone/o1-mini","name":"OpenAI: o1-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":65536},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"helicone"},"helicone/o3":{"id":"helicone/o3","name":"OpenAI o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"helicone"},"helicone/o3-mini":{"id":"helicone/o3-mini","name":"OpenAI o3 Mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2023-10","release_date":"2023-10-01","last_updated":"2023-10-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"helicone"},"helicone/o3-pro":{"id":"helicone/o3-pro","name":"OpenAI o3 Pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"helicone"},"helicone/o4-mini":{"id":"helicone/o4-mini","name":"OpenAI o4 Mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":false,"knowledge":"2024-06","release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"helicone"},"helicone/qwen2.5-coder-7b-fast":{"id":"helicone/qwen2.5-coder-7b-fast","name":"Qwen2.5 Coder 7B fast","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-15","last_updated":"2024-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":8192},"cost":{"input":0.03,"output":0.09},"sourceProvider":"helicone"},"helicone/qwen3-235b-a22b-thinking":{"id":"helicone/qwen3-235b-a22b-thinking","name":"Qwen3 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":81920},"cost":{"input":0.3,"output":2.9000000000000004},"sourceProvider":"helicone"},"helicone/qwen3-30b-a3b":{"id":"helicone/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":41000,"output":41000},"cost":{"input":0.08,"output":0.29},"sourceProvider":"helicone"},"helicone/qwen3-32b":{"id":"helicone/qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":40960},"cost":{"input":0.29,"output":0.59},"sourceProvider":"helicone"},"helicone/qwen3-coder":{"id":"helicone/qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.22,"output":0.95},"sourceProvider":"helicone"},"helicone/qwen3-coder-30b-a3b-instruct":{"id":"helicone/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.09999999999999999,"output":0.3},"sourceProvider":"helicone"},"helicone/qwen3-next-80b-a3b-instruct":{"id":"helicone/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":16384},"cost":{"input":0.14,"output":1.4},"sourceProvider":"helicone"},"helicone/qwen3-vl-235b-a22b-instruct":{"id":"helicone/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.3,"output":1.5},"sourceProvider":"helicone"},"helicone/sonar":{"id":"helicone/sonar","name":"Perplexity Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"helicone"},"helicone/sonar-deep-research":{"id":"helicone/sonar-deep-research","name":"Perplexity Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"helicone"},"helicone/sonar-pro":{"id":"helicone/sonar-pro","name":"Perplexity Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":3,"output":15},"sourceProvider":"helicone"},"helicone/sonar-reasoning":{"id":"helicone/sonar-reasoning","name":"Perplexity Sonar Reasoning","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":1,"output":5},"sourceProvider":"helicone"},"helicone/sonar-reasoning-pro":{"id":"helicone/sonar-reasoning-pro","name":"Perplexity Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"helicone"},"hetzner/Qwen/Qwen3.6-35B-A3B-FP8":{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"hetzner"},"hetzner/Qwen3.8-27B":{"id":"hetzner/Qwen3.8-27B","name":"Qwen3.8-27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"beta","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"hetzner"},"hpc-ai/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"hpc-ai"},"hpc-ai/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"hpc-ai"},"hpc-ai/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1002000,"output":128000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"hpc-ai"},"hpc-ai/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196000,"output":195000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"hpc-ai"},"hpc-ai/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"hpc-ai"},"hpc-ai/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"hpc-ai"},"hpc-ai/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"hpc-ai"},"hpc-ai/zai-org/glm-5.1":{"id":"zai-org/glm-5.1","name":"GLM 5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":202000},"cost":{"input":0.615,"output":2.46,"cache_read":0.133},"sourceProvider":"hpc-ai"},"hpc-ai/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"hpc-ai"},"huggingface/deepseek-ai/DeepSeek-R1":{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":32768},"cost":{"input":0.7,"output":2.5},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":3,"output":5},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":8192},"cost":{"input":0.4,"output":1.3},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V3-0324":{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.27,"output":1.12},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.27,"output":1},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.28,"output":0.4},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"huggingface"},"huggingface/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96},"sourceProvider":"huggingface"},"huggingface/google/gemma-4-26B-A4B-it":{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.4},"sourceProvider":"huggingface"},"huggingface/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"sourceProvider":"huggingface"},"huggingface/meta-llama/Llama-3.1-8B-Instruct":{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.06,"output":0.06},"sourceProvider":"huggingface"},"huggingface/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.59,"output":0.79},"sourceProvider":"huggingface"},"huggingface/MiniMaxAI/MiniMax-M2":{"id":"MiniMaxAI/MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"huggingface"},"huggingface/MiniMaxAI/MiniMax-M2.1":{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-10","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"huggingface"},"huggingface/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"huggingface"},"huggingface/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"huggingface"},"huggingface/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2-Instruct":{"id":"moonshotai/Kimi-K2-Instruct","name":"Kimi-K2-Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-14","last_updated":"2025-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":3},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2-Instruct-0905":{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi-K2-Instruct-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":1,"output":3},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2-Thinking":{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi-K2-Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"sourceProvider":"huggingface"},"huggingface/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15},"sourceProvider":"huggingface"},"huggingface/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.25,"output":0.69},"sourceProvider":"huggingface"},"huggingface/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.5},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen2.5-Coder-32B-Instruct":{"id":"Qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen2.5-Coder-32B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.06,"output":0.2},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-235B-A22B":{"id":"Qwen/Qwen3-235B-A22B","name":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.2,"output":0.8},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.855,"output":2.565},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":3},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-30B-A3B":{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.29,"output":0.59},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Coder-30B-A3B-Instruct":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.07,"output":0.26},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":2,"output":2},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Coder-Next":{"id":"Qwen/Qwen3-Coder-Next","name":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Embedding-4B":{"id":"Qwen/Qwen3-Embedding-4B","name":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2048},"cost":{"input":0.01,"output":0},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Embedding-8B":{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen 3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.01,"output":0},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Next-80B-A3B-Instruct":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":66536},"cost":{"input":0.25,"output":1},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-Next-80B-A3B-Thinking":{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":2},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-VL-235B-A22B-Instruct":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":1.5},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3-VL-235B-A22B-Thinking":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.5-122B-A10B":{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.5-27B":{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.5-35B-A3B":{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3.6},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.17,"output":0.25},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.47,"output":3.19},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.95},"sourceProvider":"huggingface"},"huggingface/Qwen/Qwen3.8-2.4T-A95B":{"id":"Qwen/Qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2.5,"output":6.25},"sourceProvider":"huggingface"},"huggingface/stepfun-ai/Step-3.5-Flash":{"id":"stepfun-ai/Step-3.5-Flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"huggingface"},"huggingface/stepfun-ai/Step-3.7-Flash":{"id":"stepfun-ai/Step-3.7-Flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.2,"output":1.15},"sourceProvider":"huggingface"},"huggingface/tencent/Hy3":{"id":"tencent/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.14,"output":0.58},"sourceProvider":"huggingface"},"huggingface/thinkingmachines/Inkling":{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":4.05},"sourceProvider":"huggingface"},"huggingface/thinkingmachines/Inkling-Small":{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":1048576},"cost":{"input":0.5,"output":1.2},"sourceProvider":"huggingface"},"huggingface/XiaomiMiMo/MiMo-V2-Flash":{"id":"XiaomiMiMo/MiMo-V2-Flash","name":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.1,"output":0.3},"sourceProvider":"huggingface"},"huggingface/XiaomiMiMo/MiMo-V2.5":{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"MiMo model for long-context reasoning, perception, and agentic tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.4,"output":2},"sourceProvider":"huggingface"},"huggingface/XiaomiMiMo/MiMo-V2.5-Pro":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":3},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.5":{"id":"zai-org/GLM-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.5-Air":{"id":"zai-org/GLM-4.5-Air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.5V":{"id":"zai-org/GLM-4.5V","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.6":{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.6V-Flash":{"id":"zai-org/GLM-4.6V-Flash","name":"GLM-4.6V-Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-4.7-Flash":{"id":"zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-03","last_updated":"2026-04-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"huggingface"},"huggingface/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.4,"output":4.4},"sourceProvider":"huggingface"},"hyper/deepseek-v4-flash":{"id":"hyper/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-06","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"sourceProvider":"hyper"},"hyper/deepseek-v4-flash-0731":{"id":"hyper/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.479072,"output":1.437216,"cache_read":0.015243},"sourceProvider":"hyper"},"hyper/deepseek-v4-pro":{"id":"hyper/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-06","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":2.4,"output":4.8,"cache_read":0.2},"sourceProvider":"hyper"},"hyper/deepseek-v4-pro-0813":{"id":"hyper/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.437216,"output":4.311648,"cache_read":0.047907},"sourceProvider":"hyper"},"hyper/gemma-4-26b-a4b-it":{"id":"hyper/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":25600},"cost":{"input":0.11,"output":0.408,"cache_write":0.055},"sourceProvider":"hyper"},"hyper/glm-5":{"id":"hyper/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-04-13","last_updated":"2026-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":20275},"cost":{"input":0.91,"output":2.934,"cache_write":0.455},"sourceProvider":"hyper"},"hyper/glm-5.1":{"id":"hyper/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202750,"output":3276},"cost":{"input":1.36,"output":4.4,"cache_write":0.68},"sourceProvider":"hyper"},"hyper/glm-5.2":{"id":"hyper/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":1.52432,"output":4.79072,"cache_read":0.152432},"sourceProvider":"hyper"},"hyper/gpt-oss-120b":{"id":"hyper/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-13","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":13107},"cost":{"input":0.188,"output":0.7,"cache_write":0.094},"sourceProvider":"hyper"},"hyper/kimi-k2.5":{"id":"hyper/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-13","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":26214},"cost":{"input":0.5444,"output":2.855,"cache_write":0.2722},"sourceProvider":"hyper"},"hyper/kimi-k2.6":{"id":"hyper/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-07-03","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":26214},"cost":{"input":1.03436,"output":4.3552,"cache_read":0.174208},"sourceProvider":"hyper"},"hyper/kimi-k2.7-code":{"id":"hyper/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-07-03","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16000},"cost":{"input":1.03436,"output":4.3552,"cache_read":0.206872},"sourceProvider":"hyper"},"hyper/kimi-k3":{"id":"hyper/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-27","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16000},"cost":{"input":3.2664,"output":16.332,"cache_read":0.32664},"sourceProvider":"hyper"},"hyper/llama-3.3-70b-instruct":{"id":"hyper/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":12800},"cost":{"input":0.638,"output":0.768,"cache_write":0.319},"sourceProvider":"hyper"},"hyper/llama-4-maverick-17b-128e-instruct-fp8":{"id":"hyper/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":430000,"output":43000},"cost":{"input":0.274,"output":0.8992,"cache_write":0.137},"sourceProvider":"hyper"},"hyper/minimax-m2.7":{"id":"hyper/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-05","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":6553},"cost":{"input":0.408,"output":1.512,"cache_write":0.204},"sourceProvider":"hyper"},"hyper/minimax-m3":{"id":"hyper/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":512000},"cost":{"input":0.32664,"output":1.30656,"cache_read":0.064239},"sourceProvider":"hyper"},"hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar":{"id":"hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":106000,"output":10600},"cost":{"input":0.445,"output":2.145,"cache_write":0.2225},"sourceProvider":"hyper"},"hyper/qwen3-next-80b-a3b-instruct":{"id":"hyper/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-30","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":26214},"cost":{"input":0.1175,"output":1.136,"cache_write":0.05875},"sourceProvider":"hyper"},"hyper/qwen3.6-flash":{"id":"hyper/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-20","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1,"output":4,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"hyper"},"hyper/qwen3.6-max":{"id":"hyper/qwen3.6-max","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-20","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"hyper"},"hyper/qwen3.6-plus":{"id":"hyper/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-20","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"hyper"},"hyper/qwen3.7-flash":{"id":"hyper/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-27","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":64000},"cost":{"input":0.2,"output":0.8,"cache_read":0.04},"sourceProvider":"hyper"},"hyper/qwen3.7-max":{"id":"hyper/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"sourceProvider":"hyper"},"hyper/qwen3.7-plus":{"id":"hyper/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-15","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.2,"output":4.8,"cache_read":0.24},"sourceProvider":"hyper"},"hyper/qwen3.8-max":{"id":"hyper/qwen3.8-max","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.25},"sourceProvider":"hyper"},"iflowcn/deepseek-r1":{"id":"iflowcn/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/deepseek-v3":{"id":"iflowcn/deepseek-v3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/deepseek-v3.2":{"id":"iflowcn/deepseek-v3.2","name":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/glm-4.6":{"id":"iflowcn/glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/kimi-k2":{"id":"iflowcn/kimi-k2","name":"Kimi-K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/kimi-k2-0905":{"id":"iflowcn/kimi-k2-0905","name":"Kimi-K2-0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-235b":{"id":"iflowcn/qwen3-235b","name":"Qwen3-235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-235b-a22b-instruct":{"id":"iflowcn/qwen3-235b-a22b-instruct","name":"Qwen3-235B-A22B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-235b-a22b-thinking-2507":{"id":"iflowcn/qwen3-235b-a22b-thinking-2507","name":"Qwen3-235B-A22B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-32b":{"id":"iflowcn/qwen3-32b","name":"Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-coder-plus":{"id":"iflowcn/qwen3-coder-plus","name":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-max":{"id":"iflowcn/qwen3-max","name":"Qwen3-Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-max-preview":{"id":"iflowcn/qwen3-max-preview","name":"Qwen3-Max-Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"iflowcn/qwen3-vl-plus":{"id":"iflowcn/qwen3-vl-plus","name":"Qwen3-VL-Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"iflowcn"},"impossibl/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-opus-4-5":{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"impossibl"},"impossibl/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"impossibl"},"impossibl/cerebras/gpt-oss-120b":{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75},"sourceProvider":"impossibl"},"impossibl/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.19,"output":0.51,"cache_read":0.028},"sourceProvider":"impossibl"},"impossibl/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"impossibl"},"impossibl/fireworks/glm-5.2":{"id":"fireworks/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.14},"sourceProvider":"impossibl"},"impossibl/fireworks/gpt-oss-120b":{"id":"fireworks/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"impossibl"},"impossibl/fireworks/gpt-oss-20b":{"id":"fireworks/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.07,"output":0.3,"cache_read":0.035},"sourceProvider":"impossibl"},"impossibl/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"impossibl"},"impossibl/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"impossibl"},"impossibl/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"impossibl"},"impossibl/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"sourceProvider":"impossibl"},"impossibl/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"impossibl"},"impossibl/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"impossibl"},"impossibl/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"impossibl"},"impossibl/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"sourceProvider":"impossibl"},"impossibl/groq/gpt-oss-120b":{"id":"groq/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"impossibl"},"impossibl/groq/gpt-oss-20b":{"id":"groq/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"impossibl"},"impossibl/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"impossibl"},"impossibl/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"impossibl"},"impossibl/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":3}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"cache_read":3,"tiers":[{"input":60,"output":270,"cache_read":3,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270,"cache_read":3}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"impossibl"},"impossibl/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"impossibl"},"impossibl/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"impossibl"},"impossibl/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"impossibl"},"impossibl/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"impossibl"},"impossibl/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"impossibl"},"impossibl/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"tiers":[{"input":1,"output":4,"cache_read":0.2,"tier":{"type":"context","size":262144}}],"context_over_200k":{"input":1,"output":4,"cache_read":0.2}},"sourceProvider":"impossibl"},"impossibl/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5},"sourceProvider":"impossibl"},"impossibl/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"tier":{"type":"context","size":262144}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24}},"sourceProvider":"impossibl"},"impossibl/qwen/qwen3.8-max-preview":{"id":"qwen/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.5,"output":7.5},"sourceProvider":"impossibl"},"impossibl/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"sourceProvider":"impossibl"},"impossibl/xai/grok-4.20-0309-non-reasoning":{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"impossibl"},"impossibl/xai/grok-4.20-0309-reasoning":{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"impossibl"},"impossibl/xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"impossibl"},"impossibl/xai/grok-4.5":{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"impossibl"},"impossibl/xai/grok-build-0.1":{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"impossibl"},"impossibl/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.003},"sourceProvider":"impossibl"},"impossibl/zai/glm-4.5":{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"impossibl"},"impossibl/zai/glm-4.5-air":{"id":"zai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"sourceProvider":"impossibl"},"impossibl/zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"impossibl"},"impossibl/zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"impossibl"},"impossibl/zai/glm-5":{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"impossibl"},"impossibl/zai/glm-5-turbo":{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"impossibl"},"impossibl/zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"impossibl"},"impossibl/zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"impossibl"},"inception/mercury-2":{"id":"inception/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"sourceProvider":"inception"},"inception/mercury-edit-2":{"id":"inception/mercury-edit-2","name":"Mercury Edit 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"sourceProvider":"inception"},"inceptron/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.13,"output":0.28,"cache_read":0.03,"cache_write":0},"sourceProvider":"inceptron"},"inceptron/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3.41,"cache_read":0.2,"cache_write":0},"sourceProvider":"inceptron"},"inceptron/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.67,"output":3.4,"cache_read":0.17,"cache_write":0},"sourceProvider":"inceptron"},"inceptron/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.75,"output":2.9,"cache_read":0.17,"cache_write":0},"sourceProvider":"inceptron"},"inference/google/gemma-3":{"id":"google/gemma-3","name":"Google Gemma 3","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":125000,"output":4096},"cost":{"input":0.15,"output":0.3},"sourceProvider":"inference"},"inference/meta/llama-3.1-8b-instruct":{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.025,"output":0.025},"sourceProvider":"inference"},"inference/meta/llama-3.2-11b-vision-instruct":{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.055,"output":0.055},"sourceProvider":"inference"},"inference/meta/llama-3.2-1b-instruct":{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.01,"output":0.01},"sourceProvider":"inference"},"inference/meta/llama-3.2-3b-instruct":{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.02,"output":0.02},"sourceProvider":"inference"},"inference/mistral/mistral-nemo-12b-instruct":{"id":"mistral/mistral-nemo-12b-instruct","name":"Mistral Nemo 12B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.038,"output":0.1},"sourceProvider":"inference"},"inference/osmosis/osmosis-structure-0.6b":{"id":"osmosis/osmosis-structure-0.6b","name":"Osmosis Structure 0.6B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"osmosis","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4000,"output":2048},"cost":{"input":0.1,"output":0.5},"sourceProvider":"inference"},"inference/qwen/qwen-2.5-7b-vision-instruct":{"id":"qwen/qwen-2.5-7b-vision-instruct","name":"Qwen 2.5 7B Vision Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":125000,"output":4096},"cost":{"input":0.2,"output":0.2},"sourceProvider":"inference"},"inference/qwen/qwen3-embedding-4b":{"id":"qwen/qwen3-embedding-4b","name":"Qwen 3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2048},"cost":{"input":0.01,"output":0},"sourceProvider":"inference"},"inferx/Agents-A1":{"id":"inferx/Agents-A1","name":"Agents-A1","description":"35B MoE agentic model built for long-horizon search, engineering, and scientific reasoning tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-06-26","last_updated":"2026-06-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":100000},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/deepseek-v4-flash":{"id":"inferx/deepseek-v4-flash","name":"deepseek-v4-flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":100000},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound":{"id":"inferx/Devstral-2-123B-Instruct-2512-int4-AutoRound","name":"Devstral-2-123B-Instruct-2512-int4-AutoRound","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/gemma-4-31B-it-fp8":{"id":"inferx/gemma-4-31B-it-fp8","name":"Gemma 4 31B IT FP8","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/mimo-v25":{"id":"inferx/mimo-v25","name":"mimo-v25","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":100000},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Ornith-1.0-35B-FP8":{"id":"inferx/Ornith-1.0-35B-FP8","name":"Ornith-1.0-35B-FP8","description":"Large coding-reasoning model for agentic software tasks and RL search","family":"ornith","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-25","last_updated":"2026-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":100000},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3-Coder-Next-FP8":{"id":"inferx/Qwen3-Coder-Next-FP8","name":"Qwen3 Coder Next FP8","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3-Coder-Next-FP8-no-thinking":{"id":"inferx/Qwen3-Coder-Next-FP8-no-thinking","name":"Qwen3-Coder-Next-FP8-no-thinking","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":260000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3-Embedding-8B":{"id":"inferx/Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3.6-27B-FP8":{"id":"inferx/Qwen3.6-27B-FP8","name":"Qwen3.6 27B FP8","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3.6-35B-A3B-FP8":{"id":"inferx/Qwen3.6-35B-A3B-FP8","name":"Qwen3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"inferx/Qwen3.6-35B-A3B-fp8-no-thinking":{"id":"inferx/Qwen3.6-35B-A3B-fp8-no-thinking","name":"Qwen3.6-35B-A3B-fp8-no-thinking","description":"Qwen3.6-35B-A3B-fp8 disable thinking","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"inferx"},"infomaniak/bge_multilingual_gemma2":{"id":"infomaniak/bge_multilingual_gemma2","name":"BGE Multilingual Gemma2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-07-25","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":8000,"output":3584},"cost":{"input":0.08,"output":0},"sourceProvider":"infomaniak"},"infomaniak/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":32768},"cost":{"input":0.25,"output":0.5},"sourceProvider":"infomaniak"},"infomaniak/mini_lm_l12_v2":{"id":"infomaniak/mini_lm_l12_v2","name":"All-MiniLM-L12-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2021-08-30","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128,"input":128,"output":384},"cost":{"input":0,"output":0},"sourceProvider":"infomaniak"},"infomaniak/mistralai/Ministral-3-14B-Instruct-2512":{"id":"mistralai/Ministral-3-14B-Instruct-2512","name":"Ministral 3 14B Instruct","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":25600},"status":"beta","cost":{"input":0.37,"output":0.5},"sourceProvider":"infomaniak"},"infomaniak/mistralai/Mistral-Small-4-119B-2603":{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.25,"output":0.93},"sourceProvider":"infomaniak"},"infomaniak/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"status":"beta","cost":{"input":0.74,"output":3.72},"sourceProvider":"infomaniak"},"infomaniak/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8":{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8","name":"Nemotron 3 Nano 30B A3B FP8","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":262144},"status":"beta","cost":{"input":0.06,"output":0.25},"sourceProvider":"infomaniak"},"infomaniak/Qwen/Qwen3.5-122B-A10B-FP8":{"id":"Qwen/Qwen3.5-122B-A10B-FP8","name":"Qwen3.5 122B-A10B FP8","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65536},"cost":{"input":0.5,"output":3.97},"sourceProvider":"infomaniak"},"infomaniak/Qwen/Qwen3.5-397B-A17B-FP8":{"id":"Qwen/Qwen3.5-397B-A17B-FP8","name":"Qwen3.5 397B-A17B FP8","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-08-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65536},"status":"beta","cost":{"input":0.99,"output":4.46},"sourceProvider":"infomaniak"},"infomaniak/swiss-ai/Apertus-v1.5-70B":{"id":"swiss-ai/Apertus-v1.5-70B","name":"Apertus v1.5 70B","description":"Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-07-24","last_updated":"2026-08-01","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"input":100000,"output":8192},"status":"beta","cost":{"input":0.87,"output":3.1},"sourceProvider":"infomaniak"},"io-net/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8.75,"cache_read":1,"cache_write":4},"sourceProvider":"io-net"},"io-net/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar":{"id":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","name":"Qwen 3 Coder 480B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":106000,"output":4096},"cost":{"input":0.22,"output":0.95,"cache_read":0.11,"cache_write":0.44},"sourceProvider":"io-net"},"io-net/meta-llama/Llama-3.2-90B-Vision-Instruct":{"id":"meta-llama/Llama-3.2-90B-Vision-Instruct","name":"Llama 3.2 90B Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0.35,"output":0.4,"cache_read":0.175,"cache_write":0.7},"sourceProvider":"io-net"},"io-net/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.13,"output":0.38,"cache_read":0.065,"cache_write":0.26},"sourceProvider":"io-net"},"io-net/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8":{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"Llama 4 Maverick 17B 128E Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":430000,"output":4096},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.3},"sourceProvider":"io-net"},"io-net/mistralai/Devstral-Small-2505":{"id":"mistralai/Devstral-Small-2505","name":"Devstral Small 2505","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-05-01","last_updated":"2025-05-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1},"sourceProvider":"io-net"},"io-net/mistralai/Magistral-Small-2506":{"id":"mistralai/Magistral-Small-2506","name":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-01","last_updated":"2025-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0.25,"cache_write":1},"sourceProvider":"io-net"},"io-net/mistralai/Mistral-Large-Instruct-2411":{"id":"mistralai/Mistral-Large-Instruct-2411","name":"Mistral Large Instruct 2411","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":6,"cache_read":1,"cache_write":4},"sourceProvider":"io-net"},"io-net/mistralai/Mistral-Nemo-Instruct-2407":{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo Instruct 2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.02,"output":0.04,"cache_read":0.01,"cache_write":0.04},"sourceProvider":"io-net"},"io-net/moonshotai/Kimi-K2-Instruct-0905":{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-09-05","last_updated":"2024-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.39,"output":1.9,"cache_read":0.195,"cache_write":0.78},"sourceProvider":"io-net"},"io-net/moonshotai/Kimi-K2-Thinking":{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.55,"output":2.25,"cache_read":0.275,"cache_write":1.1},"sourceProvider":"io-net"},"io-net/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.04,"output":0.4,"cache_read":0.02,"cache_write":0.08},"sourceProvider":"io-net"},"io-net/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT-OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":4096},"cost":{"input":0.03,"output":0.14,"cache_read":0.015,"cache_write":0.06},"sourceProvider":"io-net"},"io-net/Qwen/Qwen2.5-VL-32B-Instruct":{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen 2.5 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.05,"output":0.22,"cache_read":0.025,"cache_write":0.1},"sourceProvider":"io-net"},"io-net/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen 3 235B Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-07-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.11,"output":0.6,"cache_read":0.055,"cache_write":0.22},"sourceProvider":"io-net"},"io-net/Qwen/Qwen3-Next-80B-A3B-Instruct":{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen 3 Next 80B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-10","last_updated":"2025-01-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":4096},"cost":{"input":0.1,"output":0.8,"cache_read":0.05,"cache_write":0.2},"sourceProvider":"io-net"},"io-net/zai-org/GLM-4.6":{"id":"zai-org/GLM-4.6","name":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-11-15","last_updated":"2024-11-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.4,"output":1.75,"cache_read":0.2,"cache_write":0.8},"sourceProvider":"io-net"},"jalapeno/DeepSeek-V4-Flash":{"id":"jalapeno/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.14,"output":0.28},"sourceProvider":"jalapeno"},"jalapeno/DeepSeek-V4-Pro":{"id":"jalapeno/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.6,"output":3.38},"sourceProvider":"jalapeno"},"jalapeno/GLM-5.1":{"id":"jalapeno/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.38,"output":4.4},"sourceProvider":"jalapeno"},"jalapeno/GLM-5.2":{"id":"jalapeno/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4},"sourceProvider":"jalapeno"},"jalapeno/Hy3":{"id":"jalapeno/Hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":64000},"cost":{"input":0.14,"output":0.58},"sourceProvider":"jalapeno"},"jalapeno/Kimi-K2.5":{"id":"jalapeno/Kimi-K2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":180224},"cost":{"input":0.6,"output":3},"sourceProvider":"jalapeno"},"jalapeno/Kimi-K2.7-Code":{"id":"jalapeno/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":271360,"output":262144},"cost":{"input":0.95,"output":4},"sourceProvider":"jalapeno"},"jalapeno/Kimi-K3":{"id":"jalapeno/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15},"sourceProvider":"jalapeno"},"jalapeno/MiniMax-M3":{"id":"jalapeno/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"jalapeno"},"jalapeno/Qwen3-Next-80B-A3B-Instruct":{"id":"jalapeno/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":129024,"output":32768},"cost":{"input":0.15,"output":1.5},"sourceProvider":"jalapeno"},"jalapeno/Qwen3-Next-80B-A3B-Thinking":{"id":"jalapeno/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"sourceProvider":"jalapeno"},"jalapeno/Qwen3-VL-235B-A22B-Instruct":{"id":"jalapeno/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":129024,"output":32768},"cost":{"input":0.3,"output":1.5},"sourceProvider":"jalapeno"},"jalapeno/Qwen3-VL-235B-A22B-Thinking":{"id":"jalapeno/Qwen3-VL-235B-A22B-Thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"sourceProvider":"jalapeno"},"jalapeno/Qwen3.5-122B-A10B":{"id":"jalapeno/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"sourceProvider":"jalapeno"},"jalapeno/Qwen3.5-27B":{"id":"jalapeno/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"sourceProvider":"jalapeno"},"jalapeno/Qwen3.5-35B-A3B":{"id":"jalapeno/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"sourceProvider":"jalapeno"},"jalapeno/Qwen3.5-397B-A17B":{"id":"jalapeno/Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"jalapeno"},"jiekou/baidu/ernie-4.5-300b-a47b-paddle":{"id":"baidu/ernie-4.5-300b-a47b-paddle","name":"ERNIE 4.5 300B A47B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ernie","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":123000,"output":12000},"cost":{"input":0.28,"output":1.1},"sourceProvider":"jiekou"},"jiekou/baidu/ernie-4.5-vl-424b-a47b":{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"jiekou"},"jiekou/claude-haiku-4-5-20251001":{"id":"jiekou/claude-haiku-4-5-20251001","name":"claude-haiku-4-5-20251001","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":20000,"output":64000},"cost":{"input":0.9,"output":4.5},"sourceProvider":"jiekou"},"jiekou/claude-opus-4-1-20250805":{"id":"jiekou/claude-opus-4-1-20250805","name":"claude-opus-4-1-20250805","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":13.5,"output":67.5},"sourceProvider":"jiekou"},"jiekou/claude-opus-4-20250514":{"id":"jiekou/claude-opus-4-20250514","name":"claude-opus-4-20250514","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":13.5,"output":67.5},"sourceProvider":"jiekou"},"jiekou/claude-opus-4-5-20251101":{"id":"jiekou/claude-opus-4-5-20251101","name":"claude-opus-4-5-20251101","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":65536},"cost":{"input":4.5,"output":22.5},"sourceProvider":"jiekou"},"jiekou/claude-opus-4-6":{"id":"jiekou/claude-opus-4-6","name":"claude-opus-4-6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02","last_updated":"2026-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"jiekou"},"jiekou/claude-sonnet-4-20250514":{"id":"jiekou/claude-sonnet-4-20250514","name":"claude-sonnet-4-20250514","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":2.7,"output":13.5},"sourceProvider":"jiekou"},"jiekou/claude-sonnet-4-5-20250929":{"id":"jiekou/claude-sonnet-4-5-20250929","name":"claude-sonnet-4-5-20250929","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":2.7,"output":13.5},"sourceProvider":"jiekou"},"jiekou/deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.5},"sourceProvider":"jiekou"},"jiekou/deepseek/deepseek-v3-0324":{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.28,"output":1.14},"sourceProvider":"jiekou"},"jiekou/deepseek/deepseek-v3.1":{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":32767}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.27,"output":1},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-flash":{"id":"jiekou/gemini-2.5-flash","name":"gemini-2.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.27,"output":2.25},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-flash-lite":{"id":"jiekou/gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.09,"output":0.36},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-flash-lite-preview-06-17":{"id":"jiekou/gemini-2.5-flash-lite-preview-06-17","name":"gemini-2.5-flash-lite-preview-06-17","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","video","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.09,"output":0.36},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-flash-lite-preview-09-2025":{"id":"jiekou/gemini-2.5-flash-lite-preview-09-2025","name":"gemini-2.5-flash-lite-preview-09-2025","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.09,"output":0.36},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-flash-preview-05-20":{"id":"jiekou/gemini-2.5-flash-preview-05-20","name":"gemini-2.5-flash-preview-05-20","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":200000},"cost":{"input":0.135,"output":3.15},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-pro":{"id":"jiekou/gemini-2.5-pro","name":"gemini-2.5-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gemini-2.5-pro-preview-06-05":{"id":"jiekou/gemini-2.5-pro-preview-06-05","name":"gemini-2.5-pro-preview-06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":200000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gemini-3-flash-preview":{"id":"jiekou/gemini-3-flash-preview","name":"gemini-3-flash-preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"jiekou"},"jiekou/gemini-3-pro-preview":{"id":"jiekou/gemini-3-pro-preview","name":"gemini-3-pro-preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.8,"output":10.8},"sourceProvider":"jiekou"},"jiekou/gpt-5-chat-latest":{"id":"jiekou/gpt-5-chat-latest","name":"gpt-5-chat-latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gpt-5-codex":{"id":"jiekou/gpt-5-codex","name":"gpt-5-codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gpt-5-mini":{"id":"jiekou/gpt-5-mini","name":"gpt-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.225,"output":1.8},"sourceProvider":"jiekou"},"jiekou/gpt-5-nano":{"id":"jiekou/gpt-5-nano","name":"gpt-5-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.045,"output":0.36},"sourceProvider":"jiekou"},"jiekou/gpt-5-pro":{"id":"jiekou/gpt-5-pro","name":"gpt-5-pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":272000},"cost":{"input":13.5,"output":108},"sourceProvider":"jiekou"},"jiekou/gpt-5.1":{"id":"jiekou/gpt-5.1","name":"gpt-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02","last_updated":"2026-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gpt-5.1-codex":{"id":"jiekou/gpt-5.1-codex","name":"gpt-5.1-codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gpt-5.1-codex-max":{"id":"jiekou/gpt-5.1-codex-max","name":"gpt-5.1-codex-max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.125,"output":9},"sourceProvider":"jiekou"},"jiekou/gpt-5.1-codex-mini":{"id":"jiekou/gpt-5.1-codex-mini","name":"gpt-5.1-codex-mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.225,"output":1.8},"sourceProvider":"jiekou"},"jiekou/gpt-5.2":{"id":"jiekou/gpt-5.2","name":"gpt-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.575,"output":12.6},"sourceProvider":"jiekou"},"jiekou/gpt-5.2-codex":{"id":"jiekou/gpt-5.2-codex","name":"gpt-5.2-codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14},"sourceProvider":"jiekou"},"jiekou/gpt-5.2-pro":{"id":"jiekou/gpt-5.2-pro","name":"gpt-5.2-pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":18.9,"output":151.2},"sourceProvider":"jiekou"},"jiekou/grok-4-0709":{"id":"jiekou/grok-4-0709","name":"grok-4-0709","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":2.7,"output":13.5},"sourceProvider":"jiekou"},"jiekou/grok-4-1-fast-non-reasoning":{"id":"jiekou/grok-4-1-fast-non-reasoning","name":"grok-4-1-fast-non-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.18,"output":0.45},"sourceProvider":"jiekou"},"jiekou/grok-4-1-fast-reasoning":{"id":"jiekou/grok-4-1-fast-reasoning","name":"grok-4-1-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.18,"output":0.45},"sourceProvider":"jiekou"},"jiekou/grok-4-fast-non-reasoning":{"id":"jiekou/grok-4-fast-non-reasoning","name":"grok-4-fast-non-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.18,"output":0.45},"sourceProvider":"jiekou"},"jiekou/grok-4-fast-reasoning":{"id":"jiekou/grok-4-fast-reasoning","name":"grok-4-fast-reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.18,"output":0.45},"sourceProvider":"jiekou"},"jiekou/grok-code-fast-1":{"id":"jiekou/grok-code-fast-1","name":"grok-code-fast-1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.18,"output":1.35},"sourceProvider":"jiekou"},"jiekou/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"Minimax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":131071}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"jiekou"},"jiekou/minimaxai/minimax-m1-80k":{"id":"minimaxai/minimax-m1-80k","name":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":40000},"cost":{"input":0.55,"output":2.2},"sourceProvider":"jiekou"},"jiekou/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5},"sourceProvider":"jiekou"},"jiekou/moonshotai/kimi-k2-instruct":{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.57,"output":2.3},"sourceProvider":"jiekou"},"jiekou/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":262143}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3},"sourceProvider":"jiekou"},"jiekou/o3":{"id":"jiekou/o3","name":"o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":10,"output":40},"sourceProvider":"jiekou"},"jiekou/o3-mini":{"id":"jiekou/o3-mini","name":"o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":1.1,"output":4.4},"sourceProvider":"jiekou"},"jiekou/o4-mini":{"id":"jiekou/o4-mini","name":"o4-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-235b-a22b-fp8":{"id":"qwen/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.2,"output":0.8},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-235b-a22b-instruct-2507":{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.15,"output":0.8},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-235b-a22b-thinking-2507":{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22b Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":3},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-30b-a3b-fp8":{"id":"qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.09,"output":0.45},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-32b-fp8":{"id":"qwen/qwen3-32b-fp8","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.1,"output":0.45},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-coder-480b-a35b-instruct":{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":1.2},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"qwen/qwen3-coder-next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02","last_updated":"2026-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.15,"output":1.5},"sourceProvider":"jiekou"},"jiekou/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.15,"output":1.5},"sourceProvider":"jiekou"},"jiekou/xiaomimimo/mimo-v2-flash":{"id":"xiaomimimo/mimo-v2-flash","name":"XiaomiMiMo/MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"jiekou"},"jiekou/zai-org/glm-4.5":{"id":"zai-org/glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2},"sourceProvider":"jiekou"},"jiekou/zai-org/glm-4.5v":{"id":"zai-org/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8},"sourceProvider":"jiekou"},"jiekou/zai-org/glm-4.7":{"id":"zai-org/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2},"sourceProvider":"jiekou"},"jiekou/zai-org/glm-4.7-flash":{"id":"zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4},"sourceProvider":"jiekou"},"kenari/claude-fable-5":{"id":"kenari/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/claude-opus-4-7":{"id":"kenari/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/claude-opus-4-8":{"id":"kenari/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/claude-sonnet-5":{"id":"kenari/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/deepseek-v4-flash":{"id":"kenari/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/deepseek-v4-flash:free":{"id":"kenari/deepseek-v4-flash:free","name":"DeepSeek V4 Flash (Free)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/deepseek-v4-pro":{"id":"kenari/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gemini-2-5-flash":{"id":"kenari/gemini-2-5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gemini-2-5-flash-lite":{"id":"kenari/gemini-2-5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gemini-3-1-flash-lite":{"id":"kenari/gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gemma-4-31b-it":{"id":"kenari/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/glm-4-7-flash:free":{"id":"kenari/glm-4-7-flash:free","name":"GLM-4.7-Flash (Free)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/glm-5-1":{"id":"kenari/glm-5-1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/glm-5-2":{"id":"kenari/glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-5-4-mini":{"id":"kenari/gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-5-5":{"id":"kenari/gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-5-6-luna":{"id":"kenari/gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-5-6-sol":{"id":"kenari/gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-5-6-terra":{"id":"kenari/gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-image-2":{"id":"kenari/gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":272000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-oss-120b":{"id":"kenari/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/gpt-oss-20b":{"id":"kenari/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/grok-4-5":{"id":"kenari/grok-4-5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/grok-build-0-1":{"id":"kenari/grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/kimi-k2-6":{"id":"kenari/kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/kimi-k2-6:free":{"id":"kenari/kimi-k2-6:free","name":"Kimi K2.6 (Free)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/kimi-k2-7-code":{"id":"kenari/kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/kimi-k2-7-code:free":{"id":"kenari/kimi-k2-7-code:free","name":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/kimi-k3":{"id":"kenari/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/mimo-v2-5":{"id":"kenari/mimo-v2-5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/mimo-v2-5-pro":{"id":"kenari/mimo-v2-5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/mimo-v2-5:free":{"id":"kenari/mimo-v2-5:free","name":"MiMo-V2.5 (Free)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/minimax-m3":{"id":"kenari/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/nemotron-3-nano-30b-a3b":{"id":"kenari/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/nemotron-3-super-120b-a12b":{"id":"kenari/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/nemotron-3-super-120b-a12b:free":{"id":"kenari/nemotron-3-super-120b-a12b:free","name":"Nemotron 3 Super 120B A12B (Free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/nemotron-3-ultra-550b-a55b":{"id":"kenari/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kenari/qwen3-7-plus":{"id":"kenari/qwen3-7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"kenari"},"kilo/~anthropic/claude-fable-latest":{"id":"~anthropic/claude-fable-latest","name":"Anthropic: Claude Fable Latest ($$$$)","description":"This model always redirects to the latest model in the Claude Fable family.","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"kilo"},"kilo/~anthropic/claude-haiku-latest":{"id":"~anthropic/claude-haiku-latest","name":"Anthropic Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"kilo"},"kilo/~anthropic/claude-opus-latest":{"id":"~anthropic/claude-opus-latest","name":"Anthropic: Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/~anthropic/claude-sonnet-latest":{"id":"~anthropic/claude-sonnet-latest","name":"Anthropic Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/~deepseek/deepseek-v4-flash-latest":{"id":"~deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"This model always redirects to the latest model in the DeepSeek V4 Flash family.","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-01","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.04,"output":0.08,"cache_read":0.008},"sourceProvider":"kilo"},"kilo/~google/gemini-flash-latest":{"id":"~google/gemini-flash-latest","name":"Google Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"reasoning":1.875,"cache_read":0.0375,"cache_write":0.020833},"sourceProvider":"kilo"},"kilo/~google/gemini-pro-latest":{"id":"~google/gemini-pro-latest","name":"Google Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/~moonshotai/kimi-latest":{"id":"~moonshotai/kimi-latest","name":"MoonshotAI Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":974842,"output":974842},"cost":{"input":2.6,"output":13,"cache_read":0.29},"sourceProvider":"kilo"},"kilo/~openai/gpt-latest":{"id":"~openai/gpt-latest","name":"OpenAI GPT Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/~openai/gpt-mini-latest":{"id":"~openai/gpt-mini-latest","name":"OpenAI GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"kilo"},"kilo/~x-ai/grok-latest":{"id":"~x-ai/grok-latest","name":"xAI: Grok Latest","description":"This model always redirects to the latest Grok model from xAI.","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/~z-ai/glm-latest":{"id":"~z-ai/glm-latest","name":"Z.ai: GLM Latest","description":"This model always redirects to the latest GLM model from Z.ai.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"kilo"},"kilo/aion-labs/aion-2.0":{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.8,"output":1.6,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/aion-labs/aion-3.0":{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion-3.0","description":"Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute...","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"sourceProvider":"kilo"},"kilo/aion-labs/aion-3.0-mini":{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","description":"Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each...","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"sourceProvider":"kilo"},"kilo/aion-labs/aion-rp-llama-3.1-8b":{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-02-04","last_updated":"2025-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.8,"output":1.6},"sourceProvider":"kilo"},"kilo/allenai/olmo-3-32b-think":{"id":"allenai/olmo-3-32b-think","name":"AllenAI: Olmo 3 32B Think","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"allenai","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-11-21","last_updated":"2025-11-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.15,"output":0.5},"sourceProvider":"kilo"},"kilo/amazon/nova-2-lite-v1":{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.3,"output":2.5},"sourceProvider":"kilo"},"kilo/amazon/nova-lite-v1":{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.06,"output":0.24},"sourceProvider":"kilo"},"kilo/amazon/nova-micro-v1":{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":5120},"cost":{"input":0.035,"output":0.14},"sourceProvider":"kilo"},"kilo/amazon/nova-premier-v1":{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-31","last_updated":"2025-10-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":2.5,"output":12.5,"cache_read":0.625},"sourceProvider":"kilo"},"kilo/amazon/nova-pro-v1":{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.8,"output":3.2},"sourceProvider":"kilo"},"kilo/anthracite-org/magnum-v4-72b":{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":3,"output":5},"sourceProvider":"kilo"},"kilo/anthropic/claude-3-haiku":{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"kilo"},"kilo/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"kilo"},"kilo/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4 ($$$$)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.7-fast":{"id":"anthropic/claude-opus-4.7-fast","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-4.8-fast":{"id":"anthropic/claude-opus-4.8-fast","name":"Claude Opus 4.8","description":"Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis...","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/anthropic/claude-opus-5-fast":{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5","description":"Fast-mode variant of [Opus 5](/anthropic/claude-opus-5) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"kilo"},"kilo/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"kilo"},"kilo/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"kilo"},"kilo/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"kilo"},"kilo/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/arcee-ai/trinity-large-thinking":{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.22,"output":0.85,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/arcee-ai/virtuoso-large":{"id":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-05-05","last_updated":"2025-05-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":64000},"cost":{"input":0.75,"output":1.2},"sourceProvider":"kilo"},"kilo/baidu/ernie-4.5-vl-424b-a47b":{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-1.6":{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":2},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-1.6-flash":{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.3},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-2-1-turbo":{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed: Seed 2.1 Turbo","description":"Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and understanding visual and...","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.5},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-2.0-code":{"id":"bytedance-seed/seed-2.0-code","name":"Seed 2.0 Code","description":"Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tools such as Claude...","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-2.0-lite":{"id":"bytedance-seed/seed-2.0-lite","name":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.25,"output":2},"sourceProvider":"kilo"},"kilo/bytedance-seed/seed-2.0-mini":{"id":"bytedance-seed/seed-2.0-mini","name":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.1,"output":0.4},"sourceProvider":"kilo"},"kilo/bytedance/ui-tars-1.5-7b":{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":2048},"cost":{"input":0.1,"output":0.2,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/cognitivecomputations/dolphin-mistral-24b-venice-edition":{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","description":"Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.9},"sourceProvider":"kilo"},"kilo/cohere/command-a":{"id":"cohere/command-a","name":"Cohere: Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8192},"cost":{"input":2.5,"output":10},"sourceProvider":"kilo"},"kilo/cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"kilo"},"kilo/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"sourceProvider":"kilo"},"kilo/cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-r","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"kilo"},"kilo/cohere/north-mini-code:free":{"id":"cohere/north-mini-code:free","name":"Cohere: North Mini Code (free)","description":"North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...","family":"north","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.4,"output":1.3},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-chat-v3-0324":{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":0.27,"output":1.12,"cache_read":0.135},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-chat-v3.1":{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":161000,"output":161000},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.7,"output":2.5},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.5,"cache_read":0.35},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-r1-distill-llama-70b":{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.8,"output":0.8},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.269,"output":0.4,"cache_read":0.1345},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.41},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.44,"output":1.32,"cache_read":0.028},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":384000},"cost":{"input":1.6,"output":3.2,"cache_read":0.135},"sourceProvider":"kilo"},"kilo/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048575,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.132},"sourceProvider":"kilo"},"kilo/dots-studio/dots-3-note-preview:free":{"id":"dots-studio/dots-3-note-preview:free","name":"Dots Studio: Dots3-Note Preview (free)","description":"Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is...","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":512000},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"reasoning":0.4,"cache_read":0.01,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-pro-preview":{"id":"google/gemini-2.5-pro-preview","name":"Google: Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-2.5-pro-preview-05-06":{"id":"google/gemini-2.5-pro-preview-05-06","name":"Google: Gemini 2.5 Pro Preview 05-06","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Gemini 3.1 Flash Image, a.k.a. \"Nano Banana 2,\" is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines advanced...","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-flash-lite-image":{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual exploration. It delivers text-to-image generation...","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["image","text","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.25,"output":1.5},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessary edits and...","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667},"sourceProvider":"kilo"},"kilo/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performance and reliable multi-step...","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"reasoning":7.5,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"kilo"},"kilo/google/gemma-2-27b-it":{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-07-13","last_updated":"2024-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":2048},"cost":{"input":0.65,"output":0.65},"sourceProvider":"kilo"},"kilo/google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Google: Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.05,"output":0.15},"sourceProvider":"kilo"},"kilo/google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.08,"output":0.16},"sourceProvider":"kilo"},"kilo/google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Google: Gemma 3 4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.05,"output":0.1},"sourceProvider":"kilo"},"kilo/google/gemma-3n-e4b-it":{"id":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":6554},"cost":{"input":0.06,"output":0.12},"sourceProvider":"kilo"},"kilo/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.042,"output":0.22},"sourceProvider":"kilo"},"kilo/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.08,"output":0.35,"cache_read":0.01},"sourceProvider":"kilo"},"kilo/google/lyria-3-clip-preview":{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/google/lyria-3-pro-preview":{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/gryphe/mythomax-l2-13b":{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-07-02","last_updated":"2023-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"cost":{"input":0.06,"output":0.06},"sourceProvider":"kilo"},"kilo/ibm-granite/granite-4.0-h-micro":{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.017,"output":0.112},"sourceProvider":"kilo"},"kilo/ibm-granite/granite-4.1-8b":{"id":"ibm-granite/granite-4.1-8b","name":"IBM: Granite 4.1 8B","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1,"cache_read":0.05},"sourceProvider":"kilo"},"kilo/inception/mercury-2":{"id":"inception/mercury-2","name":"Inception: Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/inclusionai/ling-2.6-1t":{"id":"inclusionai/ling-2.6-1t","name":"inclusionAI: Ling-2.6-1T (retires Aug 24)","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/inclusionai/ling-2.6-flash":{"id":"inclusionai/ling-2.6-flash","name":"inclusionAI: Ling-2.6-flash (retires Aug 24)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"kilo"},"kilo/inclusionai/ling-3.0-flash":{"id":"inclusionai/ling-3.0-flash","name":"Ling-3.0-flash","description":"*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"sourceProvider":"kilo"},"kilo/inclusionai/ring-2.6-1t":{"id":"inclusionai/ring-2.6-1t","name":"inclusionAI: Ring-2.6-1T (retires Aug 24)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/kilo-auto/balanced":{"id":"kilo-auto/balanced","name":"Auto Balanced","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"reasoning":0,"cache_read":0.0325,"cache_write":0.40625},"sourceProvider":"kilo"},"kilo/kilo-auto/efficient":{"id":"kilo-auto/efficient","name":"Auto Efficient","description":"Routes each request to the cheapest model that gets the job done, based on continuously benchmarked accuracy and cost.","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"reasoning":0,"cache_read":0.0325,"cache_write":0.40625},"sourceProvider":"kilo"},"kilo/kilo-auto/free":{"id":"kilo-auto/free","name":"Auto Free","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0,"cache_write":0},"sourceProvider":"kilo"},"kilo/kilo-auto/frontier":{"id":"kilo-auto/frontier","name":"Auto Frontier","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"reasoning":0,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"kilo"},"kilo/kilo-auto/small":{"id":"kilo-auto/small","name":"Auto Small","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"1970-01-01","last_updated":"1970-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.4,"reasoning":0,"cache_read":0.005},"sourceProvider":"kilo"},"kilo/kwaipilot/kat-coder-air-v2.5":{"id":"kwaipilot/kat-coder-air-v2.5","name":"Kwaipilot: KAT-Coder-Air V2.5","description":"KAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/kwaipilot/kat-coder-pro-v2":{"id":"kwaipilot/kat-coder-pro-v2","name":"Kwaipilot: KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/kwaipilot/kat-coder-pro-v2.5":{"id":"kwaipilot/kat-coder-pro-v2.5","name":"Kwaipilot: KAT-Coder-Pro V2.5","description":"KAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to autonomously locate and make...","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.74,"output":2.96,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/liquid/lfm-2.5-2.6b:free":{"id":"liquid/lfm-2.5-2.6b:free","name":"LiquidAI: LFM2.5-2.6B (free)","description":"LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...","family":"liquid","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/mancer/weaver":{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","description":"An attempt to recreate Claude-style verbosity, but don't expect the same level of coherence or memory. Meant for use in roleplay/narrative situations.","family":"alpha","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2023-08-02","last_updated":"2023-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":6000},"cost":{"input":0.5,"output":0.75},"sourceProvider":"kilo"},"kilo/meituan/longcat-2.0":{"id":"meituan/longcat-2.0","name":"Meituan: LongCat 2.0","description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-20","last_updated":"2026-07-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"output":262144},"cost":{"input":0.75,"output":3,"cache_read":0.015},"sourceProvider":"kilo"},"kilo/meituan/longcat-2.0-free":{"id":"meituan/longcat-2.0-free","name":"Meituan: LongCat 2.0 (free)","description":"LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic workflows. Available free in Kilo for a limited time.","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"output":131072},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0},"sourceProvider":"kilo"},"kilo/meta-llama/llama-3.1-70b-instruct":{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.4,"output":0.4},"sourceProvider":"kilo"},"kilo/meta-llama/llama-3.1-8b-instruct":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.02,"output":0.04},"sourceProvider":"kilo"},"kilo/meta-llama/llama-3.2-1b-instruct":{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":60000,"output":60000},"cost":{"input":0.027,"output":0.201},"sourceProvider":"kilo"},"kilo/meta-llama/llama-3.2-3b-instruct":{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.33},"sourceProvider":"kilo"},"kilo/meta-llama/llama-3.3-70b-instruct":{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.32},"sourceProvider":"kilo"},"kilo/meta-llama/llama-4-maverick":{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":16384},"cost":{"input":0.2,"output":0.696},"sourceProvider":"kilo"},"kilo/meta-llama/llama-4-scout":{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":327680,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"kilo"},"kilo/meta-llama/llama-guard-4-12b":{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-04-30","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":16384},"cost":{"input":0.18,"output":0.18},"sourceProvider":"kilo"},"kilo/meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":1.1,"cache_read":0.04},"sourceProvider":"kilo"},"kilo/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context...","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Meta: Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark...","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"kilo"},"kilo/microsoft/phi-4":{"id":"microsoft/phi-4","name":"Microsoft: Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-01-10","last_updated":"2025-01-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.07,"output":0.14},"sourceProvider":"kilo"},"kilo/microsoft/wizardlm-2-8x22b":{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-16","last_updated":"2024-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65535,"output":8000},"cost":{"input":0.62,"output":0.62},"sourceProvider":"kilo"},"kilo/minimax/minimax-01":{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000192,"output":1000192},"cost":{"input":0.2,"output":1.1},"sourceProvider":"kilo"},"kilo/minimax/minimax-m1":{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":40000},"cost":{"input":0.4,"output":2.2},"sourceProvider":"kilo"},"kilo/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"kilo"},"kilo/minimax/minimax-m2-her":{"id":"minimax/minimax-m2-her","name":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":2048},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/mistralai/codestral-2508":{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-01","last_updated":"2025-08-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":51200},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/mistralai/ministral-14b-2512":{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":52429},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"sourceProvider":"kilo"},"kilo/mistralai/ministral-3b-2512":{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.01},"sourceProvider":"kilo"},"kilo/mistralai/ministral-8b":{"id":"mistralai/ministral-8b","name":"Mistral: Ministral 8B","description":"Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length...","family":"ministral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-10-17","last_updated":"2024-10-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.11,"output":0.11},"sourceProvider":"kilo"},"kilo/mistralai/ministral-8b-2512":{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"sourceProvider":"kilo"},"kilo/mistralai/mistral-large":{"id":"mistralai/mistral-large","name":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-02-26","last_updated":"2024-02-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":25600},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/mistralai/mistral-large-2407":{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-19","last_updated":"2024-11-19","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/mistralai/mistral-large-2512":{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":52429},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"sourceProvider":"kilo"},"kilo/mistralai/mistral-medium-3":{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":26215},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"kilo"},"kilo/mistralai/mistral-medium-3-5":{"id":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"kilo"},"kilo/mistralai/mistral-medium-3.1":{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":26215},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"kilo"},"kilo/mistralai/mistral-nemo":{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.019,"output":0.03},"sourceProvider":"kilo"},"kilo/mistralai/mistral-saba":{"id":"mistralai/mistral-saba","name":"Mistral: Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.6,"cache_read":0.02},"sourceProvider":"kilo"},"kilo/mistralai/mistral-small-24b-instruct-2501":{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral: Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.05,"output":0.08},"sourceProvider":"kilo"},"kilo/mistralai/mistral-small-2603":{"id":"mistralai/mistral-small-2603","name":"Mistral Small 4","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"kilo"},"kilo/mistralai/mistral-small-3.1-24b-instruct":{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"kilo"},"kilo/mistralai/mistral-small-3.2-24b-instruct":{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.2},"sourceProvider":"kilo"},"kilo/mistralai/mixtral-8x22b-instruct":{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":13108},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/mistralai/voxtral-small-24b-2507":{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-30","last_updated":"2025-10-30","modalities":{"input":["text","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":6400},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2":{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":100352},"cost":{"input":0.57,"output":2.3},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":100352},"cost":{"input":0.6,"output":2.5},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":100352},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3.4,"cache_read":0.16},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"kilo"},"kilo/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"kilo"},"kilo/morph/morph-v3-fast":{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":81920,"output":38000},"cost":{"input":0.8,"output":1.2},"sourceProvider":"kilo"},"kilo/morph/morph-v3-large":{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.9,"output":1.9},"sourceProvider":"kilo"},"kilo/nex-agi/nex-n2-mini":{"id":"nex-agi/nex-n2-mini","name":"Nex AGI: Nex-N2-Mini","description":"Nex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is built for coding, tool use,...","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-24","last_updated":"2026-06-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.025,"output":0.1,"cache_read":0.0025},"sourceProvider":"kilo"},"kilo/nex-agi/nex-n2-pro":{"id":"nex-agi/nex-n2-pro","name":"Nex AGI: Nex-N2-Pro","description":"Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-08","last_updated":"2026-06-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/nousresearch/hermes-3-llama-3.1-405b":{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Nous: Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-16","last_updated":"2024-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":1},"sourceProvider":"kilo"},"kilo/nousresearch/hermes-3-llama-3.1-70b":{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Nous: Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":0.7},"sourceProvider":"kilo"},"kilo/nousresearch/hermes-4-405b":{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nousresearch","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":26215},"cost":{"input":1,"output":3},"sourceProvider":"kilo"},"kilo/nousresearch/hermes-4-70b":{"id":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nousresearch","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.13,"output":0.4},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","name":"NVIDIA: Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.085,"output":0.4},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-super-120b-a12b:free":{"id":"nvidia/nemotron-3-super-120b-a12b:free","name":"NVIDIA: Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512288,"output":512288},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3-ultra-550b-a55b:free":{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","name":"NVIDIA: Nemotron 3 Ultra (free)","description":"NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3.5-content-safety:free":{"id":"nvidia/nemotron-3.5-content-safety:free","name":"NVIDIA: Nemotron 3.5 Content Safety (free)","description":"NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3.5-lightning":{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.08,"output":0.2,"cache_read":0.04},"sourceProvider":"kilo"},"kilo/nvidia/nemotron-3.5-lightning:free":{"id":"nvidia/nemotron-3.5-lightning:free","name":"NVIDIA: Nemotron 3.5 Lightning (free)","description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that... **Terms of service** For NVIDIA free endpoints (Super/Ultra/etc): Trial use only - do not submit personal or confidential data. Your use is logged for security purposes and to improve NVIDIA products and services. The logged session data for improvement purposes is not linked to your identity or any persistent identifier. For more information about our data processing practices, see our [Privacy Policy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/). By interacting with this endpoint, you consent to our collection, recording, and use of such information and the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf).","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"kilo"},"kilo/openai/gpt-3.5-turbo-0613":{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":4096},"cost":{"input":1,"output":2},"sourceProvider":"kilo"},"kilo/openai/gpt-3.5-turbo-16k":{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2023-08-28","last_updated":"2023-08-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":3,"output":4},"sourceProvider":"kilo"},"kilo/openai/gpt-3.5-turbo-instruct":{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-09-28","last_updated":"2023-09-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":4096},"cost":{"input":1.5,"output":2},"sourceProvider":"kilo"},"kilo/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":4096},"cost":{"input":30,"output":60},"sourceProvider":"kilo"},"kilo/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"kilo"},"kilo/openai/gpt-4-turbo-preview":{"id":"openai/gpt-4-turbo-preview","name":"OpenAI: GPT-4 Turbo Preview ($$$$)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"kilo"},"kilo/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"kilo"},"kilo/openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"sourceProvider":"kilo"},"kilo/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"kilo"},"kilo/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"kilo"},"kilo/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"kilo"},"kilo/openai/gpt-4o-mini-2024-07-18":{"id":"openai/gpt-4o-mini-2024-07-18","name":"OpenAI: GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"kilo"},"kilo/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"kilo"},"kilo/openai/gpt-5-image":{"id":"openai/gpt-5-image","name":"OpenAI: GPT-5 Image ($$$$)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":10,"output":10,"cache_read":1.25},"sourceProvider":"kilo"},"kilo/openai/gpt-5-image-mini":{"id":"openai/gpt-5-image-mini","name":"OpenAI: GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["pdf","image","text"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":2,"cache_read":0.25},"sourceProvider":"kilo"},"kilo/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"kilo"},"kilo/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":15,"output":120},"sourceProvider":"kilo"},"kilo/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"kilo"},"kilo/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"kilo"},"kilo/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"kilo"},"kilo/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"kilo"},"kilo/openai/gpt-5.2-chat":{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"kilo"},"kilo/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"kilo"},"kilo/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"kilo"},"kilo/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"kilo"},"kilo/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"kilo"},"kilo/openai/gpt-5.4-image-2":{"id":"openai/gpt-5.4-image-2","name":"OpenAI: GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":8,"output":15,"cache_read":2},"sourceProvider":"kilo"},"kilo/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"kilo"},"kilo/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"kilo"},"kilo/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"kilo"},"kilo/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-luna-pro":{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna","description":"GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks...","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-sol-discounted":{"id":"openai/gpt-5.6-sol-discounted","name":"OpenAI: GPT-5.6 Sol (50% off)","description":"GPT-5.6 Sol served by OpenAI through Vercel AI Gateway at 50% lower cost than other available inference providers. This promotion runs through September 18, 2026.","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15,"reasoning":0,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-sol-pro":{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol","description":"GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":5},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/openai/gpt-5.6-terra-pro":{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra","description":"GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/openai/gpt-audio":{"id":"openai/gpt-audio","name":"OpenAI: GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"sourceProvider":"kilo"},"kilo/openai/gpt-audio-mini":{"id":"openai/gpt-audio-mini","name":"OpenAI: GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio","pdf"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":2.4},"sourceProvider":"kilo"},"kilo/openai/gpt-chat-latest":{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-05-05","last_updated":"2026-05-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.17,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.03},"sourceProvider":"kilo"},"kilo/openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"kilo"},"kilo/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"kilo"},"kilo/openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":150,"output":600},"sourceProvider":"kilo"},"kilo/openai/o3":{"id":"openai/o3","name":"o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"kilo"},"kilo/openai/o3-mini-high":{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-02-12","last_updated":"2025-02-12","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"kilo"},"kilo/openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","pdf","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"kilo"},"kilo/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"kilo"},"kilo/openai/o4-mini-high":{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"kilo"},"kilo/openrouter/auto":{"id":"openrouter/auto","name":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["audio","image","pdf","text","video"],"output":["image","text"]},"open_weights":false,"limit":{"context":2000000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/openrouter/bodybuilder":{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"status":"beta","cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/openrouter/free":{"id":"openrouter/free","name":"OpenRouter Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/openrouter/pareto-code":{"id":"openrouter/pareto-code","name":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-05-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/perceptron/perceptron-mk1":{"id":"perceptron/perceptron-mk1","name":"Perceptron: Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.15,"output":1.5},"sourceProvider":"kilo"},"kilo/perplexity/sonar":{"id":"perplexity/sonar","name":"Perplexity: Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127072,"output":25415},"cost":{"input":1,"output":1},"sourceProvider":"kilo"},"kilo/perplexity/sonar-deep-research":{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":25600},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"kilo"},"kilo/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"sourceProvider":"kilo"},"kilo/perplexity/sonar-pro-search":{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-30","last_updated":"2025-10-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"sourceProvider":"kilo"},"kilo/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":25600},"cost":{"input":2,"output":8},"sourceProvider":"kilo"},"kilo/poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Poolside: Laguna S 2.1","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"sourceProvider":"kilo"},"kilo/poolside/laguna-s-2.1:free":{"id":"poolside/laguna-s-2.1:free","name":"Poolside: Laguna S 2.1 (free)","description":"Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...","family":"laguna-s","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Poolside: Laguna XS 2.1","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"sourceProvider":"kilo"},"kilo/poolside/laguna-xs-2.1:free":{"id":"poolside/laguna-xs-2.1:free","name":"Poolside: Laguna XS 2.1 (free)","description":"Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026). It combines...","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/qwen/qwen-2.5-72b-instruct":{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":16384},"cost":{"input":0.36,"output":0.4},"sourceProvider":"kilo"},"kilo/qwen/qwen-2.5-7b-instruct":{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.2},"sourceProvider":"kilo"},"kilo/qwen/qwen-2.5-coder-32b-instruct":{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-11","last_updated":"2024-11-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.66,"output":1},"sourceProvider":"kilo"},"kilo/qwen/qwen-plus":{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78,"cache_read":0.052,"cache_write":0.325},"sourceProvider":"kilo"},"kilo/qwen/qwen-plus-2025-07-28":{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78},"sourceProvider":"kilo"},"kilo/qwen/qwen-plus-2025-07-28:thinking":{"id":"qwen/qwen-plus-2025-07-28:thinking","name":"Qwen: Qwen Plus 0728 (thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78},"sourceProvider":"kilo"},"kilo/qwen/qwen2.5-vl-72b-instruct":{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-02-01","last_updated":"2025-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.8,"output":1,"cache_read":0.4},"sourceProvider":"kilo"},"kilo/qwen/qwen3-14b":{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.2275,"output":0.91},"sourceProvider":"kilo"},"kilo/qwen/qwen3-235b-a22b":{"id":"qwen/qwen3-235b-a22b","name":"Qwen3 235B-A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.455,"output":1.82},"sourceProvider":"kilo"},"kilo/qwen/qwen3-235b-a22b-2507":{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.1495,"output":0.598},"sourceProvider":"kilo"},"kilo/qwen/qwen3-235b-a22b-thinking-2507":{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":262144},"cost":{"input":0.23,"output":2.3},"sourceProvider":"kilo"},"kilo/qwen/qwen3-30b-a3b":{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.13,"output":0.52},"sourceProvider":"kilo"},"kilo/qwen/qwen3-30b-a3b-instruct-2507":{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":0.13,"output":0.52},"sourceProvider":"kilo"},"kilo/qwen/qwen3-30b-a3b-thinking-2507":{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":81920,"output":32768},"cost":{"input":0.2,"output":2.4},"sourceProvider":"kilo"},"kilo/qwen/qwen3-32b":{"id":"qwen/qwen3-32b","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.08,"output":0.28},"sourceProvider":"kilo"},"kilo/qwen/qwen3-8b":{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.117,"output":0.455},"sourceProvider":"kilo"},"kilo/qwen/qwen3-coder":{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.975,"output":4.875},"sourceProvider":"kilo"},"kilo/qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2925,"output":1.4625},"sourceProvider":"kilo"},"kilo/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375},"sourceProvider":"kilo"},"kilo/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":1.5},"sourceProvider":"kilo"},"kilo/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.65,"output":3.25,"cache_read":0.13,"cache_write":0.8125},"sourceProvider":"kilo"},"kilo/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.78,"output":3.9,"cache_read":0.156,"cache_write":0.975},"sourceProvider":"kilo"},"kilo/qwen/qwen3-max-thinking":{"id":"qwen/qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-09","last_updated":"2026-02-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.78,"output":3.9},"sourceProvider":"kilo"},"kilo/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.0975,"output":0.78},"sourceProvider":"kilo"},"kilo/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.26,"output":1.04},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":4},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-30b-a3b-instruct":{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.13,"output":0.52},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-30b-a3b-thinking":{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":2.4},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-32b-instruct":{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-23","last_updated":"2025-10-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.104,"output":0.416},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-8b-instruct":{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.117,"output":0.455},"sourceProvider":"kilo"},"kilo/qwen/qwen3-vl-8b-thinking":{"id":"qwen/qwen3-vl-8b-thinking","name":"Qwen: Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.18,"output":2.1},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.26,"output":2.08},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.195,"output":1.56},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1625,"output":1.3},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.39,"output":2.34},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.15},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-flash-02-23":{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.065,"output":0.26},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-plus-02-15":{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.26,"output":1.56},"sourceProvider":"kilo"},"kilo/qwen/qwen3.5-plus-20260420":{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.8,"cache_write":0.375},"sourceProvider":"kilo"},"kilo/qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.45,"output":2.7},"sourceProvider":"kilo"},"kilo/qwen/qwen3.6-35b-a3b":{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":1,"cache_read":0.05},"sourceProvider":"kilo"},"kilo/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375},"sourceProvider":"kilo"},"kilo/qwen/qwen3.6-max-preview":{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.027,"output":6.162,"cache_write":1.28375},"sourceProvider":"kilo"},"kilo/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"cache_write":0.40625},"sourceProvider":"kilo"},"kilo/qwen/qwen3.7-flash":{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"sourceProvider":"kilo"},"kilo/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.25,"output":3.75,"cache_read":0.125,"cache_write":1.5625},"sourceProvider":"kilo"},"kilo/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.32,"output":1.28,"cache_read":0.032,"cache_write":0.4},"sourceProvider":"kilo"},"kilo/qwen/qwen3.8-2.4t-a95b":{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/qwen/qwen3.8-27b":{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625},"sourceProvider":"kilo"},"kilo/qwen/qwen3.8-max":{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"Qwen3.8 Max is the flagship model in Alibaba's Qwen3.8 series, the general-availability successor to the Qwen3.8 Max Preview. It is a multimodal reasoning model intended for complex reasoning, visual understanding,...","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"kilo"},"kilo/rekaai/reka-edge":{"id":"rekaai/reka-edge","name":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":16384},"cost":{"input":0.1,"output":0.1},"sourceProvider":"kilo"},"kilo/rekaai/reka-flash-3":{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"reka","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.1,"output":0.2},"sourceProvider":"kilo"},"kilo/relace/relace-apply-3":{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.85,"output":1.25},"sourceProvider":"kilo"},"kilo/relace/relace-search":{"id":"relace/relace-search","name":"Relace: Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":1,"output":3},"sourceProvider":"kilo"},"kilo/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/sakana/sakana-namazu":{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Japanese instruction following,...","family":"sakana-namazu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/sao10k/l3-lunaris-8b":{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-08-13","last_updated":"2024-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":16384},"cost":{"input":0.04,"output":0.05},"sourceProvider":"kilo"},"kilo/sao10k/l3.1-euryale-70b":{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-08-28","last_updated":"2024-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.85,"output":0.85},"sourceProvider":"kilo"},"kilo/sao10k/l3.3-euryale-70b":{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0.65,"output":0.75},"sourceProvider":"kilo"},"kilo/stealth/claude-opus-4.6":{"id":"stealth/claude-opus-4.6","name":"Stealth: Claude Opus 4.6 (20% off)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"sourceProvider":"kilo"},"kilo/stealth/claude-opus-4.7":{"id":"stealth/claude-opus-4.7","name":"Stealth: Claude Opus 4.7 (20% off)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"sourceProvider":"kilo"},"kilo/stealth/claude-opus-4.8":{"id":"stealth/claude-opus-4.8","name":"Stealth: Claude Opus 4.8 (20% off)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Claude Opus 4.8 is offered at 20% lower cost than standard Claude Opus 4.8 pricing and is not served by Anthropic or Kilo Code.","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4,"output":20,"reasoning":0,"cache_read":0.4,"cache_write":5},"sourceProvider":"kilo"},"kilo/stealth/claude-sonnet-4.6":{"id":"stealth/claude-sonnet-4.6","name":"Stealth: Claude Sonnet 4.6 (20% off)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.4,"output":12,"reasoning":0,"cache_read":0.24,"cache_write":3},"sourceProvider":"kilo"},"kilo/stealth/ox-alpha":{"id":"stealth/ox-alpha","name":"Ox Alpha","description":"Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...","family":"alpha","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/stealth/qwen3.6-plus":{"id":"stealth/qwen3.6-plus","name":"Stealth: Qwen3.6 Plus (50% off)","description":"Your prompts and completions may be retained and used to train or improve the provider's services. This third-party-served variant of Qwen3.6 Plus is offered at 50% lower cost than standard Qwen3.6 Plus pricing and is not served by Alibaba or Kilo Code. Note: a surcharge applies to long-context workloads exceeding 256K input tokens.","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":0,"cache_read":0.025,"cache_write":0.3125},"sourceProvider":"kilo"},"kilo/stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.3},"sourceProvider":"kilo"},"kilo/stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters...","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"kilo"},"kilo/stepfun/step-3.7-flash:free":{"id":"stepfun/step-3.7-flash:free","name":"StepFun: Step 3.7 Flash (free)","description":"Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video understanding, activating roughly 11B parameters per token. The model supports a 256K context window and exposes selectable reasoning levels (high/medium/low), letting callers trade off speed, cost, and depth of reasoning. Designed for coding, agentic workflows, structured outputs, and long-context productivity tasks.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0},"sourceProvider":"kilo"},"kilo/tencent/hunyuan-a13b-instruct":{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.14,"output":0.57},"sourceProvider":"kilo"},"kilo/tencent/hy-mt2-1.8b":{"id":"tencent/hy-mt2-1.8b","name":"Tencent: Hy-MT2-1.8B","description":"Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.044,"output":0.177},"sourceProvider":"kilo"},"kilo/tencent/hy-mt2-30b-a3b":{"id":"tencent/hy-mt2-30b-a3b","name":"Tencent: Hy-MT2-30B-A3B","description":"Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"sourceProvider":"kilo"},"kilo/tencent/hy-mt2-7b":{"id":"tencent/hy-mt2-7b","name":"Tencent: Hy-MT2-7B","description":"Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"sourceProvider":"kilo"},"kilo/tencent/hy3":{"id":"tencent/hy3","name":"Hy3","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"sourceProvider":"kilo"},"kilo/tencent/hy3-preview":{"id":"tencent/hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.18,"output":0.6,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/tencent/hy3:free":{"id":"tencent/hy3:free","name":"Tencent: Hy3 (free)","description":"Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent, activating 21B parameters per token. It supports configurable reasoning effort, agentic workflows, reliable tool calling, and long-context tasks across coding, document processing, financial analysis, and frontend development.","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0,"output":0,"reasoning":0,"cache_read":0},"sourceProvider":"kilo"},"kilo/thedrummer/cydonia-24b-v4.1":{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-09-27","last_updated":"2025-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"sourceProvider":"kilo"},"kilo/thedrummer/rocinante-12b":{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-30","last_updated":"2024-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.25,"output":0.5},"sourceProvider":"kilo"},"kilo/thedrummer/skyfall-36b-v2":{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.55,"output":0.8,"cache_read":0.25},"sourceProvider":"kilo"},"kilo/thedrummer/unslopnemo-12b":{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-08","last_updated":"2024-11-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.4,"output":0.4},"sourceProvider":"kilo"},"kilo/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":262144},"cost":{"input":0.95,"output":4.05,"cache_read":0.16},"sourceProvider":"kilo"},"kilo/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":262144},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/thinkingmachines/inkling-small:free":{"id":"thinkingmachines/inkling-small:free","name":"Thinking Machines: Inkling Small (free)","description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/thinkingmachines/inkling:free":{"id":"thinkingmachines/inkling:free","name":"Thinking Machines: Inkling (free)","description":"Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning, coding, agentic and tool-use systems,...","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"kilo"},"kilo/undi95/remm-slerp-l2-13b":{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2023-07-22","last_updated":"2023-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":6144,"output":6144},"cost":{"input":0.45,"output":0.65},"sourceProvider":"kilo"},"kilo/upstage/solar-pro-3":{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"kilo"},"kilo/upstage/solar-pro4":{"id":"upstage/solar-pro4","name":"Upstage: Solar Pro 4","description":"Solar Pro 4 is a large language model from Upstage. It is suited for agentic workflows, office productivity, document-intensive work, and coding.","family":"solar","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"kilo"},"kilo/writer/palmyra-x5":{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","family":"palmyra","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-21","last_updated":"2026-01-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"output":8192},"cost":{"input":0.6,"output":6},"sourceProvider":"kilo"},"kilo/x-ai/grok-4.20":{"id":"x-ai/grok-4.20","name":"SpaceXAI: Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/x-ai/grok-4.20-multi-agent":{"id":"x-ai/grok-4.20-multi-agent","name":"SpaceXAI: Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":4096},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"kilo"},"kilo/x-ai/grok-4.6":{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"Grok 4.6 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"kilo"},"kilo/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"kilo"},"kilo/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.003,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"kilo"},"kilo/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.004,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.5":{"id":"z-ai/glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.5-air":{"id":"z-ai/glm-4.5-air","name":"GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.5v":{"id":"z-ai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.1},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.6v":{"id":"z-ai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.4,"output":1.75,"cache_read":0.08},"sourceProvider":"kilo"},"kilo/z-ai/glm-4.7-flash":{"id":"z-ai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"kilo"},"kilo/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":128000},"cost":{"input":0.6,"output":1.92,"cache_read":0.12},"sourceProvider":"kilo"},"kilo/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"kilo"},"kilo/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"kilo"},"kilo/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"kilo"},"kilo/z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"kilo"},"kilo/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"kilo"},"kimi-for-coding/k3":{"id":"kimi-for-coding/k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"kimi-for-coding"},"kimi-for-coding/k3-256k":{"id":"kimi-for-coding/k3-256k","name":"Kimi K3-256K","description":"256K-context version of Kimi K3, reducing token consumption for shorter coding sessions","family":"kimi-k3","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"kimi-for-coding"},"kimi-for-coding/kimi-for-coding":{"id":"kimi-for-coding/kimi-for-coding","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"kimi-for-coding"},"kimi-for-coding/kimi-for-coding-highspeed":{"id":"kimi-for-coding/kimi-for-coding-highspeed","name":"Kimi For Coding HighSpeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"kimi-for-coding"},"kosmik/qwen/qwen3.8-27b":{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.35,"output":2.2,"cache_read":0.09},"sourceProvider":"kosmik"},"kuae-cloud-coding-plan/GLM-4.7":{"id":"kuae-cloud-coding-plan/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"kuae-cloud-coding-plan"},"lilac/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":262100},"cost":{"input":0.11,"output":0.35},"sourceProvider":"lilac"},"lilac/minimaxai/minimax-m3":{"id":"minimaxai/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax-m3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.28,"output":1.1,"cache_read":0.05},"sourceProvider":"lilac"},"lilac/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.7,"output":3.5,"cache_read":0.2},"sourceProvider":"lilac"},"lilac/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":524288},"cost":{"input":0.9,"output":3,"cache_read":0.27},"sourceProvider":"lilac"},"llama/cerebras-llama-4-maverick-17b-128e-instruct":{"id":"llama/cerebras-llama-4-maverick-17b-128e-instruct","name":"Cerebras-Llama-4-Maverick-17B-128E-Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/cerebras-llama-4-scout-17b-16e-instruct":{"id":"llama/cerebras-llama-4-scout-17b-16e-instruct","name":"Cerebras-Llama-4-Scout-17B-16E-Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/groq-llama-4-maverick-17b-128e-instruct":{"id":"llama/groq-llama-4-maverick-17b-128e-instruct","name":"Groq-Llama-4-Maverick-17B-128E-Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/llama-3.3-70b-instruct":{"id":"llama/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/llama-3.3-8b-instruct":{"id":"llama/llama-3.3-8b-instruct","name":"Llama-3.3-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/llama-4-maverick-17b-128e-instruct-fp8":{"id":"llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llama/llama-4-scout-17b-16e-instruct-fp8":{"id":"llama/llama-4-scout-17b-16e-instruct-fp8","name":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"llama"},"llmgateway-providers/alibaba/deepseek-v4-flash":{"id":"alibaba/deepseek-v4-flash","name":"DeepSeek V4 Flash (Alibaba Cloud)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/deepseek-v4-pro":{"id":"alibaba/deepseek-v4-pro","name":"DeepSeek V4 Pro (Alibaba Cloud)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":2.4,"output":4.8,"cache_read":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/glm-5":{"id":"alibaba/glm-5","name":"GLM-5 (Alibaba Cloud)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.573,"output":2.58},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/glm-5.2":{"id":"alibaba/glm-5.2","name":"GLM-5.2 (Alibaba Cloud)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.28},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/kimi-k2.5":{"id":"alibaba/kimi-k2.5","name":"Kimi K2.5 (Alibaba Cloud)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.574,"output":3.011},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-coder-plus":{"id":"alibaba/qwen-coder-plus","name":"Qwen Coder Plus (Alibaba Cloud)","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.502,"output":1.004},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-flash":{"id":"alibaba/qwen-flash","name":"Qwen Flash (Alibaba Cloud)","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-max":{"id":"alibaba/qwen-max","name":"Qwen Max (Alibaba Cloud)","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-omni-turbo":{"id":"alibaba/qwen-omni-turbo","name":"Qwen Omni Turbo (Alibaba Cloud)","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.2,"output":0.8},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-plus":{"id":"alibaba/qwen-plus","name":"Qwen Plus (Alibaba Cloud)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32000},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen-plus-latest":{"id":"alibaba/qwen-plus-latest","name":"Qwen Plus Latest (Alibaba Cloud)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-09-09","last_updated":"2024-09-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3-coder-flash":{"id":"alibaba/qwen3-coder-flash","name":"Qwen3 Coder Flash (Alibaba Cloud)","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3-coder-plus":{"id":"alibaba/qwen3-coder-plus","name":"Qwen3 Coder Plus (Alibaba Cloud)","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":66000},"cost":{"input":6,"output":60,"cache_read":1.2,"cache_write":7.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3-max":{"id":"alibaba/qwen3-max","name":"Qwen3 Max (Alibaba Cloud)","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32800},"cost":{"input":3,"output":15,"cache_read":0.6,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3-vl-flash":{"id":"alibaba/qwen3-vl-flash","name":"Qwen3 VL Flash (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3-vl-plus":{"id":"alibaba/qwen3-vl-plus","name":"Qwen3 VL Plus (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"cache_read":0.04,"cache_write":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.6-35b-a3b":{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B (Alibaba Cloud)","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.6-flash":{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.6-max-preview":{"id":"alibaba/qwen3.6-max-preview","name":"Qwen3.6 Max Preview (Alibaba Cloud)","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.3,"output":7.8,"cache_read":0.13},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.6-plus":{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus (Alibaba Cloud)","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.7-flash":{"id":"alibaba/qwen3.7-flash","name":"Qwen3.7 Flash (Alibaba Cloud)","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.7-max":{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max (Alibaba Cloud)","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.7-plus":{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus (Alibaba Cloud)","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen3.8-max":{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max (Alibaba Cloud)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/alibaba/qwen35-397b-a17b":{"id":"alibaba/qwen35-397b-a17b","name":"Qwen3.5 397B A17B (Alibaba Cloud)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5 (Anthropic)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (Anthropic)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-haiku-4-5-20251001":{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (2025-10-01) (Anthropic)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-opus-4-5-20251101":{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (Anthropic)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6 (Anthropic)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7 (Anthropic)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8 (Anthropic)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5 (Anthropic)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (Anthropic)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-sonnet-4-5-20250929":{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (2025-09-29) (Anthropic)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Anthropic)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5 (Anthropic)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-fable-5":{"id":"aws-bedrock/claude-fable-5","name":"Claude Fable 5 (AWS Bedrock)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-haiku-4-5":{"id":"aws-bedrock/claude-haiku-4-5","name":"Claude Haiku 4.5 (AWS Bedrock)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-haiku-4-5-20251001":{"id":"aws-bedrock/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (2025-10-01) (AWS Bedrock)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-4-1-20250805":{"id":"aws-bedrock/claude-opus-4-1-20250805","name":"Claude Opus 4.1 (AWS Bedrock)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-4-5-20251101":{"id":"aws-bedrock/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (AWS Bedrock)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-4-6":{"id":"aws-bedrock/claude-opus-4-6","name":"Claude Opus 4.6 (AWS Bedrock)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-4-7":{"id":"aws-bedrock/claude-opus-4-7","name":"Claude Opus 4.7 (AWS Bedrock)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-4-8":{"id":"aws-bedrock/claude-opus-4-8","name":"Claude Opus 4.8 (AWS Bedrock)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-opus-5":{"id":"aws-bedrock/claude-opus-5","name":"Claude Opus 5 (AWS Bedrock)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-sonnet-4-5":{"id":"aws-bedrock/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (AWS Bedrock)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-sonnet-4-5-20250929":{"id":"aws-bedrock/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (2025-09-29) (AWS Bedrock)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-sonnet-4-6":{"id":"aws-bedrock/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (AWS Bedrock)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/claude-sonnet-5":{"id":"aws-bedrock/claude-sonnet-5","name":"Claude Sonnet 5 (AWS Bedrock)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/grok-4-3":{"id":"aws-bedrock/grok-4-3","name":"Grok 4.3 (AWS Bedrock)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/grok-4-6":{"id":"aws-bedrock/grok-4-6","name":"Grok 4.6 (AWS Bedrock)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/llama-3.1-70b-instruct":{"id":"aws-bedrock/llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct (AWS Bedrock)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":2048},"cost":{"input":0.72,"output":0.72},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/llama-4-maverick-17b-instruct":{"id":"aws-bedrock/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct (AWS Bedrock)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.24,"output":0.97},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-bedrock/llama-4-scout-17b-instruct":{"id":"aws-bedrock/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct (AWS Bedrock)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.17,"output":0.66},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-mantle/gpt-5.6-luna":{"id":"aws-mantle/gpt-5.6-luna","name":"GPT-5.6 Luna (AWS Mantle)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":278528,"output":128000},"cost":{"input":0.22,"output":1.32,"cache_read":0.022,"cache_write":0.275},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-mantle/gpt-5.6-sol":{"id":"aws-mantle/gpt-5.6-sol","name":"GPT-5.6 Sol (AWS Mantle)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":278528,"output":128000},"cost":{"input":5.5,"output":33,"cache_read":0.55,"cache_write":6.875},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/aws-mantle/gpt-5.6-terra":{"id":"aws-mantle/gpt-5.6-terra","name":"GPT-5.6 Terra (AWS Mantle)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":278528,"output":128000},"cost":{"input":2.2,"output":13.2,"cache_read":0.22,"cache_write":2.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure-ai-foundry/grok-4-1-fast-non-reasoning":{"id":"azure-ai-foundry/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure-ai-foundry/grok-4-1-fast-reasoning":{"id":"azure-ai-foundry/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast Reasoning (Azure AI Foundry)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure-ai-foundry/grok-4-3":{"id":"azure-ai-foundry/grok-4-3","name":"Grok 4.3 (Azure AI Foundry)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":20000,"output":8192},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-3.5-turbo":{"id":"azure/gpt-3.5-turbo","name":"GPT-3.5 Turbo (Azure)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4":{"id":"azure/gpt-4","name":"GPT-4 (Azure)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4-turbo":{"id":"azure/gpt-4-turbo","name":"GPT-4 Turbo (Azure)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4.1":{"id":"azure/gpt-4.1","name":"GPT-4.1 (Azure)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4.1-mini":{"id":"azure/gpt-4.1-mini","name":"GPT-4.1 Mini (Azure)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4.1-nano":{"id":"azure/gpt-4.1-nano","name":"GPT-4.1 Nano (Azure)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-4o":{"id":"azure/gpt-4o","name":"GPT-4o (Azure)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5":{"id":"azure/gpt-5","name":"GPT-5 (Azure)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5-mini":{"id":"azure/gpt-5-mini","name":"GPT-5 Mini (Azure)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5-nano":{"id":"azure/gpt-5-nano","name":"GPT-5 Nano (Azure)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.1":{"id":"azure/gpt-5.1","name":"GPT-5.1 (Azure)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.1-codex":{"id":"azure/gpt-5.1-codex","name":"GPT-5.1 Codex (Azure)","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":1.25,"output":10},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.1-codex-mini":{"id":"azure/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.2":{"id":"azure/gpt-5.2","name":"GPT-5.2 (Azure)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.2-codex":{"id":"azure/gpt-5.2-codex","name":"GPT-5.2 Codex (Azure)","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.2-pro":{"id":"azure/gpt-5.2-pro","name":"GPT-5.2 Pro (Azure)","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":21,"output":168},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.3-codex":{"id":"azure/gpt-5.3-codex","name":"GPT-5.3 Codex (Azure)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.4":{"id":"azure/gpt-5.4","name":"GPT-5.4 (Azure)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.4-mini":{"id":"azure/gpt-5.4-mini","name":"GPT-5.4 Mini (Azure)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.4-nano":{"id":"azure/gpt-5.4-nano","name":"GPT-5.4 Nano (Azure)","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.4-pro":{"id":"azure/gpt-5.4-pro","name":"GPT-5.4 Pro (Azure)","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.5":{"id":"azure/gpt-5.5","name":"GPT-5.5 (Azure)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.6-luna":{"id":"azure/gpt-5.6-luna","name":"GPT-5.6 Luna (Azure)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.6-sol":{"id":"azure/gpt-5.6-sol","name":"GPT-5.6 Sol (Azure)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-5.6-terra":{"id":"azure/gpt-5.6-terra","name":"GPT-5.6 Terra (Azure)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/gpt-oss-120b":{"id":"azure/gpt-oss-120b","name":"GPT OSS 120B (Azure)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/o1":{"id":"azure/o1","name":"o1 (Azure)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/o3":{"id":"azure/o3","name":"o3 (Azure)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/o3-mini":{"id":"azure/o3-mini","name":"o3 Mini (Azure)","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/azure/o4-mini":{"id":"azure/o4-mini","name":"o4 Mini (Azure)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/deepseek-v4-flash":{"id":"baidu/deepseek-v4-flash","name":"DeepSeek V4 Flash (Baidu)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/deepseek-v4-pro":{"id":"baidu/deepseek-v4-pro","name":"DeepSeek V4 Pro (Baidu)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.69,"output":3.38,"cache_read":0.14},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/glm-5":{"id":"baidu/glm-5","name":"GLM-5 (Baidu)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/glm-5.1":{"id":"baidu/glm-5.1","name":"GLM-5.1 (Baidu)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/glm-5.2":{"id":"baidu/glm-5.2","name":"GLM-5.2 (Baidu)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/baidu/kimi-k2.6":{"id":"baidu/kimi-k2.6","name":"Kimi K2.6 (Baidu)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/deepseek-v3.2":{"id":"bytedance/deepseek-v3.2","name":"DeepSeek V3.2 (ByteDance)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.28,"output":0.42,"cache_read":0.056},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/deepseek-v4-flash":{"id":"bytedance/deepseek-v4-flash","name":"DeepSeek V4 Flash (ByteDance)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/deepseek-v4-pro":{"id":"bytedance/deepseek-v4-pro","name":"DeepSeek V4 Pro (ByteDance)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/glm-4.7":{"id":"bytedance/glm-4.7","name":"GLM-4.7 (ByteDance)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/glm-5.2":{"id":"bytedance/glm-5.2","name":"GLM-5.2 (ByteDance)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/gpt-oss-120b":{"id":"bytedance/gpt-oss-120b","name":"GPT OSS 120B (ByteDance)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.1,"output":0.5,"cache_read":0.02},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/seed-1-6-250615":{"id":"bytedance/seed-1-6-250615","name":"Seed 1.6 (250615) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/seed-1-6-250915":{"id":"bytedance/seed-1-6-250915","name":"Seed 1.6 (250915) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/seed-1-6-flash-250715":{"id":"bytedance/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.07,"output":0.3,"cache_read":0.015},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/bytedance/seed-1-8-251228":{"id":"bytedance/seed-1-8-251228","name":"Seed 1.8 (251228) (ByteDance)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/canopywave/deepseek-v4-flash":{"id":"canopywave/deepseek-v4-flash","name":"DeepSeek V4 Flash (CanopyWave)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/canopywave/deepseek-v4-pro":{"id":"canopywave/deepseek-v4-pro","name":"DeepSeek V4 Pro (CanopyWave)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.74,"output":3.48,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/canopywave/glm-5.2":{"id":"canopywave/glm-5.2","name":"GLM-5.2 (CanopyWave)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/canopywave/kimi-k2.6":{"id":"canopywave/kimi-k2.6","name":"Kimi K2.6 (CanopyWave)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/canopywave/kimi-k3":{"id":"canopywave/kimi-k3","name":"Kimi K3 (CanopyWave)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/cerebras/gemma-4-31b-it":{"id":"cerebras/gemma-4-31b-it","name":"Gemma 4 31B IT (Cerebras)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.99,"output":1.49},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/cerebras/glm-4.7":{"id":"cerebras/glm-4.7","name":"GLM-4.7 (Cerebras)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":2.25,"output":2.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/cerebras/gpt-oss-120b":{"id":"cerebras/gpt-oss-120b","name":"GPT OSS 120B (Cerebras)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.35,"output":0.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/cerebras/llama-3.3-70b-instruct":{"id":"cerebras/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (Cerebras)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.85,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/cerebras/qwen3-235b-a22b-instruct-2507":{"id":"cerebras/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (Cerebras)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.6,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/deepseek-v3.2":{"id":"deepinfra/deepseek-v3.2","name":"DeepSeek V3.2 (DeepInfra)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":65536},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/deepseek-v4-flash":{"id":"deepinfra/deepseek-v4-flash","name":"DeepSeek V4 Flash (DeepInfra)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.08,"output":0.18,"cache_read":0.016},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/deepseek-v4-pro":{"id":"deepinfra/deepseek-v4-pro","name":"DeepSeek V4 Pro (DeepInfra)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"cost":{"input":1.3,"output":2.6,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/gemma-4-26b-a4b-it":{"id":"deepinfra/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT (DeepInfra)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/gemma-4-31b-it":{"id":"deepinfra/gemma-4-31b-it","name":"Gemma 4 31B IT (DeepInfra)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/glm-5.1":{"id":"deepinfra/glm-5.1","name":"GLM-5.1 (DeepInfra)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":65536},"cost":{"input":1.05,"output":3.5,"cache_read":0.205},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/hy3":{"id":"deepinfra/hy3","name":"Hy3 (DeepInfra)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/kimi-k2.5":{"id":"deepinfra/kimi-k2.5","name":"Kimi K2.5 (DeepInfra)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/ling-3.0-flash":{"id":"deepinfra/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (DeepInfra)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/mimo-v2.5":{"id":"deepinfra/mimo-v2.5","name":"MiMo V2.5 (DeepInfra)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.4,"output":2,"cache_read":0.08,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/mimo-v2.5-pro":{"id":"deepinfra/mimo-v2.5-pro","name":"MiMo V2.5 Pro (DeepInfra)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":1,"output":3,"cache_read":0.2,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/nemotron-3-ultra-550b":{"id":"deepinfra/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B (DeepInfra)","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/qwen3-vl-235b-a22b-instruct":{"id":"deepinfra/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct (DeepInfra)","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/qwen3-vl-30b-a3b-instruct":{"id":"deepinfra/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (DeepInfra)","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepinfra/qwen3.5-9b":{"id":"deepinfra/qwen3.5-9b","name":"Qwen3.5 9B (DeepInfra)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash (DeepSeek)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro (DeepSeek)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-4.5":{"id":"embercloud/glm-4.5","name":"GLM-4.5 (EmberCloud)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-4.5-air":{"id":"embercloud/glm-4.5-air","name":"GLM-4.5 Air (EmberCloud)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":96000},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-4.7":{"id":"embercloud/glm-4.7","name":"GLM-4.7 (EmberCloud)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.38,"output":1.98,"cache_read":0.19},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-4.7-flash":{"id":"embercloud/glm-4.7-flash","name":"GLM-4.7 Flash (EmberCloud)","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-5":{"id":"embercloud/glm-5","name":"GLM-5 (EmberCloud)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":0.72,"output":2.3,"cache_read":0.144},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-5.1":{"id":"embercloud/glm-5.1","name":"GLM-5.1 (EmberCloud)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":0.931,"output":2.93,"cache_read":0.173},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/glm-5.2":{"id":"embercloud/glm-5.2","name":"GLM-5.2 (EmberCloud)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131000},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/kimi-k2.5":{"id":"embercloud/kimi-k2.5","name":"Kimi K2.5 (EmberCloud)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.405,"output":1.98,"cache_read":0.225},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/embercloud/qwen3-coder-next":{"id":"embercloud/qwen3-coder-next","name":"Qwen3 Coder Next (EmberCloud)","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.108,"output":0.675,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/fireworks/deepseek-v4-flash":{"id":"fireworks/deepseek-v4-flash","name":"DeepSeek V4 Flash (Fireworks AI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/fireworks/deepseek-v4-pro":{"id":"fireworks/deepseek-v4-pro","name":"DeepSeek V4 Pro (Fireworks AI)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/fireworks/kimi-k3":{"id":"fireworks/kimi-k3","name":"Kimi K3 (Fireworks AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":1040384},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/fireworks/kimi-k3-fast":{"id":"fireworks/kimi-k3-fast","name":"Kimi K3 Fast (Fireworks AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":1040384},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/gonka24/deepseek-v4-flash":{"id":"gonka24/deepseek-v4-flash","name":"DeepSeek V4 Flash (Gonka24)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":390000,"output":16384},"cost":{"input":0.075,"output":0.175,"cache_read":0.0155},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/gonka24/kimi-k2.6":{"id":"gonka24/kimi-k2.6","name":"Kimi K2.6 (Gonka24)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":98304},"cost":{"input":0.22,"output":1.137,"cache_read":0.048},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/gonka24/minimax-m2.7":{"id":"gonka24/minimax-m2.7","name":"MiniMax M2.7 (Gonka24)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.08,"output":0.32,"cache_read":0.017},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-2.5-flash":{"id":"google-ai-studio/gemini-2.5-flash","name":"Gemini 2.5 Flash (Google AI Studio)","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":24576},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-2.5-flash-lite":{"id":"google-ai-studio/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite (Google AI Studio)","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-2.5-pro":{"id":"google-ai-studio/gemini-2.5-pro","name":"Gemini 2.5 Pro (Google AI Studio)","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3-flash-preview":{"id":"google-ai-studio/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview) (Google AI Studio)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.1-flash-lite":{"id":"google-ai-studio/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite (Google AI Studio)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.1-pro-preview":{"id":"google-ai-studio/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Google AI Studio)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.5-flash":{"id":"google-ai-studio/gemini-3.5-flash","name":"Gemini 3.5 Flash (Google AI Studio)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.5-flash-lite":{"id":"google-ai-studio/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite (Google AI Studio)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.6-flash":{"id":"google-ai-studio/gemini-3.6-flash","name":"Gemini 3.6 Flash (Google AI Studio)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-3.7-flash":{"id":"google-ai-studio/gemini-3.7-flash","name":"Gemini 3.7 Flash (Google AI Studio)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-ai-studio/gemini-pro-latest":{"id":"google-ai-studio/gemini-pro-latest","name":"Gemini Pro Latest (Google AI Studio)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-2.5-flash":{"id":"google-vertex/gemini-2.5-flash","name":"Gemini 2.5 Flash (Google Vertex AI)","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":24576},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-2.5-flash-lite":{"id":"google-vertex/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite (Google Vertex AI)","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-2.5-pro":{"id":"google-vertex/gemini-2.5-pro","name":"Gemini 2.5 Pro (Google Vertex AI)","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3-flash-preview":{"id":"google-vertex/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview) (Google Vertex AI)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.1-flash-lite":{"id":"google-vertex/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite (Google Vertex AI)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.1-pro-preview":{"id":"google-vertex/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Google Vertex AI)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.5-flash":{"id":"google-vertex/gemini-3.5-flash","name":"Gemini 3.5 Flash (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.5-flash-lite":{"id":"google-vertex/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.6-flash":{"id":"google-vertex/gemini-3.6-flash","name":"Gemini 3.6 Flash (Google Vertex AI)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/google-vertex/gemini-3.7-flash":{"id":"google-vertex/gemini-3.7-flash","name":"Gemini 3.7 Flash (Google Vertex AI)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/groq/gpt-oss-120b":{"id":"groq/gpt-oss-120b","name":"GPT OSS 120B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32766},"cost":{"input":0.15,"output":0.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/groq/gpt-oss-20b":{"id":"groq/gpt-oss-20b","name":"GPT OSS 20B (Groq)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32766},"cost":{"input":0.1,"output":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/iceberg/gemini-3-flash-preview":{"id":"iceberg/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview) (Iceberg)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/iceberg/gemini-3.1-pro-preview":{"id":"iceberg/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Iceberg)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/iceberg/gemini-3.6-flash":{"id":"iceberg/gemini-3.6-flash","name":"Gemini 3.6 Flash (Iceberg)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/inference.net/llama-3.2-11b-instruct":{"id":"inference.net/llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct (Inference.net)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.07,"output":0.33},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1 (Meta)","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2 (Meta)","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax M2 (MiniMax)","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.2,"output":1,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1 (MiniMax)","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.27,"output":1.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.1-lightning":{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning (MiniMax)","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":131072},"cost":{"input":0.12,"output":0.48},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5 (MiniMax)","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 Highspeed (MiniMax)","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7 (MiniMax)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 Highspeed (MiniMax)","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax M3 (MiniMax)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/minimax/minimax-text-01":{"id":"minimax/minimax-text-01","name":"MiniMax Text 01 (MiniMax)","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.2,"output":1.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/codestral-2508":{"id":"mistral/codestral-2508","name":"Codestral (Mistral AI)","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/devstral-2512":{"id":"mistral/devstral-2512","name":"Devstral 2 (Mistral AI)","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/ministral-14b-2512":{"id":"mistral/ministral-14b-2512","name":"Ministral 14B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/ministral-3b-2512":{"id":"mistral/ministral-3b-2512","name":"Ministral 3B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/ministral-8b-2512":{"id":"mistral/ministral-8b-2512","name":"Ministral 8B (Mistral AI)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/mistral-large-2512":{"id":"mistral/mistral-large-2512","name":"Mistral Large 3 (Mistral AI)","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/mistral-large-latest":{"id":"mistral/mistral-large-latest","name":"Mistral Large Latest (Mistral AI)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":262144},"cost":{"input":4,"output":12},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/mistral/mistral-small-2506":{"id":"mistral/mistral-small-2506","name":"Mistral Small 3.2 (Mistral AI)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/moonshot/kimi-k2.5":{"id":"moonshot/kimi-k2.5","name":"Kimi K2.5 (Moonshot AI)","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/moonshot/kimi-k2.6":{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6 (Moonshot AI)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/moonshot/kimi-k2.7-code":{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code (Moonshot AI)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/moonshot/kimi-k2.7-code-highspeed":{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed (Moonshot AI)","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/moonshot/kimi-k3":{"id":"moonshot/kimi-k3","name":"Kimi K3 (Moonshot AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/cosmos3-super-reasoner":{"id":"nebius/cosmos3-super-reasoner","name":"Cosmos 3 Super Reasoner (Nebius AI)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/deepseek-v4-pro":{"id":"nebius/deepseek-v4-pro","name":"DeepSeek V4 Pro (Nebius AI)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.75,"output":3.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/gemma-3-27b":{"id":"nebius/gemma-3-27b","name":"Gemma 3 27B (Nebius AI)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":110000,"output":110000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/glm-5.1":{"id":"nebius/glm-5.1","name":"GLM-5.1 (Nebius AI)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1.4,"output":4.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/glm-5.2":{"id":"nebius/glm-5.2","name":"GLM-5.2 (Nebius AI)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/gpt-oss-120b":{"id":"nebius/gpt-oss-120b","name":"GPT OSS 120B (Nebius AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/hermes-4-405b":{"id":"nebius/hermes-4-405b","name":"Hermes 4 405B (Nebius AI)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":1,"output":3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/hermes-4-70b":{"id":"nebius/hermes-4-70b","name":"Hermes 4 70B (Nebius AI)","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.13,"output":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/kimi-k2.6":{"id":"nebius/kimi-k2.6","name":"Kimi K2.6 (Nebius AI)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/kimi-k2.7-code":{"id":"nebius/kimi-k2.7-code","name":"Kimi K2.7 Code (Nebius AI)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/kimi-k3":{"id":"nebius/kimi-k3","name":"Kimi K3 (Nebius AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/llama-3.1-nemotron-ultra-253b":{"id":"nebius/llama-3.1-nemotron-ultra-253b","name":"Llama 3.1 Nemotron Ultra 253B (Nebius AI)","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.6,"output":1.8},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/llama-3.3-70b-instruct":{"id":"nebius/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (Nebius AI)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.13,"output":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/minicpm-v-4.5":{"id":"nebius/minicpm-v-4.5","name":"MiniCPM-V 4.5 (Nebius AI)","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.658,"output":1.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/minimax-m2.5":{"id":"nebius/minimax-m2.5","name":"MiniMax M2.5 (Nebius AI)","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131100},"cost":{"input":0.3,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/minimax-m3":{"id":"nebius/minimax-m3","name":"MiniMax M3 (Nebius AI)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/nemotron-3-nano-30b":{"id":"nebius/nemotron-3-nano-30b","name":"Nemotron 3 Nano 30B (Nebius AI)","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.24},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/nemotron-3-nano-omni":{"id":"nebius/nemotron-3-nano-omni","name":"Nemotron 3 Nano Omni (Nebius AI)","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.24},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/nemotron-3-super-120b":{"id":"nebius/nemotron-3-super-120b","name":"Nemotron 3 Super 120B (Nebius AI)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/nemotron-3-ultra-550b":{"id":"nebius/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B (Nebius AI)","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1,"output":3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/qwen2-5-vl-72b-instruct":{"id":"nebius/qwen2-5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct (Nebius AI)","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.25,"output":0.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/qwen3-235b-a22b-instruct-2507":{"id":"nebius/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (Nebius AI)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.2,"output":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/qwen3-30b-a3b-instruct-2507":{"id":"nebius/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507 (Nebius AI)","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":8192},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/qwen3-32b":{"id":"nebius/qwen3-32b","name":"Qwen3 32B (Nebius AI)","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":8192},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/nebius/qwen3-next-80b-a3b-thinking":{"id":"nebius/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking (Nebius AI)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/deepseek-v3.2":{"id":"novita/deepseek-v3.2","name":"DeepSeek V3.2 (NovitaAI)","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.269,"output":0.4,"cache_read":0.1345},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/deepseek-v4-flash":{"id":"novita/deepseek-v4-flash","name":"DeepSeek V4 Flash (NovitaAI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/ernie-4.5-vl-424b-a47b":{"id":"novita/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B (NovitaAI)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/gemma-4-26b-a4b-it":{"id":"novita/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT (NovitaAI)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/gemma-4-31b-it":{"id":"novita/gemma-4-31b-it","name":"Gemma 4 31B IT (NovitaAI)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.14,"output":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-4.5v":{"id":"novita/glm-4.5v","name":"GLM-4.5V (NovitaAI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-4.6":{"id":"novita/glm-4.6","name":"GLM-4.6 (NovitaAI)","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-4.6v":{"id":"novita/glm-4.6v","name":"GLM-4.6V (NovitaAI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16000},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-4.7":{"id":"novita/glm-4.7","name":"GLM-4.7 (NovitaAI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-5":{"id":"novita/glm-5","name":"GLM-5 (NovitaAI)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-5.1":{"id":"novita/glm-5.1","name":"GLM-5.1 (NovitaAI)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.38,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/glm-5.2":{"id":"novita/glm-5.2","name":"GLM-5.2 (NovitaAI)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/hy3":{"id":"novita/hy3","name":"Hy3 (NovitaAI)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/kimi-k2":{"id":"novita/kimi-k2","name":"Kimi K2 (NovitaAI)","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.57,"output":2.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/kimi-k2.6":{"id":"novita/kimi-k2.6","name":"Kimi K2.6 (NovitaAI)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3.4,"cache_read":0.16},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/kimi-k2.7-code":{"id":"novita/kimi-k2.7-code","name":"Kimi K2.7 Code (NovitaAI)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/kimi-k3":{"id":"novita/kimi-k3","name":"Kimi K3 (NovitaAI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/ling-3.0-flash":{"id":"novita/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash (NovitaAI)","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/llama-3-70b-instruct":{"id":"novita/llama-3-70b-instruct","name":"Llama 3 70B Instruct (NovitaAI)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-04-18","last_updated":"2024-04-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8000},"cost":{"input":0.51,"output":0.74},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/llama-3.2-3b-instruct":{"id":"novita/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct (NovitaAI)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32000},"cost":{"input":0.03,"output":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/llama-3.3-70b-instruct":{"id":"novita/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct (NovitaAI)","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":120000},"cost":{"input":0.135,"output":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/llama-4-maverick-17b-instruct":{"id":"novita/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct (NovitaAI)","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.27,"output":0.85},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/llama-4-scout-17b-instruct":{"id":"novita/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct (NovitaAI)","description":"Open Llama with long-context vision for efficient multimodal agents","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.18,"output":0.59},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/mimo-v2.5":{"id":"novita/mimo-v2.5","name":"MiMo V2.5 (NovitaAI)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.168,"output":0.336,"cache_read":0.0034,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/mimo-v2.5-pro":{"id":"novita/mimo-v2.5-pro","name":"MiMo V2.5 Pro (NovitaAI)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.522,"output":1.044,"cache_read":0.0043,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/minimax-m2.1":{"id":"novita/minimax-m2.1","name":"MiniMax M2.1 (NovitaAI)","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/minimax-m2.5":{"id":"novita/minimax-m2.5","name":"MiniMax M2.5 (NovitaAI)","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/minimax-m2.7":{"id":"novita/minimax-m2.7","name":"MiniMax M2.7 (NovitaAI)","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-235b-a22b-fp8":{"id":"novita/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8 (NovitaAI)","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":20000},"cost":{"input":0.2,"output":0.8},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-235b-a22b-instruct-2507":{"id":"novita/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (NovitaAI)","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.09,"output":0.58},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-235b-a22b-thinking-2507":{"id":"novita/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507 (NovitaAI)","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-coder-30b-a3b-instruct":{"id":"novita/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct (NovitaAI)","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":32768},"cost":{"input":0.07,"output":0.27},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-coder-480b-a35b-instruct":{"id":"novita/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct (NovitaAI)","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.38,"output":1.55},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-max":{"id":"novita/qwen3-max","name":"Qwen3 Max (NovitaAI)","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.845,"output":3.38},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-next-80b-a3b-instruct":{"id":"novita/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct (NovitaAI)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-vl-235b-a22b-instruct":{"id":"novita/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct (NovitaAI)","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":1.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-vl-235b-a22b-thinking":{"id":"novita/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking (NovitaAI)","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3-vl-30b-a3b-instruct":{"id":"novita/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct (NovitaAI)","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-10-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.7},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3.6-35b-a3b":{"id":"novita/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B (NovitaAI)","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.248,"output":1.485},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3.7-max":{"id":"novita/qwen3.7-max","name":"Qwen3.7 Max (NovitaAI)","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen3.8-max":{"id":"novita/qwen3.8-max","name":"Qwen3.8 Max (NovitaAI)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/novita/qwen35-397b-a17b":{"id":"novita/qwen35-397b-a17b","name":"Qwen3.5 397B A17B (NovitaAI)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":64000},"cost":{"input":0.6,"output":3.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo (OpenAI)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4 (OpenAI)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo (OpenAI)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1 (OpenAI)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini (OpenAI)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano (OpenAI)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o (OpenAI)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o Mini (OpenAI)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4o-mini-transcribe":{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe (OpenAI)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":2000},"cost":{"input":1.25,"output":5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-4o-transcribe":{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe (OpenAI)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":2000},"cost":{"input":2.5,"output":10},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5 (OpenAI)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini (OpenAI)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano (OpenAI)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro (OpenAI)","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1 (OpenAI)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2 (OpenAI)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro (OpenAI)","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":21,"output":168},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex (OpenAI)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4 (OpenAI)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini (OpenAI)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano (OpenAI)","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro (OpenAI)","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5 (OpenAI)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro (OpenAI)","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna (OpenAI)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol (OpenAI)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra (OpenAI)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/o1":{"id":"openai/o1","name":"o1 (OpenAI)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/o3":{"id":"openai/o3","name":"o3 (OpenAI)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/o3-mini":{"id":"openai/o3-mini","name":"o3 Mini (OpenAI)","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/openai/o4-mini":{"id":"openai/o4-mini","name":"o4 Mini (OpenAI)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/permafrost/kimi-k3":{"id":"permafrost/kimi-k3","name":"Kimi K3 (Permafrost)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar (Perplexity)","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro (Perplexity)","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro (Perplexity)","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/quartz/gemini-3.1-pro-preview":{"id":"quartz/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview) (Quartz)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/ranoai/deepseek-v4-flash":{"id":"ranoai/deepseek-v4-flash","name":"DeepSeek V4 Flash (RanoAI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/deepseek-v4-flash":{"id":"runware/deepseek-v4-flash","name":"DeepSeek V4 Flash (Runware)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/deepseek-v4-pro":{"id":"runware/deepseek-v4-pro","name":"DeepSeek V4 Pro (Runware)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.961,"output":1.922,"cache_read":0.079},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/gemma-4-31b-it":{"id":"runware/gemma-4-31b-it","name":"Gemma 4 31B IT (Runware)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.102,"output":0.297,"cache_read":0.012},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/glm-5.2":{"id":"runware/glm-5.2","name":"GLM-5.2 (Runware)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":128000},"cost":{"input":0.8,"output":2.55,"cache_read":0.16},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/gpt-oss-120b":{"id":"runware/gpt-oss-120b","name":"GPT OSS 120B (Runware)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.032,"output":0.14,"cache_read":0.032},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/runware/kimi-k2.6":{"id":"runware/kimi-k2.6","name":"Kimi K2.6 (Runware)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.6,"output":3.05,"cache_read":0.13},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra (Sakana AI)","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai-gp/glm-5.2":{"id":"scx-ai-gp/glm-5.2","name":"GLM-5.2 (SCX.ai)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.55,"output":1.784,"cache_read":0.111},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai-gp/glm-5.2-fast":{"id":"scx-ai-gp/glm-5.2-fast","name":"GLM-5.2 Turbo (SCX.ai)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.99,"output":6.16,"cache_read":0.4},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai-gp/qwen3.8-max":{"id":"scx-ai-gp/qwen3.8-max","name":"Qwen3.8 Max (SCX.ai)","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.815,"output":5.4461,"cache_read":0.21,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai/gemma-4-31b-it":{"id":"scx-ai/gemma-4-31b-it","name":"Gemma 4 31B IT (SCX.ai (Turbo))","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.3,"output":0.91},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai/gpt-oss-120b":{"id":"scx-ai/gpt-oss-120b","name":"GPT OSS 120B (SCX.ai (Turbo))","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.17,"output":0.55},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai/llama-4-maverick-17b-instruct":{"id":"scx-ai/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct (SCX.ai (Turbo))","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.53,"output":1.62},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai/minimax-m2.7":{"id":"scx-ai/minimax-m2.7","name":"MiniMax M2.7 (SCX.ai (Turbo))","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.48,"output":1.79,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/scx-ai/qwen3-32b":{"id":"scx-ai/qwen3-32b","name":"Qwen3 32B (SCX.ai (Turbo))","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.36,"output":0.87},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/deepseek-v4-flash":{"id":"together-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash (Together AI)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/deepseek-v4-pro":{"id":"together-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro (Together AI)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":163840},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/gemma-4-31b-it":{"id":"together-ai/gemma-4-31b-it","name":"Gemma 4 31B IT (Together AI)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.39,"output":0.97},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/glm-4.7":{"id":"together-ai/glm-4.7","name":"GLM-4.7 (Together AI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.45,"output":2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/gpt-oss-120b":{"id":"together-ai/gpt-oss-120b","name":"GPT OSS 120B (Together AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/gpt-oss-20b":{"id":"together-ai/gpt-oss-20b","name":"GPT OSS 20B (Together AI)","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/kimi-k3":{"id":"together-ai/kimi-k3","name":"Kimi K3 (Together AI)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/together-ai/minimax-m3":{"id":"together-ai/minimax-m3","name":"MiniMax M3 (Together AI)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/tundra/kimi-k2.6":{"id":"tundra/kimi-k2.6","name":"Kimi K2.6 (Tundra)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2.2,"cache_read":0.08},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-haiku-4-5":{"id":"vertex-anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (Vertex AI (Anthropic))","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-opus-4-5-20251101":{"id":"vertex-anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (Vertex AI (Anthropic))","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-opus-4-6":{"id":"vertex-anthropic/claude-opus-4-6","name":"Claude Opus 4.6 (Vertex AI (Anthropic))","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-opus-4-7":{"id":"vertex-anthropic/claude-opus-4-7","name":"Claude Opus 4.7 (Vertex AI (Anthropic))","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-sonnet-4-5":{"id":"vertex-anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (Vertex AI (Anthropic))","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-sonnet-4-6":{"id":"vertex-anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6 (Vertex AI (Anthropic))","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-anthropic/claude-sonnet-5":{"id":"vertex-anthropic/claude-sonnet-5","name":"Claude Sonnet 5 (Vertex AI (Anthropic))","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/deepseek-v3.2":{"id":"vertex-openai/deepseek-v3.2","name":"DeepSeek V3.2 (Vertex AI (OpenAI-compatible))","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.56,"output":1.68,"cache_read":0.056},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/glm-4.7":{"id":"vertex-openai/glm-4.7","name":"GLM-4.7 (Vertex AI (OpenAI-compatible))","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":128000},"cost":{"input":0.6,"output":2.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/glm-5":{"id":"vertex-openai/glm-5","name":"GLM-5 (Vertex AI (OpenAI-compatible))","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":32768},"cost":{"input":1,"output":3.2,"cache_read":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/grok-4-20-non-reasoning":{"id":"vertex-openai/grok-4-20-non-reasoning","name":"Grok 4.20 Non-Reasoning (Vertex AI (OpenAI-compatible))","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/grok-4-20-reasoning":{"id":"vertex-openai/grok-4-20-reasoning","name":"Grok 4.20 Reasoning (Vertex AI (OpenAI-compatible))","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/grok-4-6":{"id":"vertex-openai/grok-4-6","name":"Grok 4.6 (Vertex AI (OpenAI-compatible))","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/kimi-k2-thinking":{"id":"vertex-openai/kimi-k2-thinking","name":"Kimi K2 Thinking (Vertex AI (OpenAI-compatible))","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/qwen3-235b-a22b-instruct-2507":{"id":"vertex-openai/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible))","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.22,"output":0.88},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/qwen3-coder-480b-a35b-instruct":{"id":"vertex-openai/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible))","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-instruct":{"id":"vertex-openai/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible))","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/vertex-openai/qwen3-next-80b-a3b-thinking":{"id":"vertex-openai/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking (Vertex AI (OpenAI-compatible))","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4":{"id":"xai/grok-4","name":"Grok 4 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4-20-beta-0309-non-reasoning":{"id":"xai/grok-4-20-beta-0309-non-reasoning","name":"Grok 4.20 Beta Non-Reasoning (0309) (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4-20-beta-0309-reasoning":{"id":"xai/grok-4-20-beta-0309-reasoning","name":"Grok 4.20 Beta Reasoning (0309) (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4-3":{"id":"xai/grok-4-3","name":"Grok 4.3 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4-5":{"id":"xai/grok-4-5","name":"Grok 4.5 (xAI)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-4-6":{"id":"xai/grok-4-6","name":"Grok 4.6 (xAI)","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xai/grok-build-0-1":{"id":"xai/grok-build-0-1","name":"Grok Build 0.1 (xAI)","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo V2.5 (Xiaomi)","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro (Xiaomi)","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4-32b-0414-128k":{"id":"zai/glm-4-32b-0414-128k","name":"GLM-4 32B (0414-128k) (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.1,"output":0.1},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.5":{"id":"zai/glm-4.5","name":"GLM-4.5 (Z AI)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.5-air":{"id":"zai/glm-4.5-air","name":"GLM-4.5 Air (Z AI)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.5-airx":{"id":"zai/glm-4.5-airx","name":"GLM-4.5 AirX (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":1.1,"output":4.5,"cache_read":0.22},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.5-x":{"id":"zai/glm-4.5-x","name":"GLM-4.5 X (Z AI)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2.2,"output":8.9,"cache_read":0.45},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.5v":{"id":"zai/glm-4.5v","name":"GLM-4.5V (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM-4.6 (Z AI)","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.6v":{"id":"zai/glm-4.6v","name":"GLM-4.6V (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16000},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.6v-flashx":{"id":"zai/glm-4.6v-flashx","name":"GLM-4.6V FlashX (Z AI)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.04,"output":0.4,"cache_read":0.004},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM-4.7 (Z AI)","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-4.7-flashx":{"id":"zai/glm-4.7-flashx","name":"GLM-4.7 FlashX (Z AI)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-5":{"id":"zai/glm-5","name":"GLM-5 (Z AI)","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131100},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM-5.1 (Z AI)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM-5.2 (Z AI)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway-providers/zai/glm-5.3":{"id":"zai/glm-5.3","name":"GLM-5.3 (Z AI)","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway-providers"},"llmgateway/auto":{"id":"llmgateway/auto","name":"Auto Route","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"llmgateway"},"llmgateway/claude-fable-5":{"id":"llmgateway/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"llmgateway"},"llmgateway/claude-haiku-4-5":{"id":"llmgateway/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway"},"llmgateway/claude-haiku-4-5-20251001":{"id":"llmgateway/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-4-1-20250805":{"id":"llmgateway/claude-opus-4-1-20250805","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-4-5-20251101":{"id":"llmgateway/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":31999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-4-6":{"id":"llmgateway/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-4-7":{"id":"llmgateway/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-4-8":{"id":"llmgateway/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/claude-opus-5":{"id":"llmgateway/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/claude-sonnet-4-5":{"id":"llmgateway/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway"},"llmgateway/claude-sonnet-4-5-20250929":{"id":"llmgateway/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway"},"llmgateway/claude-sonnet-4-6":{"id":"llmgateway/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":63999},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"llmgateway"},"llmgateway/claude-sonnet-5":{"id":"llmgateway/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway"},"llmgateway/codestral-2508":{"id":"llmgateway/codestral-2508","name":"Codestral","description":"Mistral coding model for code completion, generation, and developer workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.3,"output":0.9},"sourceProvider":"llmgateway"},"llmgateway/cosmos3-super-reasoner":{"id":"llmgateway/cosmos3-super-reasoner","name":"Cosmos 3 Super Reasoner","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway"},"llmgateway/custom":{"id":"llmgateway/custom","name":"Custom Model","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"llmgateway"},"llmgateway/deepseek-v3.2":{"id":"llmgateway/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":16384},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"sourceProvider":"llmgateway"},"llmgateway/deepseek-v4-flash":{"id":"llmgateway/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"sourceProvider":"llmgateway"},"llmgateway/deepseek-v4-pro":{"id":"llmgateway/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"llmgateway"},"llmgateway/devstral-2512":{"id":"llmgateway/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"llmgateway"},"llmgateway/ernie-4.5-vl-424b-a47b":{"id":"llmgateway/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":123000,"output":123000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"llmgateway"},"llmgateway/fugu-ultra":{"id":"llmgateway/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-22","last_updated":"2026-06-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"llmgateway"},"llmgateway/gemini-2.5-flash":{"id":"llmgateway/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":24576},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"llmgateway"},"llmgateway/gemini-2.5-flash-lite":{"id":"llmgateway/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway"},"llmgateway/gemini-2.5-pro":{"id":"llmgateway/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"llmgateway"},"llmgateway/gemini-3-flash-preview":{"id":"llmgateway/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.1-flash-lite":{"id":"llmgateway/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.1-pro-preview":{"id":"llmgateway/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.5-flash":{"id":"llmgateway/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.5-flash-lite":{"id":"llmgateway/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.6-flash":{"id":"llmgateway/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway"},"llmgateway/gemini-3.7-flash":{"id":"llmgateway/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.08333},"sourceProvider":"llmgateway"},"llmgateway/gemini-pro-latest":{"id":"llmgateway/gemini-pro-latest","name":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-27","last_updated":"2026-02-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"llmgateway"},"llmgateway/gemma-3-27b":{"id":"llmgateway/gemma-3-27b","name":"Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":110000,"output":110000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway"},"llmgateway/gemma-4-26b-a4b-it":{"id":"llmgateway/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.07,"output":0.34},"sourceProvider":"llmgateway"},"llmgateway/gemma-4-31b-it":{"id":"llmgateway/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.102,"output":0.297,"cache_read":0.012},"sourceProvider":"llmgateway"},"llmgateway/glm-4-32b-0414-128k":{"id":"llmgateway/glm-4-32b-0414-128k","name":"GLM-4 32B (0414-128k)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.1},"sourceProvider":"llmgateway"},"llmgateway/glm-4.5":{"id":"llmgateway/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-4.5-air":{"id":"llmgateway/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-4.5-airx":{"id":"llmgateway/glm-4.5-airx","name":"GLM-4.5 AirX","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":4.5,"cache_read":0.22},"sourceProvider":"llmgateway"},"llmgateway/glm-4.5-x":{"id":"llmgateway/glm-4.5-x","name":"GLM-4.5 X","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"status":"beta","cost":{"input":2.2,"output":8.9,"cache_read":0.45},"sourceProvider":"llmgateway"},"llmgateway/glm-4.5v":{"id":"llmgateway/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"llmgateway"},"llmgateway/glm-4.6":{"id":"llmgateway/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-4.6v":{"id":"llmgateway/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/glm-4.6v-flashx":{"id":"llmgateway/glm-4.6v-flashx","name":"GLM-4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.04,"output":0.4,"cache_read":0.004},"sourceProvider":"llmgateway"},"llmgateway/glm-4.7":{"id":"llmgateway/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.38,"output":1.98,"cache_read":0.19,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-4.7-flash":{"id":"llmgateway/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.06,"output":0.4,"cache_read":0.01,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-4.7-flashx":{"id":"llmgateway/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-5":{"id":"llmgateway/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":203000,"output":131072},"cost":{"input":0.72,"output":2.3,"cache_read":0.144,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-5.1":{"id":"llmgateway/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.931,"output":2.93,"cache_read":0.173,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-5.2":{"id":"llmgateway/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.55,"output":1.784,"cache_read":0.111,"cache_write":0},"sourceProvider":"llmgateway"},"llmgateway/glm-5.2-fast":{"id":"llmgateway/glm-5.2-fast","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.99,"output":6.16,"cache_read":0.4},"sourceProvider":"llmgateway"},"llmgateway/glm-5.3":{"id":"llmgateway/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"llmgateway"},"llmgateway/gpt-3.5-turbo":{"id":"llmgateway/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0},"sourceProvider":"llmgateway"},"llmgateway/gpt-4":{"id":"llmgateway/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"llmgateway"},"llmgateway/gpt-4-turbo":{"id":"llmgateway/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"llmgateway"},"llmgateway/gpt-4.1":{"id":"llmgateway/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway"},"llmgateway/gpt-4.1-mini":{"id":"llmgateway/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"llmgateway"},"llmgateway/gpt-4.1-nano":{"id":"llmgateway/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"llmgateway"},"llmgateway/gpt-4o":{"id":"llmgateway/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"llmgateway"},"llmgateway/gpt-4o-mini":{"id":"llmgateway/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"llmgateway"},"llmgateway/gpt-4o-mini-transcribe":{"id":"llmgateway/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":1.25,"output":5},"sourceProvider":"llmgateway"},"llmgateway/gpt-4o-transcribe":{"id":"llmgateway/gpt-4o-transcribe","name":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":2.5,"output":10},"sourceProvider":"llmgateway"},"llmgateway/gpt-5":{"id":"llmgateway/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway"},"llmgateway/gpt-5-mini":{"id":"llmgateway/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"llmgateway"},"llmgateway/gpt-5-nano":{"id":"llmgateway/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"llmgateway"},"llmgateway/gpt-5-pro":{"id":"llmgateway/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.1":{"id":"llmgateway/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.1-codex":{"id":"llmgateway/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.1-codex-mini":{"id":"llmgateway/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.2":{"id":"llmgateway/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.2-codex":{"id":"llmgateway/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.2-pro":{"id":"llmgateway/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.3-codex":{"id":"llmgateway/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.4":{"id":"llmgateway/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.4-mini":{"id":"llmgateway/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.4-nano":{"id":"llmgateway/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.4-pro":{"id":"llmgateway/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.5":{"id":"llmgateway/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.5-pro":{"id":"llmgateway/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.6-luna":{"id":"llmgateway/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.6-sol":{"id":"llmgateway/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"llmgateway"},"llmgateway/gpt-5.6-terra":{"id":"llmgateway/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"llmgateway"},"llmgateway/gpt-oss-120b":{"id":"llmgateway/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32766},"cost":{"input":0.032,"output":0.14,"cache_read":0.032},"sourceProvider":"llmgateway"},"llmgateway/gpt-oss-20b":{"id":"llmgateway/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32766},"cost":{"input":0.05,"output":0.2},"sourceProvider":"llmgateway"},"llmgateway/grok-4":{"id":"llmgateway/grok-4","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"llmgateway"},"llmgateway/grok-4-1-fast-non-reasoning":{"id":"llmgateway/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/grok-4-1-fast-reasoning":{"id":"llmgateway/grok-4-1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/grok-4-20-beta-0309-non-reasoning":{"id":"llmgateway/grok-4-20-beta-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/grok-4-20-beta-0309-reasoning":{"id":"llmgateway/grok-4-20-beta-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":2,"output":6,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/grok-4-20-non-reasoning":{"id":"llmgateway/grok-4-20-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/grok-4-20-reasoning":{"id":"llmgateway/grok-4-20-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/grok-4-3":{"id":"llmgateway/grok-4-3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/grok-4-5":{"id":"llmgateway/grok-4-5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"llmgateway"},"llmgateway/grok-4-6":{"id":"llmgateway/grok-4-6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"llmgateway"},"llmgateway/grok-build-0-1":{"id":"llmgateway/grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/hermes-4-405b":{"id":"llmgateway/hermes-4-405b","name":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":1,"output":3},"sourceProvider":"llmgateway"},"llmgateway/hermes-4-70b":{"id":"llmgateway/hermes-4-70b","name":"Hermes 4 70B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.13,"output":0.4},"sourceProvider":"llmgateway"},"llmgateway/hy3":{"id":"llmgateway/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.14,"output":0.58,"cache_read":0.035},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2":{"id":"llmgateway/kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.57,"output":2.3,"cache_read":0.5},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2-thinking":{"id":"llmgateway/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.06},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2.5":{"id":"llmgateway/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.405,"output":1.98,"cache_read":0.225},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2.6":{"id":"llmgateway/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.22,"output":1.137,"cache_read":0.048},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2.7-code":{"id":"llmgateway/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"llmgateway"},"llmgateway/kimi-k2.7-code-highspeed":{"id":"llmgateway/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"llmgateway"},"llmgateway/kimi-k3":{"id":"llmgateway/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"llmgateway"},"llmgateway/kimi-k3-fast":{"id":"llmgateway/kimi-k3-fast","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1040384,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"llmgateway"},"llmgateway/ling-3.0-flash":{"id":"llmgateway/ling-3.0-flash","name":"InclusionAI Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"sourceProvider":"llmgateway"},"llmgateway/llama-3-70b-instruct":{"id":"llmgateway/llama-3-70b-instruct","name":"Llama 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-04-18","last_updated":"2024-04-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8000},"cost":{"input":0.51,"output":0.74},"sourceProvider":"llmgateway"},"llmgateway/llama-3.1-70b-instruct":{"id":"llmgateway/llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"status":"beta","cost":{"input":0.72,"output":0.72},"sourceProvider":"llmgateway"},"llmgateway/llama-3.1-nemotron-ultra-253b":{"id":"llmgateway/llama-3.1-nemotron-ultra-253b","name":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.6,"output":1.8},"sourceProvider":"llmgateway"},"llmgateway/llama-3.2-11b-instruct":{"id":"llmgateway/llama-3.2-11b-instruct","name":"Llama 3.2 11B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.07,"output":0.33},"sourceProvider":"llmgateway"},"llmgateway/llama-3.2-3b-instruct":{"id":"llmgateway/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.03,"output":0.05},"sourceProvider":"llmgateway"},"llmgateway/llama-3.3-70b-instruct":{"id":"llmgateway/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.13,"output":0.4},"sourceProvider":"llmgateway"},"llmgateway/llama-4-maverick-17b-instruct":{"id":"llmgateway/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":2048},"cost":{"input":0.27,"output":0.85},"sourceProvider":"llmgateway"},"llmgateway/llama-4-scout-17b-instruct":{"id":"llmgateway/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":2048},"cost":{"input":0.18,"output":0.59},"sourceProvider":"llmgateway"},"llmgateway/mimo-v2.5":{"id":"llmgateway/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"llmgateway"},"llmgateway/mimo-v2.5-pro":{"id":"llmgateway/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"llmgateway"},"llmgateway/minicpm-v-4.5":{"id":"llmgateway/minicpm-v-4.5","name":"MiniCPM-V 4.5","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.658,"output":1.11},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2":{"id":"llmgateway/minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0.2,"output":1,"cache_read":0.03},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.1":{"id":"llmgateway/minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.27,"output":1.1},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.1-lightning":{"id":"llmgateway/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.12,"output":0.48},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.5":{"id":"llmgateway/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":228700,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.5-highspeed":{"id":"llmgateway/minimax-m2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.7":{"id":"llmgateway/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.08,"output":0.32,"cache_read":0.017,"cache_write":0.375},"sourceProvider":"llmgateway"},"llmgateway/minimax-m2.7-highspeed":{"id":"llmgateway/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"llmgateway"},"llmgateway/minimax-m3":{"id":"llmgateway/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"llmgateway"},"llmgateway/minimax-text-01":{"id":"llmgateway/minimax-text-01","name":"MiniMax Text 01","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.2,"output":1.1},"sourceProvider":"llmgateway"},"llmgateway/ministral-14b-2512":{"id":"llmgateway/ministral-14b-2512","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.2},"sourceProvider":"llmgateway"},"llmgateway/ministral-3b-2512":{"id":"llmgateway/ministral-3b-2512","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.1,"output":0.1},"sourceProvider":"llmgateway"},"llmgateway/ministral-8b-2512":{"id":"llmgateway/ministral-8b-2512","name":"Ministral 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"mistral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.15},"sourceProvider":"llmgateway"},"llmgateway/mistral-large-2512":{"id":"llmgateway/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"llmgateway"},"llmgateway/mistral-large-latest":{"id":"llmgateway/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":262144},"cost":{"input":4,"output":12},"sourceProvider":"llmgateway"},"llmgateway/mistral-small-2506":{"id":"llmgateway/mistral-small-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway"},"llmgateway/muse-spark-1.1":{"id":"llmgateway/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":32000},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"llmgateway"},"llmgateway/muse-spark-1.2":{"id":"llmgateway/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"llmgateway"},"llmgateway/nemotron-3-nano-30b":{"id":"llmgateway/nemotron-3-nano-30b","name":"Nemotron 3 Nano 30B","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.24},"sourceProvider":"llmgateway"},"llmgateway/nemotron-3-nano-omni":{"id":"llmgateway/nemotron-3-nano-omni","name":"Nemotron 3 Nano Omni","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.06,"output":0.24},"sourceProvider":"llmgateway"},"llmgateway/nemotron-3-super-120b":{"id":"llmgateway/nemotron-3-super-120b","name":"Nemotron 3 Super 120B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9},"sourceProvider":"llmgateway"},"llmgateway/nemotron-3-ultra-550b":{"id":"llmgateway/nemotron-3-ultra-550b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.5,"output":2.2,"cache_read":0.1},"sourceProvider":"llmgateway"},"llmgateway/o1":{"id":"llmgateway/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"llmgateway"},"llmgateway/o3":{"id":"llmgateway/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"llmgateway"},"llmgateway/o3-mini":{"id":"llmgateway/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"llmgateway"},"llmgateway/o4-mini":{"id":"llmgateway/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"llmgateway"},"llmgateway/qwen-coder-plus":{"id":"llmgateway/qwen-coder-plus","name":"Qwen Coder Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.502,"output":1.004},"sourceProvider":"llmgateway"},"llmgateway/qwen-flash":{"id":"llmgateway/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4,"cache_read":0.01,"cache_write":0.0625},"sourceProvider":"llmgateway"},"llmgateway/qwen-max":{"id":"llmgateway/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":1.6,"output":6.4},"sourceProvider":"llmgateway"},"llmgateway/qwen-omni-turbo":{"id":"llmgateway/qwen-omni-turbo","name":"Qwen-Omni Turbo","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-01-19","last_updated":"2025-03-26","modalities":{"input":["text","image","audio","video"],"output":["text","audio"]},"open_weights":false,"limit":{"context":32768,"output":2048},"cost":{"input":0.2,"output":0.8},"sourceProvider":"llmgateway"},"llmgateway/qwen-plus":{"id":"llmgateway/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":1.2,"reasoning":4,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway"},"llmgateway/qwen-plus-latest":{"id":"llmgateway/qwen-plus-latest","name":"Qwen Plus Latest","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-25","last_updated":"2025-01-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":8192},"cost":{"input":0.4,"output":1.2,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway"},"llmgateway/qwen2-5-vl-72b-instruct":{"id":"llmgateway/qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-09","last_updated":"2024-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.25,"output":0.75},"sourceProvider":"llmgateway"},"llmgateway/qwen3-235b-a22b-fp8":{"id":"llmgateway/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":8192},"cost":{"input":0.2,"output":0.8},"sourceProvider":"llmgateway"},"llmgateway/qwen3-235b-a22b-instruct-2507":{"id":"llmgateway/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct (2507)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.09,"output":0.58},"sourceProvider":"llmgateway"},"llmgateway/qwen3-235b-a22b-thinking-2507":{"id":"llmgateway/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking (2507)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.3,"output":3},"sourceProvider":"llmgateway"},"llmgateway/qwen3-30b-a3b-instruct-2507":{"id":"llmgateway/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct (2507)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":8192},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmgateway"},"llmgateway/qwen3-32b":{"id":"llmgateway/qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":16384},"cost":{"input":0.1,"output":0.3,"reasoning":8.4},"sourceProvider":"llmgateway"},"llmgateway/qwen3-coder-30b-a3b-instruct":{"id":"llmgateway/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0.07,"output":0.27},"sourceProvider":"llmgateway"},"llmgateway/qwen3-coder-480b-a35b-instruct":{"id":"llmgateway/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.38,"output":1.55},"sourceProvider":"llmgateway"},"llmgateway/qwen3-coder-flash":{"id":"llmgateway/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"llmgateway"},"llmgateway/qwen3-coder-next":{"id":"llmgateway/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.108,"output":0.675,"cache_read":0.06},"sourceProvider":"llmgateway"},"llmgateway/qwen3-coder-plus":{"id":"llmgateway/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":6,"output":60,"cache_read":1.2,"cache_write":7.5},"sourceProvider":"llmgateway"},"llmgateway/qwen3-max":{"id":"llmgateway/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.845,"output":3.38,"cache_read":0.6,"cache_write":3.75},"sourceProvider":"llmgateway"},"llmgateway/qwen3-next-80b-a3b-instruct":{"id":"llmgateway/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"llmgateway"},"llmgateway/qwen3-next-80b-a3b-thinking":{"id":"llmgateway/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"llmgateway"},"llmgateway/qwen3-vl-235b-a22b-instruct":{"id":"llmgateway/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.88,"cache_read":0.11},"sourceProvider":"llmgateway"},"llmgateway/qwen3-vl-235b-a22b-thinking":{"id":"llmgateway/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.98,"output":3.95},"sourceProvider":"llmgateway"},"llmgateway/qwen3-vl-30b-a3b-instruct":{"id":"llmgateway/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmgateway"},"llmgateway/qwen3-vl-flash":{"id":"llmgateway/qwen3-vl-flash","name":"Qwen3 VL Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-09","last_updated":"2025-10-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32000},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"sourceProvider":"llmgateway"},"llmgateway/qwen3-vl-plus":{"id":"llmgateway/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":1.6,"reasoning":4.8,"cache_read":0.04,"cache_write":0.25},"sourceProvider":"llmgateway"},"llmgateway/qwen3.5-9b":{"id":"llmgateway/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.15},"sourceProvider":"llmgateway"},"llmgateway/qwen3.6-35b-a3b":{"id":"llmgateway/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"sourceProvider":"llmgateway"},"llmgateway/qwen3.6-flash":{"id":"llmgateway/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.05,"cache_write":0.3125},"sourceProvider":"llmgateway"},"llmgateway/qwen3.6-max-preview":{"id":"llmgateway/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.3,"output":7.8,"cache_read":0.13,"cache_write":1.625},"sourceProvider":"llmgateway"},"llmgateway/qwen3.6-plus":{"id":"llmgateway/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"llmgateway"},"llmgateway/qwen3.7-flash":{"id":"llmgateway/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-27","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.0375},"sourceProvider":"llmgateway"},"llmgateway/qwen3.7-max":{"id":"llmgateway/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"llmgateway"},"llmgateway/qwen3.7-plus":{"id":"llmgateway/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"llmgateway"},"llmgateway/qwen3.8-max":{"id":"llmgateway/qwen3.8-max","name":"Qwen3.8 Max Preview","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.815,"output":5.4461,"cache_read":0.21,"cache_write":2.5},"sourceProvider":"llmgateway"},"llmgateway/qwen35-397b-a17b":{"id":"llmgateway/qwen35-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"llmgateway"},"llmgateway/seed-1-6-250615":{"id":"llmgateway/seed-1-6-250615","name":"Seed 1.6 (250615)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/seed-1-6-250915":{"id":"llmgateway/seed-1-6-250915","name":"Seed 1.6 (250915)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/seed-1-6-flash-250715":{"id":"llmgateway/seed-1-6-flash-250715","name":"Seed 1.6 Flash (250715)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.07,"output":0.3,"cache_read":0.015},"sourceProvider":"llmgateway"},"llmgateway/seed-1-8-251228":{"id":"llmgateway/seed-1-8-251228","name":"Seed 1.8 (251228)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"llmgateway"},"llmgateway/sonar":{"id":"llmgateway/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":130000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"llmgateway"},"llmgateway/sonar-pro":{"id":"llmgateway/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"llmgateway"},"llmgateway/sonar-reasoning-pro":{"id":"llmgateway/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"llmgateway"},"llmtr/gemma-4":{"id":"llmtr/gemma-4","name":"Gemma 4","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":2,"output":5,"cache_read":0.5},"sourceProvider":"llmtr"},"llmtr/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.1},"sourceProvider":"llmtr"},"llmtr/magibu-11b-v8":{"id":"llmtr/magibu-11b-v8","name":"Magibu 11B v8","description":"Turkish-language chat model for instruction following and assistant flows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-06-05","last_updated":"2026-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":0.1,"output":0.5},"sourceProvider":"llmtr"},"llmtr/medgemma-4b":{"id":"llmtr/medgemma-4b","name":"MedGemma 4B","description":"Multimodal medical-domain Gemma variant for text and image analysis","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-26","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"status":"deprecated","cost":{"input":3,"output":5},"sourceProvider":"llmtr"},"llmtr/meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2},"sourceProvider":"llmtr"},"llmtr/mimo/mimo-v2.5":{"id":"mimo/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.14,"output":0.28},"sourceProvider":"llmtr"},"llmtr/mimo/mimo-v2.5-pro":{"id":"mimo/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87},"sourceProvider":"llmtr"},"llmtr/mistral/voxtral-small-latest":{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"llmtr"},"llmtr/muse-glimmer-30b-tr":{"id":"llmtr/muse-glimmer-30b-tr","name":"Muse Glimmer 30B (TR)","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":2,"output":5,"cache_read":0.5},"sourceProvider":"llmtr"},"llmtr/perplexity/sonar-deep-research":{"id":"perplexity/sonar-deep-research","name":"Sonar Deep Research","description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"llmtr"},"llmtr/poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"llmtr"},"llmtr/publicai/apertus-70b-instruct":{"id":"publicai/apertus-70b-instruct","name":"Apertus 70B Instruct","description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8192},"cost":{"input":0.82,"output":2.92},"sourceProvider":"llmtr"},"llmtr/publicai/apertus-8b-instruct":{"id":"publicai/apertus-8b-instruct","name":"Apertus 8B Instruct","description":"Fully open 8B multilingual LLM supporting 1800+ languages with 65K context. Trained on compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8192},"cost":{"input":0.1,"output":0.2},"sourceProvider":"llmtr"},"llmtr/qwen/qwen-flash":{"id":"qwen/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.05,"output":0.4},"sourceProvider":"llmtr"},"llmtr/qwen/qwen-plus":{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.4,"output":1.2},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.5},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1,"output":5},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3-vl-plus":{"id":"qwen/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"cost":{"input":0.2,"output":1.6},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.6,"output":3.6},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3.5-plus":{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"llmtr"},"llmtr/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6},"sourceProvider":"llmtr"},"llmtr/qwen3-6-35b":{"id":"llmtr/qwen3-6-35b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":5,"output":10},"sourceProvider":"llmtr"},"llmtr/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30},"sourceProvider":"llmtr"},"llmtr/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.87,"output":4.68},"sourceProvider":"llmtr"},"llmtr/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.58,"output":1.44},"sourceProvider":"llmtr"},"llmtr/trendyol-asure-12b":{"id":"llmtr/trendyol-asure-12b","name":"Trendyol Asure 12B","description":"Turkish-language multimodal instruct model built on Gemma 3 12B for e-commerce text, chat, and image-text tasks","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-19","last_updated":"2026-02-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.1,"output":0.5,"cache_read":0.025},"sourceProvider":"llmtr"},"llmtr/upstage/solar-pro2":{"id":"upstage/solar-pro2","name":"Solar Pro 2","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmtr"},"llmtr/upstage/solar-pro3":{"id":"upstage/solar-pro3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"llmtr"},"llmtr/upstage/solar-pro4":{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.03,"output":0.12},"sourceProvider":"llmtr"},"lmstudio/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"lmstudio"},"lmstudio/qwen/qwen3-30b-a3b-2507":{"id":"qwen/qwen3-30b-a3b-2507","name":"Qwen3 30B A3B 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"lmstudio"},"lmstudio/qwen/qwen3-coder-30b":{"id":"qwen/qwen3-coder-30b","name":"Qwen3 Coder 30B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"lmstudio"},"longcat/LongCat-2.0":{"id":"longcat/LongCat-2.0","name":"LongCat-2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.75,"output":2.95,"cache_read":0.015},"sourceProvider":"longcat"},"lucidquery/lucidnova-rf1-100b":{"id":"lucidquery/lucidnova-rf1-100b","name":"LucidNova RF1 100B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"nova","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-09-16","release_date":"2024-12-28","last_updated":"2025-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":120000,"output":8000},"cost":{"input":2,"output":5},"sourceProvider":"lucidquery"},"lucidquery/lucidquery-agi-01-frontier":{"id":"lucidquery/lucidquery-agi-01-frontier","name":"AGI-01 Frontier","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-06-05","release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":120000},"cost":{"input":4.5,"output":22},"sourceProvider":"lucidquery"},"lucidquery/lucidquery-agi-01-swift":{"id":"lucidquery/lucidquery-agi-01-swift","name":"AGI-01 Swift","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-06-05","release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":120000},"cost":{"input":2.5,"output":15},"sourceProvider":"lucidquery"},"lucidquery/lucidquery-nexus-coder":{"id":"lucidquery/lucidquery-nexus-coder","name":"LucidQuery Nexus Coder","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"lucid","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-08-01","release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":250000,"output":60000},"cost":{"input":2,"output":5},"sourceProvider":"lucidquery"},"lynkr/lynkr-auto":{"id":"lynkr/lynkr-auto","name":"Lynkr Auto (complexity routing)","description":"Virtual model: Lynkr scores each request on complexity and routes it to the tier model the user configured (local Ollama/llama.cpp for simple requests, configured cloud providers for complex ones).","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2026-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"lynkr"},"meganova/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":64000},"cost":{"input":0.5,"output":2.15},"sourceProvider":"meganova"},"meganova/deepseek-ai/DeepSeek-V3-0324":{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":0.88},"sourceProvider":"meganova"},"meganova/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-08-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"sourceProvider":"meganova"},"meganova/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.26,"output":0.38},"sourceProvider":"meganova"},"meganova/deepseek-ai/DeepSeek-V3.2-Exp":{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-10-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.4},"sourceProvider":"meganova"},"meganova/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"meganova"},"meganova/MiniMaxAI/MiniMax-M2.1":{"id":"MiniMaxAI/MiniMax-M2.1","name":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":131072},"cost":{"input":0.28,"output":1.2},"sourceProvider":"meganova"},"meganova/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"meganova"},"meganova/mistralai/Mistral-Nemo-Instruct-2407":{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo Instruct 2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.02,"output":0.04},"sourceProvider":"meganova"},"meganova/mistralai/Mistral-Small-3.2-24B-Instruct-2506":{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral Small 3.2 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"meganova"},"meganova/moonshotai/Kimi-K2-Thinking":{"id":"moonshotai/Kimi-K2-Thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.6},"sourceProvider":"meganova"},"meganova/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":2.8},"sourceProvider":"meganova"},"meganova/Qwen/Qwen2.5-VL-32B-Instruct":{"id":"Qwen/Qwen2.5-VL-32B-Instruct","name":"Qwen2.5 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.2,"output":0.6},"sourceProvider":"meganova"},"meganova/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.09,"output":0.6},"sourceProvider":"meganova"},"meganova/Qwen/Qwen3.5-Plus":{"id":"Qwen/Qwen3.5-Plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02","last_updated":"2026-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"reasoning":2.4},"sourceProvider":"meganova"},"meganova/XiaomiMiMo/MiMo-V2-Flash":{"id":"XiaomiMiMo/MiMo-V2-Flash","name":"MiMo V2 Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"meganova"},"meganova/zai-org/GLM-4.6":{"id":"zai-org/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.45,"output":1.9},"sourceProvider":"meganova"},"meganova/zai-org/GLM-4.7":{"id":"zai-org/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.2,"output":0.8},"sourceProvider":"meganova"},"meganova/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.8,"output":2.56},"sourceProvider":"meganova"},"merge-gateway/anthropic/claude-3-7-sonnet-20250219":{"id":"anthropic/claude-3-7-sonnet-20250219","name":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-haiku-4-5-20251001":{"id":"anthropic/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5 (20251001)","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-1-20250805":{"id":"anthropic/claude-opus-4-1-20250805","name":"Claude Opus 4.1 (20250805)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-20250514":{"id":"anthropic/claude-opus-4-20250514","name":"Claude Opus 4 (20250514)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-5-20251101":{"id":"anthropic/claude-opus-4-5-20251101","name":"Claude Opus 4.5 (20251101)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":128000}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-sonnet-4-20250514":{"id":"anthropic/claude-sonnet-4-20250514","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-sonnet-4-5-20250929":{"id":"anthropic/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5 (20250929)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"merge-gateway"},"merge-gateway/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"merge-gateway"},"merge-gateway/bytedance/dola-seed-2.0-code":{"id":"bytedance/dola-seed-2.0-code","name":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.4,"output":2.4},"sourceProvider":"merge-gateway"},"merge-gateway/bytedance/dola-seed-2.0-code-preview":{"id":"bytedance/dola-seed-2.0-code-preview","name":"Dola Seed 2.0 Code (preview)","description":"Preview coding model for repository understanding, refactors, and engineering tasks","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"merge-gateway"},"merge-gateway/bytedance/dola-seed-2.0-lite":{"id":"bytedance/dola-seed-2.0-lite","name":"Seed 2.0 Lite","description":"Efficient Seed model for general chat, analysis, and lightweight production tasks","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-28","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.25,"output":2},"sourceProvider":"merge-gateway"},"merge-gateway/bytedance/dola-seed-2.0-mini":{"id":"bytedance/dola-seed-2.0-mini","name":"Seed 2.0 Mini","description":"Low-cost Seed model for general chat, extraction, and lightweight production tasks","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.4},"sourceProvider":"merge-gateway"},"merge-gateway/bytedance/dola-seed-2.0-pro":{"id":"bytedance/dola-seed-2.0-pro","name":"Seed 2.0 Pro","description":"Higher-capability Seed model for complex chat, analysis, and production tasks","family":"seed","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"merge-gateway"},"merge-gateway/cohere/command-a-03-2025":{"id":"cohere/command-a-03-2025","name":"Command A 03-2025","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"merge-gateway"},"merge-gateway/cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Command R 08-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"merge-gateway"},"merge-gateway/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+ 08-2024","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"sourceProvider":"merge-gateway"},"merge-gateway/cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Command R7B 12-2024","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":40960},"cost":{"input":1.35,"output":5.4},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v3":{"id":"deepseek/deepseek-v3","name":"DeepSeek V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":81920},"cost":{"input":0.58,"output":1.68},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v3.1":{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":41000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":40960},"cost":{"input":0.28,"output":0.45,"cache_read":0.14},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.035,"output":0.07,"cache_read":0.007},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v4-pro-0423":{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":393216},"cost":{"input":1.65,"output":3.3},"sourceProvider":"merge-gateway"},"merge-gateway/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-2.5-computer-use-preview-10-2025":{"id":"google/gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview (10-2025)","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":1.25,"output":10},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":2.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Gemini 3 Pro Image","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":2,"output":12},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3-pro-preview":{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Gemini 3.1 Flash Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash-Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-embedding-001":{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":4096},"cost":{"input":0.15,"output":0},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-flash-latest":{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemini-flash-lite-latest":{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.13,"output":0.4},"sourceProvider":"merge-gateway"},"merge-gateway/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B It","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.14,"output":0.4},"sourceProvider":"merge-gateway"},"merge-gateway/meta/llama-3.1-8b-instruct":{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"cost":{"input":0.22,"output":0.22},"sourceProvider":"merge-gateway"},"merge-gateway/meta/llama-3.3-70b-instruct":{"id":"meta/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.22,"output":0.5,"cache_read":0.11},"sourceProvider":"merge-gateway"},"merge-gateway/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"merge-gateway"},"merge-gateway/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":262144},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 Highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":8192},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":128000}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/codestral-latest":{"id":"mistral/codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/devstral-2512":{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/devstral-medium-2507":{"id":"mistral/devstral-medium-2507","name":"Devstral Medium","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/devstral-medium-latest":{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/devstral-small-2507":{"id":"mistral/devstral-small-2507","name":"Devstral Small","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/magistral-medium-latest":{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2,"output":5},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-large-2411":{"id":"mistral/mistral-large-2411","name":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":2,"output":6},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-large-2512":{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-large-latest":{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-medium-2505":{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-medium-latest":{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/mistral-small-latest":{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"merge-gateway"},"merge-gateway/mistral/pixtral-large-latest":{"id":"mistral/pixtral-large-latest","name":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2024-11-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":6},"sourceProvider":"merge-gateway"},"merge-gateway/moonshot/kimi-k2.5":{"id":"moonshot/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"merge-gateway"},"merge-gateway/moonshot/kimi-k2.6":{"id":"moonshot/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"merge-gateway"},"merge-gateway/moonshot/kimi-k2.7-code":{"id":"moonshot/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"merge-gateway"},"merge-gateway/moonshot/kimi-k2.7-code-highspeed":{"id":"moonshot/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"merge-gateway"},"merge-gateway/moonshot/kimi-k3":{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"merge-gateway"},"merge-gateway/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.6,"output":2.5},"sourceProvider":"merge-gateway"},"merge-gateway/nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"merge-gateway"},"merge-gateway/nvidia/nemotron-nano-9b-v2":{"id":"nvidia/nemotron-nano-9b-v2","name":"Nemotron Nano 9B","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.06,"output":0.23},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o Mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5-chat-latest":{"id":"openai/gpt-5-chat-latest","name":"GPT-5 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.1-chat-latest":{"id":"openai/gpt-5.1-chat-latest","name":"GPT-5.1 Chat Latest","description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.2-chat-latest":{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.3-chat-latest":{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":24,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.09,"output":0.36},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT-OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.04,"output":0.2,"cache_read":0.02},"sourceProvider":"merge-gateway"},"merge-gateway/openai/gpt-oss-safeguard-120b":{"id":"openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.15,"output":0.6},"sourceProvider":"merge-gateway"},"merge-gateway/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"merge-gateway"},"merge-gateway/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/openai/o3-mini":{"id":"openai/o3-mini","name":"o3 Mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"merge-gateway"},"merge-gateway/openai/o4-mini":{"id":"openai/o4-mini","name":"o4 Mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen-flash":{"id":"qwen/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.022,"output":0.216,"cache_read":0.0044},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen-plus":{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.115,"output":0.287,"cache_read":0.023},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-235b-a22b":{"id":"qwen/qwen3-235b-a22b","name":"Qwen3 235B A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":1.147,"cache_read":0.0574},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-235b-a22b-instruct-2507":{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.6,"cache_read":0.05},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-30b-a3b":{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.108,"output":1.076,"cache_read":0.0216},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-32b":{"id":"qwen/qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-coder-480b-a35b-instruct":{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.22,"output":1.8},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.144,"output":0.574,"cache_read":0.0288},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.8,"cache_read":0.075},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.574,"output":2.294,"cache_read":0.1148},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.359,"output":1.434,"cache_read":0.0718},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.144,"output":0.574,"cache_read":0.0288},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3-VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":1.147,"cache_read":0.15785},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3-VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.287,"output":2.867,"cache_read":0.0574},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3-vl-plus":{"id":"qwen/qwen3-vl-plus","name":"Qwen3-VL Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.143,"output":1.434,"cache_read":0.0286},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.115,"output":0.917,"cache_read":0.023},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.086,"output":0.688,"cache_read":0.0172},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.057,"output":0.459,"cache_read":0.020357},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.172,"output":1.032,"cache_read":0.0344},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.09,"output":0.13},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-flash":{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.029,"output":0.287,"cache_read":0.0058},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.5-plus":{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.115,"output":0.688,"cache_read":0.023},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.289,"output":2.4},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.6-35b-a3b":{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485,"cache_read":0.0496},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.165,"output":0.99,"cache_read":0.033},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.6-max-preview":{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1.31,"output":7.88},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.276,"output":1.651,"cache_read":0.0552},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.825,"output":2.4755,"cache_read":0.165},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.8-2.4t-a95b":{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":1010000},"cost":{"input":2.5,"output":6.25,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/qwen/qwen3.8-max":{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"sourceProvider":"merge-gateway"},"merge-gateway/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/sakana/sakana-namazu":{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","family":"sakana-namazu","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"sourceProvider":"merge-gateway"},"merge-gateway/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"output":32000},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"merge-gateway"},"merge-gateway/writer/palmyra-x4":{"id":"writer/palmyra-x4","name":"Palmyra X4","description":"Enterprise language model for writing, analysis, and tool-assisted workflows","family":"palmyra","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-10-09","last_updated":"2024-10-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":2.5,"output":10},"sourceProvider":"merge-gateway"},"merge-gateway/writer/palmyra-x5":{"id":"writer/palmyra-x5","name":"Palmyra X5","description":"Enterprise multimodal model for writing, analysis, and tool-assisted workflows","family":"palmyra","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":250000},"cost":{"input":0.6,"output":6},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-4.20-0309-non-reasoning":{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-4.20-0309-reasoning":{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-4.5":{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-4.6":{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":1.5,"output":4.5,"cache_read":0.375},"sourceProvider":"merge-gateway"},"merge-gateway/xai/grok-build-0.1":{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.5":{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.5-air":{"id":"zai/glm-4.5-air","name":"GLM-4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.5v":{"id":"zai/glm-4.5v","name":"Glm 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.7-flash":{"id":"zai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-4.7-flashx":{"id":"zai/glm-4.7-flashx","name":"GLM-4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-5":{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-5-turbo":{"id":"zai/glm-5-turbo","name":"GLM-5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":50000}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.05,"output":3.3,"cache_read":0.195},"sourceProvider":"merge-gateway"},"merge-gateway/zai/glm-5.3":{"id":"zai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.7,"output":2.2,"cache_read":0.13},"sourceProvider":"merge-gateway"},"meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"meta"},"meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"meta"},"meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"meta"},"minimax-cn-coding-plan/MiniMax-M2":{"id":"minimax-cn-coding-plan/MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M2.1":{"id":"minimax-cn-coding-plan/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M2.5":{"id":"minimax-cn-coding-plan/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M2.5-highspeed":{"id":"minimax-cn-coding-plan/MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M2.7":{"id":"minimax-cn-coding-plan/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M2.7-highspeed":{"id":"minimax-cn-coding-plan/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn-coding-plan/MiniMax-M3":{"id":"minimax-cn-coding-plan/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-cn-coding-plan"},"minimax-cn/MiniMax-M2":{"id":"minimax-cn/MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M2.1":{"id":"minimax-cn/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M2.5":{"id":"minimax-cn/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M2.5-highspeed":{"id":"minimax-cn/MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M2.7":{"id":"minimax-cn/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M2.7-highspeed":{"id":"minimax-cn/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax-cn"},"minimax-cn/MiniMax-M3":{"id":"minimax-cn/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"sourceProvider":"minimax-cn"},"minimax-coding-plan/MiniMax-M2":{"id":"minimax-coding-plan/MiniMax-M2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M2.1":{"id":"minimax-coding-plan/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M2.5":{"id":"minimax-coding-plan/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M2.5-highspeed":{"id":"minimax-coding-plan/MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M2.7":{"id":"minimax-coding-plan/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M2.7-highspeed":{"id":"minimax-coding-plan/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax-coding-plan/MiniMax-M3":{"id":"minimax-coding-plan/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"minimax-coding-plan"},"minimax/MiniMax-M2":{"id":"minimax/MiniMax-M2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"minimax"},"minimax/MiniMax-M2.1":{"id":"minimax/MiniMax-M2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"minimax"},"minimax/MiniMax-M2.5":{"id":"minimax/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"minimax"},"minimax/MiniMax-M2.5-highspeed":{"id":"minimax/MiniMax-M2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax"},"minimax/MiniMax-M2.7":{"id":"minimax/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax"},"minimax/MiniMax-M2.7-highspeed":{"id":"minimax/MiniMax-M2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"minimax"},"minimax/MiniMax-M3":{"id":"minimax/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"sourceProvider":"minimax"},"mistral/codestral-latest":{"id":"mistral/codestral-latest","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9},"sourceProvider":"mistral"},"mistral/devstral-2512":{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/devstral-latest":{"id":"mistral/devstral-latest","name":"Devstral 2","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/devstral-medium-2507":{"id":"mistral/devstral-medium-2507","name":"Devstral Medium","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/devstral-medium-latest":{"id":"mistral/devstral-medium-latest","name":"Devstral 2 (latest)","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/devstral-small-2505":{"id":"mistral/devstral-small-2505","name":"Devstral Small 2505","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"sourceProvider":"mistral"},"mistral/devstral-small-2507":{"id":"mistral/devstral-small-2507","name":"Devstral Small","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.1,"output":0.3},"sourceProvider":"mistral"},"mistral/labs-devstral-small-2512":{"id":"mistral/labs-devstral-small-2512","name":"Devstral Small 2","description":"Legacy model retained for compatibility with older integrations","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"mistral"},"mistral/magistral-medium-latest":{"id":"mistral/magistral-medium-latest","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":2,"output":5},"sourceProvider":"mistral"},"mistral/magistral-small":{"id":"mistral/magistral-small","name":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"mistral"},"mistral/ministral-3b-latest":{"id":"mistral/ministral-3b-latest","name":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.04,"output":0.04},"sourceProvider":"mistral"},"mistral/ministral-8b-latest":{"id":"mistral/ministral-8b-latest","name":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.1,"output":0.1},"sourceProvider":"mistral"},"mistral/mistral-embed":{"id":"mistral/mistral-embed","name":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":3072},"cost":{"input":0.1,"output":0},"sourceProvider":"mistral"},"mistral/mistral-large-2411":{"id":"mistral/mistral-large-2411","name":"Mistral Large 2.1","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":2,"output":6},"sourceProvider":"mistral"},"mistral/mistral-large-2512":{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"mistral"},"mistral/mistral-large-latest":{"id":"mistral/mistral-large-latest","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"mistral"},"mistral/mistral-medium-2505":{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/mistral-medium-2508":{"id":"mistral/mistral-medium-2508","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"mistral"},"mistral/mistral-medium-2604":{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"mistral"},"mistral/mistral-medium-latest":{"id":"mistral/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"mistral"},"mistral/mistral-nemo":{"id":"mistral/mistral-nemo","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.15,"output":0.15},"sourceProvider":"mistral"},"mistral/mistral-small-2506":{"id":"mistral/mistral-small-2506","name":"Mistral Small 3.2","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"mistral"},"mistral/mistral-small-2603":{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"mistral"},"mistral/mistral-small-latest":{"id":"mistral/mistral-small-latest","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"mistral"},"mistral/open-mistral-7b":{"id":"mistral/open-mistral-7b","name":"Mistral 7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-09-27","last_updated":"2023-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"output":8000},"cost":{"input":0.25,"output":0.25},"sourceProvider":"mistral"},"mistral/open-mistral-nemo":{"id":"mistral/open-mistral-nemo","name":"Open Mistral Nemo","description":"Legacy model retained for compatibility with older integrations","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"status":"deprecated","cost":{"input":0.15,"output":0.15},"sourceProvider":"mistral"},"mistral/open-mixtral-8x22b":{"id":"mistral/open-mixtral-8x22b","name":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":64000},"cost":{"input":2,"output":6},"sourceProvider":"mistral"},"mistral/open-mixtral-8x7b":{"id":"mistral/open-mixtral-8x7b","name":"Mixtral 8x7B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-01","release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.7,"output":0.7},"sourceProvider":"mistral"},"mistral/pixtral-12b":{"id":"mistral/pixtral-12b","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.15,"output":0.15},"sourceProvider":"mistral"},"mistral/pixtral-large-latest":{"id":"mistral/pixtral-large-latest","name":"Pixtral Large (latest)","description":"Mistral's larger vision model for document-heavy image understanding and chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2024-11-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":6},"sourceProvider":"mistral"},"mistral/voxtral-mini-latest":{"id":"mistral/voxtral-mini-latest","name":"Voxtral Mini (latest)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"voxtral","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"mistral"},"mistral/voxtral-mini-tts-latest":{"id":"mistral/voxtral-mini-tts-latest","name":"Voxtral Mini TTS (latest)","description":"Multilingual text-to-speech model with zero-shot voice cloning","family":"voxtral","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"mistral"},"mistral/voxtral-small-latest":{"id":"mistral/voxtral-small-latest","name":"Voxtral Small (latest)","description":"Instruct model with native audio input for speech understanding and tool use","family":"voxtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-15","last_updated":"2025-07-15","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"mistral"},"mixlayer/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":3.2},"sourceProvider":"mixlayer"},"mixlayer/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":2.4},"sourceProvider":"mixlayer"},"mixlayer/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.3},"sourceProvider":"mixlayer"},"mixlayer/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3.6},"sourceProvider":"mixlayer"},"mixlayer/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.4},"sourceProvider":"mixlayer"},"moark/GLM-4.7":{"id":"moark/GLM-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":3.5,"output":14},"sourceProvider":"moark"},"moark/MiniMax-M2.1":{"id":"moark/MiniMax-M2.1","name":"MiniMax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":2.1,"output":8.4,"cache_read":2.1,"cache_write":8.4},"sourceProvider":"moark"},"modal/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"reasoning":15,"cache_read":0.3},"sourceProvider":"modal"},"modal/thinkingmachines/Inkling-NVFP4":{"id":"thinkingmachines/Inkling-NVFP4","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1.2,"output":5,"cache_read":0.27},"sourceProvider":"modal"},"model-oracle-ai/auto":{"id":"model-oracle-ai/auto","name":"Auto","description":"Model Oracle AI decision engine that selects and routes among configured coding-agent models","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-29","last_updated":"2026-07-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/claude-fable-5":{"id":"model-oracle-ai/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/claude-haiku-4.5":{"id":"model-oracle-ai/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/claude-opus-4.8":{"id":"model-oracle-ai/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/claude-sonnet-5":{"id":"model-oracle-ai/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/deepseek-v4-pro":{"id":"model-oracle-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/glm-5.2":{"id":"model-oracle-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-4.1":{"id":"model-oracle-ai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-4.1-mini":{"id":"model-oracle-ai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-5":{"id":"model-oracle-ai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-5.4":{"id":"model-oracle-ai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-5.4-mini":{"id":"model-oracle-ai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-5.4-nano":{"id":"model-oracle-ai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/gpt-5.5":{"id":"model-oracle-ai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"sourceProvider":"model-oracle-ai"},"model-oracle-ai/o4-mini":{"id":"model-oracle-ai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"sourceProvider":"model-oracle-ai"},"modelis/claude-fable-5":{"id":"modelis/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50},"sourceProvider":"modelis"},"modelis/claude-opus-4-8":{"id":"modelis/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]},{"type":"toggle"}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25},"sourceProvider":"modelis"},"modelis/claude-sonnet-4-6":{"id":"modelis/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"modelis"},"modelis/deepseek-v4-flash":{"id":"modelis/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.0983,"output":0.1966},"sourceProvider":"modelis"},"modelis/deepseek-v4-pro":{"id":"modelis/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87},"sourceProvider":"modelis"},"modelis/gemini-2.5-flash":{"id":"modelis/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","max"]},{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5},"sourceProvider":"modelis"},"modelis/gemini-2.5-pro":{"id":"modelis/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10},"sourceProvider":"modelis"},"modelis/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":3,"output":9},"sourceProvider":"modelis"},"modelis/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.768,"output":3.072},"sourceProvider":"modelis"},"modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/Qwen/Qwen3-30B-A3B-Thinking-2507":{"id":"Qwen/Qwen3-30B-A3B-Thinking-2507","name":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-30","last_updated":"2025-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/Qwen/Qwen3-Coder-30B-A3B-Instruct":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/ZhipuAI/GLM-4.5":{"id":"ZhipuAI/GLM-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"modelscope/ZhipuAI/GLM-4.6":{"id":"ZhipuAI/GLM-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":98304},"cost":{"input":0,"output":0},"sourceProvider":"modelscope"},"moonshotai-cn/kimi-k2-0711-preview":{"id":"moonshotai-cn/kimi-k2-0711-preview","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-14","last_updated":"2025-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2-0905-preview":{"id":"moonshotai-cn/kimi-k2-0905-preview","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2-thinking":{"id":"moonshotai-cn/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2-thinking-turbo":{"id":"moonshotai-cn/kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.15,"output":8,"cache_read":0.15},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2-turbo-preview":{"id":"moonshotai-cn/kimi-k2-turbo-preview","name":"Kimi K2 Turbo","description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.4,"output":10,"cache_read":0.6},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2.5":{"id":"moonshotai-cn/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2.6":{"id":"moonshotai-cn/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2.7-code":{"id":"moonshotai-cn/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k2.7-code-highspeed":{"id":"moonshotai-cn/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"moonshotai-cn"},"moonshotai-cn/kimi-k3":{"id":"moonshotai-cn/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"moonshotai-cn"},"moonshotai/kimi-k2-0711-preview":{"id":"moonshotai/kimi-k2-0711-preview","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-07-14","last_updated":"2025-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2-0905-preview":{"id":"moonshotai/kimi-k2-0905-preview","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2-thinking-turbo":{"id":"moonshotai/kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.15,"output":8,"cache_read":0.15},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2-turbo-preview":{"id":"moonshotai/kimi-k2-turbo-preview","name":"Kimi K2 Turbo","description":"Fast Kimi model for responsive chat, coding help, and agent loops","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":2.4,"output":10,"cache_read":0.6},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"moonshotai"},"moonshotai/kimi-k2.7-code-highspeed":{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code HighSpeed","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"moonshotai"},"moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"moonshotai"},"morph/auto":{"id":"morph/auto","name":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-06-01","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.85,"output":1.55},"sourceProvider":"morph"},"morph/morph-v3-fast":{"id":"morph/morph-v3-fast","name":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":0.8,"output":1.2},"sourceProvider":"morph"},"morph/morph-v3-large":{"id":"morph/morph-v3-large","name":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.9,"output":1.9},"sourceProvider":"morph"},"nano-gpt/abacusai/Dracarys-72B-Instruct":{"id":"abacusai/Dracarys-72B-Instruct","name":"Llama 3.1 70B Dracarys 2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/aion-labs/aion-2.0":{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.8,"output":1.6,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/aion-labs/aion-3.0":{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion 3.0","description":"Aion 3.0 is a GLM-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/aion-labs/aion-3.0-mini":{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion 3.0 Mini","description":"Aion 3.0 Mini is a DeepSeek-family collaborative generation model tuned for immersive roleplay and storytelling, with stronger narrative structure, tension, conflict, and nuanced mature themes.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"sourceProvider":"nano-gpt"},"nano-gpt/aion-labs/aion-rp-llama-3.1-8b":{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"Llama 3.1 8b (uncensored)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.8,"output":1.6,"cache_read":0.4},"sourceProvider":"nano-gpt"},"nano-gpt/alibaba/qwen3.6-27b":{"id":"alibaba/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.203,"output":2.24,"cache_read":0.1015},"sourceProvider":"nano-gpt"},"nano-gpt/alibaba/qwen3.6-27b:thinking":{"id":"alibaba/qwen3.6-27b:thinking","name":"Qwen3.6 27B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":131072}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.203,"output":2.24,"cache_read":0.1015},"sourceProvider":"nano-gpt"},"nano-gpt/alibaba/qwen3.6-flash":{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.19,"output":1.16,"cache_read":0.02,"cache_write":0.24},"sourceProvider":"nano-gpt"},"nano-gpt/amazon/nova-2-lite-v1":{"id":"amazon/nova-2-lite-v1","name":"Amazon Nova 2 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65535},"cost":{"input":0.51,"output":4.25,"cache_read":0.255},"sourceProvider":"nano-gpt"},"nano-gpt/amazon/nova-lite-v1":{"id":"amazon/nova-lite-v1","name":"Amazon Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"input":300000,"output":5120},"cost":{"input":0.0595,"output":0.238,"cache_read":0.02975},"sourceProvider":"nano-gpt"},"nano-gpt/amazon/nova-pro-v1":{"id":"amazon/nova-pro-v1","name":"Amazon Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"input":300000,"output":32000},"cost":{"input":0.799,"output":3.196,"cache_read":0.3995},"sourceProvider":"nano-gpt"},"nano-gpt/anthracite-org/magnum-v2-72b":{"id":"anthracite-org/magnum-v2-72b","name":"Magnum V2 72B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":2.006,"output":2.992,"cache_read":1.003},"sourceProvider":"nano-gpt"},"nano-gpt/anthracite-org/magnum-v4-72b":{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":2.006,"output":2.992,"cache_read":1.003},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-fable-latest":{"id":"anthropic/claude-fable-latest","name":"Claude Fable Latest","description":"Compatibility alias for Claude Fable.","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-haiku-latest":{"id":"anthropic/claude-haiku-latest","name":"Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude 4.6 Opus","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.6:thinking":{"id":"anthropic/claude-opus-4.6:thinking","name":"Claude 4.6 Opus Thinking","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.6:thinking:low":{"id":"anthropic/claude-opus-4.6:thinking:low","name":"Claude 4.6 Opus Thinking Low","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.6:thinking:max":{"id":"anthropic/claude-opus-4.6:thinking:max","name":"Claude 4.6 Opus Thinking Max","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.6:thinking:medium":{"id":"anthropic/claude-opus-4.6:thinking:medium","name":"Claude 4.6 Opus Thinking Medium","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude 4.7 Opus","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.7:thinking":{"id":"anthropic/claude-opus-4.7:thinking","name":"Claude 4.7 Opus Thinking","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-4.8:thinking":{"id":"anthropic/claude-opus-4.8:thinking","name":"Claude Opus 4.8 Thinking","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-opus-latest":{"id":"anthropic/claude-opus-latest","name":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-sonnet-4.6:thinking":{"id":"anthropic/claude-sonnet-4.6:thinking","name":"Claude Sonnet 4.6 Thinking","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-sonnet-5:thinking":{"id":"anthropic/claude-sonnet-5:thinking","name":"Claude Sonnet 5 Thinking","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/anthropic/claude-sonnet-latest":{"id":"anthropic/claude-sonnet-latest","name":"Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/arcee-ai/trinity-large-thinking":{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":80000},"cost":{"input":0.25,"output":0.9,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/asi1-mini":{"id":"nano-gpt/asi1-mini","name":"ASI1 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1,"output":1,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/auto-model":{"id":"nano-gpt/auto-model","name":"Auto model","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":0,"output":0},"sourceProvider":"nano-gpt"},"nano-gpt/auto-model-basic":{"id":"nano-gpt/auto-model-basic","name":"Auto model (Basic)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"sourceProvider":"nano-gpt"},"nano-gpt/auto-model-premium":{"id":"nano-gpt/auto-model-premium","name":"Auto model (Premium)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"sourceProvider":"nano-gpt"},"nano-gpt/auto-model-standard":{"id":"nano-gpt/auto-model-standard","name":"Auto model (Standard)","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-04-16","last_updated":"2024-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":9.996,"output":19.992,"cache_read":4.998},"sourceProvider":"nano-gpt"},"nano-gpt/azure-gpt-4-turbo":{"id":"nano-gpt/azure-gpt-4-turbo","name":"Azure gpt-4-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"nano-gpt"},"nano-gpt/azure-gpt-4o":{"id":"nano-gpt/azure-gpt-4o","name":"Azure gpt-4o","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/azure-gpt-4o-mini":{"id":"nano-gpt/azure-gpt-4o-mini","name":"Azure gpt-4o-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/azure-o1":{"id":"nano-gpt/azure-o1","name":"Azure o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"nano-gpt"},"nano-gpt/azure-o3-mini":{"id":"nano-gpt/azure-o3-mini","name":"Azure o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":65536},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/Baichuan-M2":{"id":"nano-gpt/Baichuan-M2","name":"Baichuan M2 32B Medical","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"baichuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":15.73,"output":15.73,"cache_read":7.865},"sourceProvider":"nano-gpt"},"nano-gpt/Baichuan4-Air":{"id":"nano-gpt/Baichuan4-Air","name":"Baichuan 4 Air","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"baichuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.157,"output":0.157,"cache_read":0.0785},"sourceProvider":"nano-gpt"},"nano-gpt/Baichuan4-Turbo":{"id":"nano-gpt/Baichuan4-Turbo","name":"Baichuan 4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"baichuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":2.42,"output":2.42,"cache_read":1.21},"sourceProvider":"nano-gpt"},"nano-gpt/baseten/Kimi-K2-Instruct-FP4":{"id":"baseten/Kimi-K2-Instruct-FP4","name":"Kimi K2 0711 Instruct FP4","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":131072},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/brave":{"id":"nano-gpt/brave","name":"Brave (Answers)","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-13","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":5,"output":5},"sourceProvider":"nano-gpt"},"nano-gpt/brave-pro":{"id":"nano-gpt/brave-pro","name":"Brave (Pro)","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-10","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":5,"output":5},"sourceProvider":"nano-gpt"},"nano-gpt/brave-research":{"id":"nano-gpt/brave-research","name":"Brave (Research)","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-10","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":5,"output":5},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance-seed/seed-2-1-turbo":{"id":"bytedance-seed/seed-2-1-turbo","name":"ByteDance Seed 2.1 Turbo","description":"ByteDance Seed 2.1 Turbo is a multimodal model for coding and long-horizon agent workflows, including end-to-end software delivery and multi-step task execution. It supports text, image, and video input with a 262k context window.","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance-seed/seed-2.0-code":{"id":"bytedance-seed/seed-2.0-code","name":"ByteDance Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.5,"output":3,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance-seed/seed-2.0-lite":{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.25,"output":2,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance/doubao-seed-2.1-pro":{"id":"bytedance/doubao-seed-2.1-pro","name":"Doubao Seed 2.1 Pro","description":"Higher-capability model in the Doubao Seed 2.1 family for agentic coding, long-context analysis, complex instruction following, and productivity workflows. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":1,"output":5,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance/doubao-seed-2.1-turbo":{"id":"bytedance/doubao-seed-2.1-turbo","name":"Doubao Seed 2.1 Turbo","description":"Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/bytedance/doubao-seed-character":{"id":"bytedance/doubao-seed-character","name":"Doubao Seed Character","description":"ByteDance's character-focused Doubao Seed model for roleplay, persona consistency, dialogue, and creative character interactions. It supports text and image input with a 128k context window. Requests route through ZenMux to ByteDance; ZenMux does not publish a model-API zero-retention or training guarantee, so avoid sensitive data.","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":false,"structured_output":false,"release_date":"2026-07-18","last_updated":"2026-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.1179,"output":0.2947,"cache_read":0.0236,"cache_write":0.0025},"sourceProvider":"nano-gpt"},"nano-gpt/celeris-1":{"id":"nano-gpt/celeris-1","name":"Celeris 1","description":"Celeris 1 is a diffusion language model built for ultra-low-latency classification, extraction, judging, query rewriting, and other short structured responses.","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-07-25","last_updated":"2026-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":2,"output":6,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/chutesai/Mistral-Small-3.2-24B-Instruct-2506":{"id":"chutesai/Mistral-Small-3.2-24B-Instruct-2506","name":"Mistral Small 3.2 24b Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"chutesai","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":131072},"cost":{"input":0.2,"output":0.4,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/claude-haiku-4-5-20251001":{"id":"nano-gpt/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/claude-haiku-4-5-20251001-thinking":{"id":"nano-gpt/claude-haiku-4-5-20251001-thinking","name":"Claude Haiku 4.5 Thinking","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-20250805":{"id":"nano-gpt/claude-opus-4-1-20250805","name":"Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-thinking":{"id":"nano-gpt/claude-opus-4-1-thinking","name":"Claude 4.1 Opus Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-thinking:1024":{"id":"nano-gpt/claude-opus-4-1-thinking:1024","name":"Claude 4.1 Opus Thinking (1K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-thinking:32000":{"id":"nano-gpt/claude-opus-4-1-thinking:32000","name":"Claude 4.1 Opus Thinking (32K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-thinking:32768":{"id":"nano-gpt/claude-opus-4-1-thinking:32768","name":"Claude 4.1 Opus Thinking (32K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-1-thinking:8192":{"id":"nano-gpt/claude-opus-4-1-thinking:8192","name":"Claude 4.1 Opus Thinking (8K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-20250514":{"id":"nano-gpt/claude-opus-4-20250514","name":"Claude 4 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-5-20251101":{"id":"nano-gpt/claude-opus-4-5-20251101","name":"Claude 4.5 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-5-20251101:thinking":{"id":"nano-gpt/claude-opus-4-5-20251101:thinking","name":"Claude 4.5 Opus Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-thinking":{"id":"nano-gpt/claude-opus-4-thinking","name":"Claude 4 Opus Thinking","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-thinking:1024":{"id":"nano-gpt/claude-opus-4-thinking:1024","name":"Claude 4 Opus Thinking (1K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-thinking:32000":{"id":"nano-gpt/claude-opus-4-thinking:32000","name":"Claude 4 Opus Thinking (32K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-thinking:32768":{"id":"nano-gpt/claude-opus-4-thinking:32768","name":"Claude 4 Opus Thinking (32K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-opus-4-thinking:8192":{"id":"nano-gpt/claude-opus-4-thinking:8192","name":"Claude 4 Opus Thinking (8K)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-20250514":{"id":"nano-gpt/claude-sonnet-4-20250514","name":"Claude 4 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-5-20250929":{"id":"nano-gpt/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-5-20250929-thinking":{"id":"nano-gpt/claude-sonnet-4-5-20250929-thinking","name":"Claude Sonnet 4.5 Thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-thinking":{"id":"nano-gpt/claude-sonnet-4-thinking","name":"Claude 4 Sonnet Thinking","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-thinking:1024":{"id":"nano-gpt/claude-sonnet-4-thinking:1024","name":"Claude 4 Sonnet Thinking (1K)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-thinking:32768":{"id":"nano-gpt/claude-sonnet-4-thinking:32768","name":"Claude 4 Sonnet Thinking (32K)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-thinking:64000":{"id":"nano-gpt/claude-sonnet-4-thinking:64000","name":"Claude 4 Sonnet Thinking (64K)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claude-sonnet-4-thinking:8192":{"id":"nano-gpt/claude-sonnet-4-thinking:8192","name":"Claude 4 Sonnet Thinking (8K)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/claw-high":{"id":"nano-gpt/claw-high","name":"Claw High","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/claw-low":{"id":"nano-gpt/claw-low","name":"Claw Low","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"nano-gpt"},"nano-gpt/claw-medium":{"id":"nano-gpt/claw-medium","name":"Claw Medium","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.315,"output":1.26,"cache_read":0.1575},"sourceProvider":"nano-gpt"},"nano-gpt/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":2.856,"output":14.246,"cache_read":1.428},"sourceProvider":"nano-gpt"},"nano-gpt/cohere/north-mini-code":{"id":"cohere/north-mini-code","name":"Cohere North Mini Code 1.0","description":"Cohere coding model for practical software engineering and agentic edits","family":"north","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-23","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":64000},"cost":{"input":0.2,"output":0.8,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/command-a-plus-05-2026":{"id":"nano-gpt/command-a-plus-05-2026","name":"Cohere Command A+ (05/2026)","description":"Cohere's stronger command model for multilingual agents and enterprise workflows","family":"command-a","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-04-01","release_date":"2026-05-20","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":64000},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/command-a-reasoning-08-2025":{"id":"nano-gpt/command-a-reasoning-08-2025","name":"Cohere Command A (08/2025)","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/crofai/greg-2-super":{"id":"crofai/greg-2-super","name":"Greg 2 Super","description":"Greg 2 Super is CrofAI's balanced Greg 2 model for strong UI design, frontend iteration, coding, writing, and everyday agent tasks at a lower cost than Ultra.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-06-19","last_updated":"2026-06-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"input":229376,"output":229376},"cost":{"input":1.5,"output":5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/crofai/greg-2-ultra":{"id":"crofai/greg-2-ultra","name":"Greg 2 Ultra","description":"Greg 2 Ultra is CrofAI's most capable Greg 2 model, tuned for premium UI design, agentic coding, creative writing, and higher-end general reasoning tasks.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-06-19","last_updated":"2026-06-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":229376,"input":229376,"output":229376},"cost":{"input":3,"output":10,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/deepclaude":{"id":"nano-gpt/deepclaude","name":"DeepClaude","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-10","last_updated":"2025-02-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/deepcogito/cogito-v1-preview-qwen-32B":{"id":"deepcogito/cogito-v1-preview-qwen-32B","name":"Cogito v1 Preview Qwen 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-05-10","last_updated":"2025-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":1.8,"output":1.8,"cache_read":0.9},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":163840},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.7,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.25,"output":0.7,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/DeepSeek-V3.1-Terminus:thinking":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus:thinking","name":"DeepSeek V3.1 Terminus (Thinking)","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.25,"output":0.7,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/DeepSeek-V3.1:thinking":{"id":"deepseek-ai/DeepSeek-V3.1:thinking","name":"DeepSeek V3.1 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.7,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/deepseek-v3.2-exp":{"id":"deepseek-ai/deepseek-v3.2-exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"input":163840,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-ai/deepseek-v3.2-exp-thinking":{"id":"deepseek-ai/deepseek-v3.2-exp-thinking","name":"DeepSeek V3.2 Exp Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"input":163840,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-chat":{"id":"nano-gpt/deepseek-chat","name":"DeepSeek V3/Deepseek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.1,"output":0.425,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-chat-cheaper":{"id":"nano-gpt/deepseek-chat-cheaper","name":"DeepSeek V3/Chat Cheaper","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.1,"output":0.425,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-r1":{"id":"nano-gpt/deepseek-r1","name":"DeepSeek R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-r1-sambanova":{"id":"nano-gpt/deepseek-r1-sambanova","name":"DeepSeek R1 Fast","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":4.998,"output":6.987,"cache_read":2.499},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-reasoner":{"id":"nano-gpt/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"input":64000,"output":65536},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-reasoner-cheaper":{"id":"nano-gpt/deepseek-reasoner-cheaper","name":"Deepseek R1 Cheaper","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.4,"output":1.7,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek-v3-0324":{"id":"nano-gpt/deepseek-v3-0324","name":"DeepSeek Chat 0324","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2,"output":0.77,"cache_read":0.135},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-latest":{"id":"deepseek/deepseek-latest","name":"DeepSeek Latest","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":1.1,"output":2.5,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-prover-v2-671b":{"id":"deepseek/deepseek-prover-v2-671b","name":"DeepSeek Prover v2 671B","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-11-15","last_updated":"2025-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"input":160000,"output":16384},"cost":{"input":1,"output":2.5,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163000,"input":163000,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v3.2:thinking":{"id":"deepseek/deepseek-v3.2:thinking","name":"DeepSeek V3.2 Thinking","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":163000,"input":163000,"output":65536},"cost":{"input":0.28,"output":0.42,"cache_read":0.14},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.014},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash-0731:thinking":{"id":"deepseek/deepseek-v4-flash-0731:thinking","name":"DeepSeek V4 Flash 0731 (Thinking)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.014},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash-latest":{"id":"deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"Compatibility alias that routes to the newest dated DeepSeek V4 Flash release. Currently routes to DeepSeek V4 Flash 0731. ⚠️ This route goes directly to DeepSeek, so privacy and logging guarantees are limited.","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-02","last_updated":"2026-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.014},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-flash:thinking":{"id":"deepseek/deepseek-v4-flash:thinking","name":"DeepSeek V4 Flash (Thinking)","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":1.1,"output":2.5,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-pro-0813:thinking":{"id":"deepseek/deepseek-v4-pro-0813:thinking","name":"DeepSeek V4 Pro 0813 Thinking","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":1.1,"output":2.5,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/deepseek/deepseek-v4-pro:thinking":{"id":"deepseek/deepseek-v4-pro:thinking","name":"DeepSeek V4 Pro (Thinking)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":384000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/dmind/dmind-1-mini":{"id":"dmind/dmind-1-mini","name":"DMind-1-Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.2,"output":0.4,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/Doctor-Shotgun/MS3.2-24B-Magnum-Diamond":{"id":"Doctor-Shotgun/MS3.2-24B-Magnum-Diamond","name":"MS3.2 24B Magnum Diamond","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":32768},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/dots-studio/dots-3-note-preview":{"id":"dots-studio/dots-3-note-preview","name":"Dots3-Note Preview","description":"Dots Studio's open-weight multimodal Mixture-of-Experts model activates 16B of 280B parameters for long-context reasoning, coding, visual and document understanding, tool use, and long-horizon agent workflows. Prompts and completions of this model may be logged.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-15","last_updated":"2026-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":393216,"input":393216,"output":393216},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-1.5-pro-256k":{"id":"nano-gpt/doubao-1.5-pro-256k","name":"Doubao 1.5 Pro 256k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":16384},"cost":{"input":0.799,"output":1.445,"cache_read":0.3995},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-1.5-pro-32k":{"id":"nano-gpt/doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-11-20","last_updated":"2025-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.1343,"output":0.3349,"cache_read":0.06715},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-1.5-vision-pro-32k":{"id":"nano-gpt/doubao-1.5-vision-pro-32k","name":"Doubao 1.5 Vision Pro 32k","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-11-20","last_updated":"2025-01-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.459,"output":1.377,"cache_read":0.2295},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-1-6-250615":{"id":"nano-gpt/doubao-seed-1-6-250615","name":"Doubao Seed 1.6","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":16384},"cost":{"input":0.204,"output":0.51,"cache_read":0.102},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-1-6-flash-250615":{"id":"nano-gpt/doubao-seed-1-6-flash-250615","name":"Doubao Seed 1.6 Flash","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":16384},"cost":{"input":0.0374,"output":0.374,"cache_read":0.0187},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-2-0-code-preview-260215":{"id":"nano-gpt/doubao-seed-2-0-code-preview-260215","name":"Doubao Seed 2.0 Code Preview","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.782,"output":3.893,"cache_read":0.391},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-2-0-lite-260215":{"id":"nano-gpt/doubao-seed-2-0-lite-260215","name":"Doubao Seed 2.0 Lite","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32000},"cost":{"input":0.1462,"output":0.8738,"cache_read":0.0731},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-2-0-mini-260215":{"id":"nano-gpt/doubao-seed-2-0-mini-260215","name":"Doubao Seed 2.0 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32000},"cost":{"input":0.0493,"output":0.4845,"cache_read":0.02465},"sourceProvider":"nano-gpt"},"nano-gpt/doubao-seed-2-0-pro-260215":{"id":"nano-gpt/doubao-seed-2-0-pro-260215","name":"Doubao Seed 2.0 Pro","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":128000},"cost":{"input":0.782,"output":3.876,"cache_read":0.391},"sourceProvider":"nano-gpt"},"nano-gpt/Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B":{"id":"Envoid/Llama-3.05-Nemotron-Tenyxchat-Storybreaker-70B","name":"Nemotron Tenyxchat Storybreaker 70b","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B":{"id":"Envoid/Llama-3.05-NT-Storybreaker-Ministral-70B","name":"Llama 3.05 Storybreaker Ministral 70b","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/ernie-5.0-thinking-preview":{"id":"nano-gpt/ernie-5.0-thinking-preview","name":"Ernie 5.0 Thinking Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1,"output":3.5,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/ernie-5.1":{"id":"nano-gpt/ernie-5.1","name":"ERNIE 5.1","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-05-10","last_updated":"2026-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":119000,"input":119000,"output":64000},"cost":{"input":0.75,"output":3,"cache_read":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/ernie-5.1:thinking":{"id":"nano-gpt/ernie-5.1:thinking","name":"ERNIE 5.1 Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2026-05-10","last_updated":"2026-05-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":119000,"input":119000,"output":64000},"cost":{"input":0.75,"output":3,"cache_read":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/ernie-x1.1-preview":{"id":"nano-gpt/ernie-x1.1-preview","name":"ERNIE X1.1","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"ernie","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-10","last_updated":"2025-09-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"input":64000,"output":8192},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0":{"id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0","name":"EVA Llama 3.33 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":2.006,"output":2.006,"cache_read":1.003},"sourceProvider":"nano-gpt"},"nano-gpt/EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1":{"id":"EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1","name":"EVA-LLaMA-3.33-70B-v0.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":2.006,"output":2.006,"cache_read":1.003},"sourceProvider":"nano-gpt"},"nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2":{"id":"EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2","name":"EVA-Qwen2.5-32B-v0.2","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.799,"output":0.799,"cache_read":0.3995},"sourceProvider":"nano-gpt"},"nano-gpt/EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2":{"id":"EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2","name":"EVA-Qwen2.5-72B-v0.2","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.799,"output":0.799,"cache_read":0.3995},"sourceProvider":"nano-gpt"},"nano-gpt/exa-answer":{"id":"nano-gpt/exa-answer","name":"Exa (Answer)","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-23","last_updated":"2025-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"input":4096,"output":4096},"cost":{"input":2.5,"output":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5":{"id":"failspy/Meta-Llama-3-70B-Instruct-abliterated-v3.5","name":"Llama 3 70B abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/fastgpt":{"id":"nano-gpt/fastgpt","name":"Web Answer","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-23","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":7.5,"output":7.5},"sourceProvider":"nano-gpt"},"nano-gpt/featherless-ai/Qwerky-72B":{"id":"featherless-ai/Qwerky-72B","name":"Qwerky 72B","description":"General-purpose chat model for instruction following, writing, and analysis","family":"qwerky","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/GalrionSoftworks/MN-LooseCannon-12B-v1":{"id":"GalrionSoftworks/MN-LooseCannon-12B-v1","name":"MN-LooseCannon-12B-v1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.0-pro-exp-02-05":{"id":"nano-gpt/gemini-2.0-pro-exp-02-05","name":"Gemini 2.0 Pro 0205","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2097152,"input":2097152,"output":8192},"cost":{"input":1.989,"output":7.956,"cache_read":0.49725},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.0-pro-reasoner":{"id":"nano-gpt/gemini-2.0-pro-reasoner","name":"Gemini 2.0 Pro Reasoner","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-02-05","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":1.292,"output":4.998,"cache_read":0.323},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash":{"id":"nano-gpt/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-lite":{"id":"nano-gpt/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-lite-preview-06-17":{"id":"nano-gpt/gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash Lite Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-lite-preview-09-2025":{"id":"nano-gpt/gemini-2.5-flash-lite-preview-09-2025","name":"Gemini 2.5 Flash Lite Preview (09/2025)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-lite-preview-09-2025-thinking":{"id":"nano-gpt/gemini-2.5-flash-lite-preview-09-2025-thinking","name":"Gemini 2.5 Flash Lite Preview (09/2025) – Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-nothinking":{"id":"nano-gpt/gemini-2.5-flash-nothinking","name":"Gemini 2.5 Flash (No Thinking)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-04-17":{"id":"nano-gpt/gemini-2.5-flash-preview-04-17","name":"Gemini 2.5 Flash Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-04-17","last_updated":"2025-04-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-04-17:thinking":{"id":"nano-gpt/gemini-2.5-flash-preview-04-17:thinking","name":"Gemini 2.5 Flash Preview Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-04-17","last_updated":"2025-04-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.15,"output":3.5,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-05-20":{"id":"nano-gpt/gemini-2.5-flash-preview-05-20","name":"Gemini 2.5 Flash 0520","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"input":1048000,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-05-20:thinking":{"id":"nano-gpt/gemini-2.5-flash-preview-05-20:thinking","name":"Gemini 2.5 Flash 0520 Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"input":1048000,"output":65536},"cost":{"input":0.15,"output":3.5,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-09-2025":{"id":"nano-gpt/gemini-2.5-flash-preview-09-2025","name":"Gemini 2.5 Flash Preview (09/2025)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-flash-preview-09-2025-thinking":{"id":"nano-gpt/gemini-2.5-flash-preview-09-2025-thinking","name":"Gemini 2.5 Flash Preview (09/2025) – Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-pro":{"id":"nano-gpt/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-pro-exp-03-25":{"id":"nano-gpt/gemini-2.5-pro-exp-03-25","name":"Gemini 2.5 Pro Experimental 0325","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-pro-preview-03-25":{"id":"nano-gpt/gemini-2.5-pro-preview-03-25","name":"Gemini 2.5 Pro Preview 0325","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-pro-preview-05-06":{"id":"nano-gpt/gemini-2.5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 0506","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-05-06","last_updated":"2025-05-06","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-2.5-pro-preview-06-05":{"id":"nano-gpt/gemini-2.5-pro-preview-06-05","name":"Gemini 2.5 Pro Preview 0605","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2.5,"output":10,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-3-pro-image-preview":{"id":"nano-gpt/gemini-3-pro-image-preview","name":"Gemini 3 Pro Image","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/gemini-exp-1206":{"id":"nano-gpt/gemini-exp-1206","name":"Gemini 2.0 Pro 1206","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":2097152,"input":2097152,"output":8192},"cost":{"input":1.258,"output":4.998,"cache_read":0.629},"sourceProvider":"nano-gpt"},"nano-gpt/gemma-4-12b-it":{"id":"nano-gpt/gemma-4-12b-it","name":"Gemma 4 12B Instruct","description":"Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-08-01","last_updated":"2026-08-01","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.06,"output":0.3,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled":{"id":"nano-gpt/Gemma-4-31B-Claude-4.6-Opus-Reasoning-Distilled","name":"Gemma 4 31B Claude 4.6 Opus Reasoning Distilled","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"claude","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.0306},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-Cognitive-Unshackled":{"id":"nano-gpt/Gemma-4-31B-Cognitive-Unshackled","name":"Gemma 4 31B Cognitive Unshackled","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-DarkIdol":{"id":"nano-gpt/Gemma-4-31B-DarkIdol","name":"Gemma 4 31B DarkIdol","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-GarnetV2":{"id":"nano-gpt/Gemma-4-31B-GarnetV2","name":"Gemma 4 31B Garnet V2","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-MeroMero-v2":{"id":"nano-gpt/Gemma-4-31B-MeroMero-v2","name":"Gemma 4 31B MeroMero v2","description":"Gemma 4 31B MeroMero v2 is a LoRA finetune for emotive dialogue, relationship scenes, creative writing, and multimodal roleplay.","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-08-23","last_updated":"2026-08-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":32768},"cost":{"input":0.08,"output":0.33,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/Gemma-4-31B-Queen":{"id":"nano-gpt/Gemma-4-31B-Queen","name":"Gemma 4 31B Queen","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-01","last_updated":"2026-05-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/gemma-4-e2b-it":{"id":"nano-gpt/gemma-4-e2b-it","name":"Gemma 4 E2B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.02,"output":0.1,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/gemma-4-e4b-it":{"id":"nano-gpt/gemma-4-e4b-it","name":"Gemma 4 E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.04,"output":0.2,"cache_read":0.02},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4":{"id":"nano-gpt/glm-4","name":"GLM-4","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":14.994,"output":14.994,"cache_read":7.497},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-air":{"id":"nano-gpt/glm-4-air","name":"GLM-4 Air","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-air-0111":{"id":"nano-gpt/glm-4-air-0111","name":"GLM 4 Air 0111","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-01-11","last_updated":"2025-01-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":0.1394,"output":0.1394,"cache_read":0.0697},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-airx":{"id":"nano-gpt/glm-4-airx","name":"GLM-4 AirX","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"input":8000,"output":4096},"cost":{"input":2.006,"output":2.006,"cache_read":1.003},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-flash":{"id":"nano-gpt/glm-4-flash","name":"GLM-4 Flash","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":0.1003,"output":0.1003,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-long":{"id":"nano-gpt/glm-4-long","name":"GLM-4 Long","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":4096},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-plus":{"id":"nano-gpt/glm-4-plus","name":"GLM-4 Plus","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-09-20","last_updated":"2024-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":7.497,"output":7.497,"cache_read":3.7485},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4-plus-0111":{"id":"nano-gpt/glm-4-plus-0111","name":"GLM 4 Plus 0111","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":9.996,"output":9.996,"cache_read":4.998},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4.1v-thinking-flash":{"id":"nano-gpt/glm-4.1v-thinking-flash","name":"GLM 4.1V Thinking Flash","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"input":64000,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/glm-4.1v-thinking-flashx":{"id":"nano-gpt/glm-4.1v-thinking-flashx","name":"GLM 4.1V Thinking FlashX","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"input":64000,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/GLM-4.6-Derestricted-v5":{"id":"nano-gpt/GLM-4.6-Derestricted-v5","name":"GLM 4.6 Derestricted v5","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.4,"output":1.5,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/glm-z1-air":{"id":"nano-gpt/glm-z1-air","name":"GLM Z1 Air","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":16384},"cost":{"input":0.07,"output":0.07,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/glm-z1-airx":{"id":"nano-gpt/glm-z1-airx","name":"GLM Z1 AirX","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/glm-zero-preview":{"id":"nano-gpt/glm-zero-preview","name":"GLM Zero Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-12-20","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"input":8000,"output":4096},"cost":{"input":1.802,"output":1.802,"cache_read":0.901},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash (Preview)","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3-flash-preview-thinking":{"id":"google/gemini-3-flash-preview-thinking","name":"Gemini 3 Flash Thinking","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro (Preview)","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro (Preview Custom Tools)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.1-pro-preview-high":{"id":"google/gemini-3.1-pro-preview-high","name":"Gemini 3.1 Pro (Preview High)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-21","last_updated":"2026-02-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.1-pro-preview-low":{"id":"google/gemini-3.1-pro-preview-low","name":"Gemini 3.1 Pro (Preview Low)","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-21","last_updated":"2026-02-21","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.5-flash-thinking":{"id":"google/gemini-3.5-flash-thinking","name":"Gemini 3.5 Flash Thinking","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.041667},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.020833},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-flash-latest":{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"cache_read":0.0375,"cache_write":0.020833},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-flash-lite-latest":{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemini-pro-latest":{"id":"google/gemini-pro-latest","name":"Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.08,"output":0.33,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemma-4-26b-a4b-it:thinking":{"id":"google/gemma-4-26b-a4b-it:thinking","name":"Gemma 4 26B A4B Thinking","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.13,"output":0.4,"cache_read":0.065},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemma-4-26b-a4b-uncensored":{"id":"google/gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored","description":"Gemma 4 26B A4B Uncensored is an NVFP4 open-weight multimodal mixture-of-experts model tuned for fewer refusals across chat, coding, tool use, and long-context work.","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-08-22","last_updated":"2026-08-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.08,"output":0.33,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.08,"output":0.33,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/google/gemma-4-31b-it:thinking":{"id":"google/gemma-4-31b-it:thinking","name":"Gemma 4 31B Thinking","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.1,"output":0.35,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/Gryphe/MythoMax-L2-13b":{"id":"Gryphe/MythoMax-L2-13b","name":"MythoMax 13B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4000,"input":4000,"output":4096},"cost":{"input":0.1003,"output":0.1003,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/hermes-high":{"id":"nano-gpt/hermes-high","name":"Hermes High","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/hermes-low":{"id":"nano-gpt/hermes-low","name":"Hermes Low","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.08333},"sourceProvider":"nano-gpt"},"nano-gpt/hermes-medium":{"id":"nano-gpt/hermes-medium","name":"Hermes Medium","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.315,"output":1.26,"cache_read":0.1575},"sourceProvider":"nano-gpt"},"nano-gpt/holo3-35b-a3b":{"id":"nano-gpt/holo3-35b-a3b","name":"Holo3-35B-A3B","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":0.25,"output":1.8,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/holo3-35b-a3b:thinking":{"id":"nano-gpt/holo3-35b-a3b:thinking","name":"Holo3-35B-A3B Thinking","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":0.25,"output":1.8,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated":{"id":"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","name":"DeepSeek R1 Llama 70B Abliterated","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated":{"id":"huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated","name":"DeepSeek R1 Qwen Abliterated","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":1.4,"output":1.4,"cache_read":0.7},"sourceProvider":"nano-gpt"},"nano-gpt/huihui-ai/Llama-3.3-70B-Instruct-abliterated":{"id":"huihui-ai/Llama-3.3-70B-Instruct-abliterated","name":"Llama 3.3 70B Instruct abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/huihui-ai/Qwen2.5-32B-Instruct-abliterated":{"id":"huihui-ai/Qwen2.5-32B-Instruct-abliterated","name":"Qwen 2.5 32B Abliterated","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-01-06","last_updated":"2025-01-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/hunyuan-turbos-20250226":{"id":"nano-gpt/hunyuan-turbos-20250226","name":"Hunyuan Turbo S","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"hunyuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":24000,"input":24000,"output":8192},"cost":{"input":0.187,"output":0.374,"cache_read":0.0935},"sourceProvider":"nano-gpt"},"nano-gpt/ibm-granite/granite-4.1-8b":{"id":"ibm-granite/granite-4.1-8b","name":"Granite 4.1 8B","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.05,"output":0.1,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/inclusionai/ling-2.6-1t":{"id":"inclusionai/ling-2.6-1t","name":"Ling 2.6 1T","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/inclusionai/ling-2.6-flash":{"id":"inclusionai/ling-2.6-flash","name":"Ling 2.6 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"nano-gpt"},"nano-gpt/inclusionai/ling-3.0-flash":{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","description":"Ling-3.0-flash is a 124B-parameter Mixture-of-Experts model with approximately 5.1B parameters active per token. It prioritizes token efficiency and production-scale agentic inference, helping coding and tool-using agents complete more work within constrained latency and serving budgets.","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/inclusionai/ling-3.0-flash:thinking":{"id":"inclusionai/ling-3.0-flash:thinking","name":"Ling 3.0 Flash Thinking","description":"Ling-3.0-flash Thinking enables visible reasoning on inclusionAI's token-efficient 124B-parameter Mixture-of-Experts model for harder coding, tool use, planning, and production-scale agent workflows.","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.075,"output":0.22,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/inclusionai/ring-2.6-1t":{"id":"inclusionai/ring-2.6-1t","name":"Ring 2.6 1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/inflatebot/MN-12B-Mag-Mell-R1":{"id":"inflatebot/MN-12B-Mag-Mell-R1","name":"Mag Mell R1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/inflection/inflection-3-pi":{"id":"inflection/inflection-3-pi","name":"Inflection 3 Pi","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-11-21","last_updated":"2024-10-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"input":8000,"output":4096},"cost":{"input":2.499,"output":9.996,"cache_read":1.2495},"sourceProvider":"nano-gpt"},"nano-gpt/inflection/inflection-3-productivity":{"id":"inflection/inflection-3-productivity","name":"Inflection 3 Productivity","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-11-21","last_updated":"2024-10-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"input":8000,"output":4096},"cost":{"input":2.499,"output":9.996,"cache_read":1.2495},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-large":{"id":"nano-gpt/jamba-large","name":"Jamba Large","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":1.989,"output":7.99,"cache_read":0.9945},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-large-1.6":{"id":"nano-gpt/jamba-large-1.6","name":"Jamba Large 1.6","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":1.989,"output":7.99,"cache_read":0.9945},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-large-1.7":{"id":"nano-gpt/jamba-large-1.7","name":"Jamba Large 1.7","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":1.989,"output":7.99,"cache_read":0.9945},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-mini":{"id":"nano-gpt/jamba-mini","name":"Jamba Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":0.1989,"output":0.408,"cache_read":0.09945},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-mini-1.6":{"id":"nano-gpt/jamba-mini-1.6","name":"Jamba Mini 1.6","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":0.1989,"output":0.408,"cache_read":0.09945},"sourceProvider":"nano-gpt"},"nano-gpt/jamba-mini-1.7":{"id":"nano-gpt/jamba-mini-1.7","name":"Jamba Mini 1.7","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"jamba","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":4096},"cost":{"input":0.1989,"output":0.408,"cache_read":0.09945},"sourceProvider":"nano-gpt"},"nano-gpt/kimi-k2-instruct-fast":{"id":"nano-gpt/kimi-k2-instruct-fast","name":"Kimi K2 0711 Fast","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-12-15","last_updated":"2025-07-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/kwaipilot/kat-coder-air-v2.5":{"id":"kwaipilot/kat-coder-air-v2.5","name":"KAT Coder Air V2.5","description":"Fast, cost-efficient KAT Coder model for code generation, editing, debugging, and agentic software-development workflows.","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-07-14","last_updated":"2026-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":80000},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/kwaipilot/kat-coder-pro-v2":{"id":"kwaipilot/kat-coder-pro-v2","name":"KAT Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-28","last_updated":"2026-03-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/kwaipilot/kat-coder-pro-v2.5":{"id":"kwaipilot/kat-coder-pro-v2.5","name":"KAT Coder Pro V2.5","description":"Higher-capability KAT Coder model for complex code generation, repository-scale editing, debugging, and agentic software-development workflows.","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-07-14","last_updated":"2026-07-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":80000},"cost":{"input":0.74,"output":2.96,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/LatitudeGames/Wayfarer-Large-70B-Llama-3.3":{"id":"LatitudeGames/Wayfarer-Large-70B-Llama-3.3","name":"Llama 3.3 70B Wayfarer","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/learnlm-1.5-pro-experimental":{"id":"nano-gpt/learnlm-1.5-pro-experimental","name":"Gemini LearnLM Experimental","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-05-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32767,"input":32767,"output":8192},"cost":{"input":3.502,"output":10.506,"cache_read":1.751},"sourceProvider":"nano-gpt"},"nano-gpt/liquid/lfm-2.5-2.6b":{"id":"liquid/lfm-2.5-2.6b","name":"LFM2.5 2.6B","description":"Liquid AI's compact 2.6B reasoning model for agent workflows, data extraction, RAG, and long-context processing. It supports tool calling and structured output, but Liquid advises against using it for agentic coding. Warning: prompts and responses may be logged and used for model training or service improvement; do not send sensitive data.","family":"liquid","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/LLM360/K2-Think":{"id":"LLM360/K2-Think","name":"K2-Think","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"sourceProvider":"nano-gpt"},"nano-gpt/longcat-2.0":{"id":"nano-gpt/longcat-2.0","name":"LongCat 2.0","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":262144},"cost":{"input":0.75,"output":3,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/longcat-2.0:thinking":{"id":"nano-gpt/longcat-2.0:thinking","name":"LongCat 2.0 Thinking","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048756,"input":1048756,"output":262144},"cost":{"input":0.75,"output":3,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/MarinaraSpaghetti/NemoMix-Unleashed-12B":{"id":"MarinaraSpaghetti/NemoMix-Unleashed-12B","name":"NemoMix 12B Unleashed","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/meganova-ai/manta-flash-1.0":{"id":"meganova-ai/manta-flash-1.0","name":"Manta Flash 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.02,"output":0.16,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/meganova-ai/manta-mini-1.0":{"id":"meganova-ai/manta-mini-1.0","name":"Manta Mini 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.02,"output":0.16,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/meganova-ai/manta-pro-1.0":{"id":"meganova-ai/manta-pro-1.0","name":"Manta Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-20","last_updated":"2025-12-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.06,"output":0.5,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/mercury-2":{"id":"nano-gpt/mercury-2","name":"Mercury 2","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/mercury-coder-small":{"id":"nano-gpt/mercury-coder-small","name":"Mercury Coder Small","description":"Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.","family":"mercury","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":16384},"cost":{"input":0.25,"output":1,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8":{"id":"nano-gpt/Meta-Llama-3-1-8B-Instruct-FP8","name":"Llama 3.1 8B (decentralized)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.02,"output":0.03,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/meta-llama/llama-3.1-8b-instruct":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama 3.1 8b Instruct","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.0544,"output":0.085,"cache_read":0.0272},"sourceProvider":"nano-gpt"},"nano-gpt/meta-llama/llama-3.2-3b-instruct":{"id":"meta-llama/llama-3.2-3b-instruct","name":"Llama 3.2 3b Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-09-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.0306,"output":0.0493,"cache_read":0.0153},"sourceProvider":"nano-gpt"},"nano-gpt/meta-llama/llama-3.3-70b-instruct":{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama 3.3 70b Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.05,"output":0.23,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/meta-llama/llama-4-maverick":{"id":"meta-llama/llama-4-maverick","name":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":65536},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/meta-llama/llama-4-scout":{"id":"meta-llama/llama-4-scout","name":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":328000,"input":328000,"output":65536},"cost":{"input":0.085,"output":0.46,"cache_read":0.0425},"sourceProvider":"nano-gpt"},"nano-gpt/meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor (Data Used for Training)","description":"A much cheaper opt-in version of Muse Spark 1.2 with the same multimodal coding and agentic capabilities. Prompts and outputs sent to this Contributor model may be used by Meta for training and to improve its products; use the standard Muse Spark 1.2 model if you do not want your data used for training.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"nano-gpt"},"nano-gpt/microsoft/wizardlm-2-8x22b":{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/MiniMax-M1":{"id":"nano-gpt/MiniMax-M1","name":"MiniMax M1","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"minimax","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-01-08","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.1394,"output":1.3328,"cache_read":0.0697},"sourceProvider":"nano-gpt"},"nano-gpt/MiniMax-M2":{"id":"nano-gpt/MiniMax-M2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.17,"output":1.53,"cache_read":0.085},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-01":{"id":"minimax/minimax-01","name":"MiniMax 01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-15","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000192,"input":1000192,"output":16384},"cost":{"input":0.1394,"output":1.122,"cache_read":0.0697},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-latest":{"id":"minimax/minimax-latest","name":"MiniMax Latest","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m2-her":{"id":"minimax/minimax-m2-her","name":"MiniMax M2-her","description":"MiniMax M2 variant tuned for conversational and character-driven agent interactions","family":"minimax","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65532,"input":65532,"output":2048},"cost":{"input":0.302,"output":1.207,"cache_read":0.151},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.33,"output":1.32,"cache_read":0.165},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.315,"output":1.26,"cache_read":0.1575},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m2.7-turbo":{"id":"minimax/minimax-m2.7-turbo","name":"MiniMax M2.7 Turbo","description":"Efficient MiniMax model for quick assistance, coding, and routine automation","family":"minimax-m2.7","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"input":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/minimax/minimax-m3:thinking":{"id":"minimax/minimax-m3:thinking","name":"MiniMax M3 Thinking","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"input":512000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/MiniMaxAI/MiniMax-M1-80k":{"id":"MiniMaxAI/MiniMax-M1-80k","name":"MiniMax M1 80K","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-01-08","last_updated":"2025-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.6052,"output":2.4225,"cache_read":0.3026},"sourceProvider":"nano-gpt"},"nano-gpt/mistral-code-agent-latest":{"id":"nano-gpt/mistral-code-agent-latest","name":"Mistral Code Agent Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistral-code-latest":{"id":"nano-gpt/mistral-code-latest","name":"Mistral Code Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/mistral-small-31-24b-instruct":{"id":"nano-gpt/mistral-small-31-24b-instruct","name":"Mistral Small 31 24b Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":131072},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/mistral/mistral-medium-3.5":{"id":"mistral/mistral-medium-3.5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.5,"output":7.5,"cache_read":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/mistral/mistral-medium-3.5:thinking":{"id":"mistral/mistral-medium-3.5:thinking","name":"Mistral Medium 3.5 Thinking","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.5,"output":7.5,"cache_read":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/codestral-2508":{"id":"mistralai/codestral-2508","name":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-01","last_updated":"2025-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/devstral-2-123b-instruct-2512":{"id":"mistralai/devstral-2-123b-instruct-2512","name":"Devstral 2 123B","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/Devstral-Small-2505":{"id":"mistralai/Devstral-Small-2505","name":"Mistral Devstral Small 2505","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-02","last_updated":"2025-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.06,"output":0.06,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/ministral-14b-2512":{"id":"mistralai/ministral-14b-2512","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/ministral-14b-instruct-2512":{"id":"mistralai/ministral-14b-instruct-2512","name":"Ministral 3 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/ministral-3b-2512":{"id":"mistralai/ministral-3b-2512","name":"Ministral 3B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/ministral-8b-2512":{"id":"mistralai/ministral-8b-2512","name":"Ministral 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-large":{"id":"mistralai/mistral-large","name":"Mistral Large 2411","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":256000},"cost":{"input":2.006,"output":6.001,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-large-3-675b-instruct-2512":{"id":"mistralai/mistral-large-3-675b-instruct-2512","name":"Mistral Large 3 675B","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-25","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":256000},"cost":{"input":1,"output":3,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-medium-3":{"id":"mistralai/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-medium-3.1":{"id":"mistralai/mistral-medium-3.1","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.4,"output":2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/Mistral-Nemo-Instruct-2407":{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-saba":{"id":"mistralai/mistral-saba","name":"Mistral Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":32768},"cost":{"input":0.1989,"output":0.595,"cache_read":0.09945},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-small-4-119b-2603":{"id":"mistralai/mistral-small-4-119b-2603","name":"Mistral Small 4 119B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mistral-small-4-119b-2603:thinking":{"id":"mistralai/mistral-small-4-119b-2603:thinking","name":"Mistral Small 4 119B Thinking","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.4,"output":1.4,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mistralai/mixtral-8x22b-instruct-v0.1":{"id":"mistralai/mixtral-8x22b-instruct-v0.1","name":"Mixtral 8x22B","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mixtral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/mlabonne/NeuralDaredevil-8B-abliterated":{"id":"mlabonne/NeuralDaredevil-8B-abliterated","name":"Neural Daredevil 8B abliterated","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.44,"output":0.44,"cache_read":0.22},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2-instruct":{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2-instruct-0711":{"id":"moonshotai/kimi-k2-instruct-0711","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/Kimi-K2-Instruct-0905":{"id":"moonshotai/Kimi-K2-Instruct-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":262144},"cost":{"input":0.4,"output":1.8,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":98304},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.3,"output":1.9,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.5:thinking":{"id":"moonshotai/kimi-k2.5:thinking","name":"Kimi K2.5 Thinking","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.3,"output":1.9,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.5,"output":2.6,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.6:thinking":{"id":"moonshotai/kimi-k2.6:thinking","name":"Kimi K2.6 Thinking","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.5,"output":2.6,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k2.7-code-highspeed":{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code High-Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":1.9,"output":8,"cache_read":0.32},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":1048576},"cost":{"input":2.5,"output":13.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/moonshotai/kimi-latest":{"id":"moonshotai/kimi-latest","name":"Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":1048576},"cost":{"input":2.5,"output":13.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/nano-gpt-help":{"id":"nano-gpt/nano-gpt-help","name":"NanoGPT Help","description":"Text-only NanoGPT support assistant. Questions are processed by the Help inference provider; do not paste secrets or account credentials. Covers the website, models, API, pricing, memory, media generation, and support.","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-06-06","last_updated":"2026-06-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":6000,"input":6000,"output":512},"cost":{"input":0,"output":0},"sourceProvider":"nano-gpt"},"nano-gpt/nanogpt/coding-router":{"id":"nanogpt/coding-router","name":"Coding Router","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/nanogpt/coding-router:high":{"id":"nanogpt/coding-router:high","name":"Coding Router High","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":1.1,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/nanogpt/coding-router:low":{"id":"nanogpt/coding-router:low","name":"Coding Router Low","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"nano-gpt"},"nano-gpt/nanogpt/coding-router:max":{"id":"nanogpt/coding-router:max","name":"Coding Router Max","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/nanogpt/coding-router:medium":{"id":"nanogpt/coding-router:medium","name":"Coding Router Medium","description":"Automatic model router for matching prompts to suitable backends and budgets","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"nano-gpt"},"nano-gpt/NeverSleep/Lumimaid-v0.2-70B":{"id":"NeverSleep/Lumimaid-v0.2-70B","name":"Lumimaid v0.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":1,"output":1.5,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/nex-agi/nex-n2-mini":{"id":"nex-agi/nex-n2-mini","name":"Nex N2 Mini","description":"Nex AGI's open-source agentic mixture-of-experts model in the Nex N2 family. It accepts text and image input and is built for coding, tool use, structured outputs, and optional reasoning with a 256K context window.","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-06-24","last_updated":"2026-06-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.025,"output":0.1,"cache_read":0.0025},"sourceProvider":"nano-gpt"},"nano-gpt/nex-agi/nex-n2-pro":{"id":"nex-agi/nex-n2-pro","name":"Nex N2 Pro","description":"Nex AGI's open-source agentic reasoning model, post-trained on Qwen3.5-397B-A17B. It is built for agentic coding, software engineering, deep research, tool use, and long-horizon tasks with a 256K context window.","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/nothingiisreal/L3.1-70B-Celeste-V0.1-BF16":{"id":"nothingiisreal/L3.1-70B-Celeste-V0.1-BF16","name":"Llama 3.1 70B Celeste v0.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/NousResearch/hermes-3-llama-3.1-70b":{"id":"NousResearch/hermes-3-llama-3.1-70b","name":"Hermes 3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-01-07","last_updated":"2026-01-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.408,"output":0.408,"cache_read":0.204},"sourceProvider":"nano-gpt"},"nano-gpt/NousResearch/hermes-4-405b":{"id":"NousResearch/hermes-4-405b","name":"Hermes 4 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/NousResearch/hermes-4-405b:thinking":{"id":"NousResearch/hermes-4-405b:thinking","name":"Hermes 4 Large (Thinking)","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/NousResearch/hermes-4-70b":{"id":"NousResearch/hermes-4-70b","name":"Hermes 4 Medium","description":"General-purpose chat model for instruction following, writing, and analysis","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-03","last_updated":"2025-07-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2006,"output":0.3995,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/NousResearch/Hermes-4-70B:thinking":{"id":"NousResearch/Hermes-4-70B:thinking","name":"Hermes 4 (Thinking)","description":"General-purpose chat model for instruction following, writing, and analysis","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-17","last_updated":"2025-09-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2006,"output":0.3995,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF":{"id":"nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","name":"Nvidia Nemotron 70b","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.357,"output":0.408,"cache_read":0.1785},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/Llama-3.3-Nemotron-Super-49B-v1":{"id":"nvidia/Llama-3.3-Nemotron-Super-49B-v1","name":"Nvidia Nemotron Super 49B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-08","last_updated":"2025-08-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.15,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nvidia Nemotron 3 Nano 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":262144},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nvidia Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.105,"output":0.42,"cache_read":0.0525},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nvidia Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-super-120b-a12b:thinking":{"id":"nvidia/nemotron-3-super-120b-a12b:thinking","name":"Nvidia Nemotron 3 Super 120B Thinking","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.05,"output":0.25,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nvidia Nemotron 3 Ultra 550B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3-ultra-550b-a55b:thinking":{"id":"nvidia/nemotron-3-ultra-550b-a55b:thinking","name":"Nvidia Nemotron 3 Ultra 550B Thinking","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3.5-lightning":{"id":"nvidia/nemotron-3.5-lightning","name":"Nvidia Nemotron 3.5 Lightning","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/nvidia/nemotron-3.5-lightning:thinking":{"id":"nvidia/nemotron-3.5-lightning:thinking","name":"Nvidia Nemotron 3.5 Lightning Thinking","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":0.05,"output":0.2,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"input":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4-turbo-preview":{"id":"openai/gpt-4-turbo-preview","name":"GPT-4 Turbo Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT 4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT 4.1 Mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT 4.1 Nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o-mini-search-preview":{"id":"openai/gpt-4o-mini-search-preview","name":"GPT-4o mini Search Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-10","last_updated":"2024-07-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-4o-search-preview":{"id":"openai/gpt-4o-search-preview","name":"GPT-4o Search Preview","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-10","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT 5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT 5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT 5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT 5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":15,"output":120,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT 5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.1-2025-11-13":{"id":"openai/gpt-5.1-2025-11-13","name":"GPT-5.1 (2025-11-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":32768},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT 5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT 5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT 5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT 5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":922000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT 5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.1,"output":0.6,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-luna-pro":{"id":"openai/gpt-5.6-luna-pro","name":"GPT 5.6 Luna Pro","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":0.1,"output":0.6,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT 5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-sol-pro":{"id":"openai/gpt-5.6-sol-pro","name":"GPT 5.6 Sol Pro","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT 5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-5.6-terra-pro":{"id":"openai/gpt-5.6-terra-pro","name":"GPT 5.6 Terra Pro","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-chat-latest":{"id":"openai/gpt-chat-latest","name":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-latest":{"id":"openai/gpt-latest","name":"GPT Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-29","last_updated":"2026-03-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.35,"output":0.75},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.2,"output":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2026-02-23","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.075,"output":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o1":{"id":"openai/o1","name":"OpenAI o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o1-preview":{"id":"openai/o1-preview","name":"OpenAI o1-preview","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":32768},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o1-pro":{"id":"openai/o1-pro","name":"OpenAI o1 Pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":150,"output":600,"cache_read":75},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3":{"id":"openai/o3","name":"OpenAI o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3-deep-research":{"id":"openai/o3-deep-research","name":"OpenAI o3 Deep Research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05","release_date":"2024-06-26","last_updated":"2024-06-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":11,"output":44,"cache_read":5.5},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3-mini":{"id":"openai/o3-mini","name":"OpenAI o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3-mini-high":{"id":"openai/o3-mini-high","name":"OpenAI o3-mini (High)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-01-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3-mini-low":{"id":"openai/o3-mini-low","name":"OpenAI o3-mini (Low)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-01-31","last_updated":"2025-01-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o3-pro-2025-06-10":{"id":"openai/o3-pro-2025-06-10","name":"OpenAI o3-pro (2025-06-10)","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2024-01-01","last_updated":"2025-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":22,"output":88,"cache_read":11},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o4-mini":{"id":"openai/o4-mini","name":"OpenAI o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o4-mini-deep-research":{"id":"openai/o4-mini-deep-research","name":"OpenAI o4-mini Deep Research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-05","release_date":"2024-06-26","last_updated":"2024-06-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":2.2,"output":8.8,"cache_read":1.1},"sourceProvider":"nano-gpt"},"nano-gpt/openai/o4-mini-high":{"id":"openai/o4-mini-high","name":"OpenAI o4-mini high","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-12-04","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nano-gpt"},"nano-gpt/ornith-ai/ornith-1.5-35b-a3b":{"id":"ornith-ai/ornith-1.5-35b-a3b","name":"Ornith 1.5 35B","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, tool use, image understanding, and long-context work. This variant disables thinking for faster direct responses.","family":"ornith","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/ornith-ai/ornith-1.5-35b-a3b:thinking":{"id":"ornith-ai/ornith-1.5-35b-a3b:thinking","name":"Ornith 1.5 35B Thinking","description":"Ornith 1.5 35B A3B is an open-weight mixture-of-experts model for agentic coding, reasoning, tool use, image understanding, and long-context work. This variant enables thinking by default.","family":"ornith","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/ornith-ai/ornith-1.5-9b":{"id":"ornith-ai/ornith-1.5-9b","name":"Ornith 1.5 9B","description":"Ornith 1.5 9B is an FP8 dense open-weight reasoning model built for agentic coding, tool use, visual understanding, and efficient long-context work.","family":"ornith","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-23","last_updated":"2026-08-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.05,"output":0.1,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/pamanseau/OpenReasoning-Nemotron-32B":{"id":"pamanseau/OpenReasoning-Nemotron-32B","name":"OpenReasoning Nemotron 32B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/perceptron/perceptron-mk1":{"id":"perceptron/perceptron-mk1","name":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.15,"output":1.5,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/perplexity-academic-researcher":{"id":"nano-gpt/perplexity-academic-researcher","name":"Perplexity Academic Researcher","description":"Sonar Reasoning Pro with Perplexity's academic search mode. Prioritizes scholarly and peer-reviewed sources from academic repositories and returns cited research synthesis.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"input":127000,"output":128000},"cost":{"input":2,"output":8,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/phi-4-mini-instruct":{"id":"nano-gpt/phi-4-mini-instruct","name":"Phi 4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.17,"output":0.68,"cache_read":0.085},"sourceProvider":"nano-gpt"},"nano-gpt/phi-4-multimodal-instruct":{"id":"nano-gpt/phi-4-multimodal-instruct","name":"Phi 4 Multimodal","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.07,"output":0.11,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/pokee-isaac":{"id":"nano-gpt/pokee-isaac","name":"Pokee-Isaac 28B","description":"Pokee-Isaac is a 28B agentic model with a roughly 10-million-token context window, function calling, and OpenAI-compatible structured output. Pokee bills in $0.01 increments, rounding each non-zero request up to the next cent.","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-04","last_updated":"2026-08-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":10000000,"input":10000000,"output":60000},"cost":{"input":0.15,"output":1,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/poolside/laguna-m.1":{"id":"poolside/laguna-m.1","name":"Laguna M.1","description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.2,"output":0.4,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/poolside/laguna-s-2.1:thinking":{"id":"poolside/laguna-s-2.1:thinking","name":"Laguna S 2.1 Thinking","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"sourceProvider":"nano-gpt"},"nano-gpt/qvq-max":{"id":"nano-gpt/qvq-max","name":"Qwen: QvQ Max","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-28","last_updated":"2025-03-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":1.2,"output":4.8,"cache_read":0.6},"sourceProvider":"nano-gpt"},"nano-gpt/qwen-3.6-plus":{"id":"nano-gpt/qwen-3.6-plus","name":"Qwen 3.6 Plus","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.6","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.325,"output":1.95,"cache_read":0.0325,"cache_write":0.40625},"sourceProvider":"nano-gpt"},"nano-gpt/qwen-long":{"id":"nano-gpt/qwen-long","name":"Qwen Long 10M","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-08-01","last_updated":"2025-01-25","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":10000000,"input":10000000,"output":8192},"cost":{"input":0.1003,"output":0.408,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/qwen-max":{"id":"nano-gpt/qwen-max","name":"Qwen 2.5 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":1.5997,"output":6.392,"cache_read":0.79985},"sourceProvider":"nano-gpt"},"nano-gpt/qwen-plus":{"id":"nano-gpt/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":995904,"input":995904,"output":32768},"cost":{"input":0.3995,"output":1.2002,"cache_read":0.19975},"sourceProvider":"nano-gpt"},"nano-gpt/qwen-turbo":{"id":"nano-gpt/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":8192},"cost":{"input":0.04998,"output":0.2006,"cache_read":0.02499},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen-2.5-72b-instruct":{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-07-03","last_updated":"2025-07-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.357,"output":0.408,"cache_read":0.1785},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen2.5-Coder-32B-Instruct":{"id":"qwen/Qwen2.5-Coder-32B-Instruct","name":"Qwen 2.5 Coder 32b","description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-14b":{"id":"qwen/qwen3-14b","name":"Qwen 3 14b","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.08,"output":0.24,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-235b-a22b":{"id":"qwen/qwen3-235b-a22b","name":"Qwen 3 235b A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen 3 235b A22B 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":262144},"cost":{"input":0.13,"output":0.5,"cache_read":0.065},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen 3 235b A22B 2507 Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2025-09-11","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":262144},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-30b-a3b":{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-32b":{"id":"qwen/qwen3-32b","name":"Qwen 3 32b","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3-8B":{"id":"qwen/Qwen3-8B","name":"Qwen 3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":41000,"input":41000,"output":32768},"cost":{"input":0.47,"output":0.47,"cache_read":0.235},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-coder":{"id":"qwen/qwen3-coder","name":"Qwen 3 Coder 480B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"input":262000,"output":65536},"cost":{"input":0.13,"output":0.5,"cache_read":0.065},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.5,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.2,"output":1.5,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":1,"output":5,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.2002,"output":6.001,"cache_read":0.6001},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3-Next-80B-A3B-Instruct":{"id":"qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen3 Next 80B A3B (Instruct)","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":262144},"cost":{"input":0.15,"output":0.65,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.15,"output":0.65,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3-VL-235B-A22B-Instruct":{"id":"qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":262144},"cost":{"input":0.3,"output":1.2,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":258048,"input":258048,"output":65536},"cost":{"input":0.6,"output":3.6,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.5-397b-a17b-thinking":{"id":"qwen/qwen3.5-397b-a17b-thinking","name":"Qwen3.5 397B A17B Thinking","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":258048,"input":258048,"output":65536},"cost":{"input":0.6,"output":3.6,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65536},"cost":{"input":0.05,"output":0.15,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.5-plus":{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.5-plus-thinking":{"id":"qwen/qwen3.5-plus-thinking","name":"Qwen3.5 Plus Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3.6-35B-A3B":{"id":"qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.112,"output":0.8,"cache_read":0.056},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.6-35b-a3b-uncensored":{"id":"qwen/qwen3.6-35b-a3b-uncensored","name":"Qwen 3.6 35B A3B Uncensored","description":"Qwen 3.6 35B A3B Uncensored is an FP8 open-weight mixture-of-experts model tuned for fewer refusals across chat, coding, tool use, and multimodal tasks.","family":"qwen3.6","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":32768},"cost":{"input":0.15,"output":0.5,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/Qwen3.6-35B-A3B:thinking":{"id":"qwen/Qwen3.6-35B-A3B:thinking","name":"Qwen3.6 35B A3B Thinking","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.112,"output":0.8,"cache_read":0.056},"sourceProvider":"nano-gpt"},"nano-gpt/qwen/qwen3.8-27b-uncensored":{"id":"qwen/qwen3.8-27b-uncensored","name":"Qwen 3.8 27B Uncensored","description":"Qwen 3.8 27B Uncensored is an FP8 open-weight multimodal model tuned for fewer refusals across chat, coding, tool use, and long-context work.","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.18,"output":0.5,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/qwen25-vl-72b-instruct":{"id":"nano-gpt/qwen25-vl-72b-instruct","name":"Qwen25 VL 72b","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-05-10","last_updated":"2025-05-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":32768},"cost":{"input":0.69989,"output":0.69989,"cache_read":0.349945},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3-30b-a3b-instruct-2507":{"id":"nano-gpt/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.2,"output":0.5,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3-coder-30b-a3b-instruct":{"id":"nano-gpt/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30B A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3-max-2026-01-23":{"id":"nano-gpt/qwen3-max-2026-01-23","name":"Qwen3 Max 2026-01-23","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-01-26","last_updated":"2026-01-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":1.2002,"output":6.001,"cache_read":0.6001},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3-vl-235b-a22b-instruct-original":{"id":"nano-gpt/qwen3-vl-235b-a22b-instruct-original","name":"Qwen3 VL 235B A22B Instruct Original","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.5,"output":1.2,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3-vl-235b-a22b-thinking":{"id":"nano-gpt/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.5,"output":6,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-0.8b":{"id":"nano-gpt/qwen3.5-0.8b","name":"Qwen3.5 0.8B","description":"Qwen3.5 0.8B is a lightweight open-weight multimodal model from Alibaba for fast reasoning, visual understanding, tool use, and JSON output.","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-16","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.06,"output":0.12,"cache_read":0.03},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-122b-a10b":{"id":"nano-gpt/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.437,"output":3.496,"cache_read":0.103788},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-122b-a10b:thinking":{"id":"nano-gpt/qwen3.5-122b-a10b:thinking","name":"Qwen3.5 122B A10B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0.437,"output":3.496,"cache_read":0.103788},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-27b":{"id":"nano-gpt/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.27,"output":2.16,"cache_read":0.135},"sourceProvider":"nano-gpt"},"nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted":{"id":"nano-gpt/Qwen3.5-27B-BlueStar-v3-Derestricted","name":"Qwen3.5 27B BlueStar v3 Derestricted","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/Qwen3.5-27B-Queen-Derestricted":{"id":"nano-gpt/Qwen3.5-27B-Queen-Derestricted","name":"Qwen3.5 27B Queen Derestricted","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":16384},"cost":{"input":0.306,"output":0.306,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-27b:thinking":{"id":"nano-gpt/qwen3.5-27b:thinking","name":"Qwen3.5 27B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.27,"output":2.16,"cache_read":0.135},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-2b":{"id":"nano-gpt/qwen3.5-2b","name":"Qwen3.5 2B","description":"Qwen3.5 2B is a small open-weight multimodal model from Alibaba for efficient reasoning, coding, visual understanding, tool use, and JSON output.","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-16","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.08,"output":0.16,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-35b-a3b":{"id":"nano-gpt/qwen3.5-35b-a3b","name":"Qwen3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.225,"output":1.8,"cache_read":0.1125},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-35b-a3b:thinking":{"id":"nano-gpt/qwen3.5-35b-a3b:thinking","name":"Qwen3.5 35B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":260096,"input":260096,"output":65536},"cost":{"input":0.225,"output":1.8,"cache_read":0.1125},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-4b":{"id":"nano-gpt/qwen3.5-4b","name":"Qwen3.5 4B","description":"Qwen3.5 4B is a compact open-weight multimodal model from Alibaba for reasoning, coding, visual understanding, tool use, and structured output.","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-08-16","last_updated":"2026-08-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.1,"output":0.2,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-flash":{"id":"nano-gpt/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-flash:thinking":{"id":"nano-gpt/qwen3.5-flash:thinking","name":"Qwen3.5 Flash Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024,"max":81920}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-omni-flash":{"id":"nano-gpt/qwen3.5-omni-flash","name":"Qwen3.5 Omni Flash","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"qwen3.5","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":49152,"input":49152,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.5-omni-plus":{"id":"nano-gpt/qwen3.5-omni-plus","name":"Qwen3.5 Omni Plus","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"qwen3.5","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.6-max-preview":{"id":"nano-gpt/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":245760,"input":245760,"output":65536},"cost":{"input":1.04,"output":6.24,"cache_read":0.52},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-flash":{"id":"nano-gpt/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-flash:thinking":{"id":"nano-gpt/qwen3.7-flash:thinking","name":"Qwen3.7 Flash Thinking","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-max":{"id":"nano-gpt/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-max:thinking":{"id":"nano-gpt/qwen3.7-max:thinking","name":"Qwen3.7 Max Thinking","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-plus":{"id":"nano-gpt/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":991808,"input":991808,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.7-plus:thinking":{"id":"nano-gpt/qwen3.7-plus:thinking","name":"Qwen3.7 Plus Thinking","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":983616,"input":983616,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.8-27b":{"id":"nano-gpt/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.2,"output":1.4,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.8-27b:thinking":{"id":"nano-gpt/qwen3.8-27b:thinking","name":"Qwen3.8 27B Thinking","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":32768},"cost":{"input":0.2,"output":1.4,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.8-max":{"id":"nano-gpt/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"input":991000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/qwen3.8-max:thinking":{"id":"nano-gpt/qwen3.8-max:thinking","name":"Qwen3.8 Max Thinking","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"input":991000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"nano-gpt"},"nano-gpt/ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0":{"id":"ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0","name":"Omega Directive 24B Unslop v2.0","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":32768},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":16384},"cost":{"input":5.25,"output":31.5,"cache_read":0.525},"sourceProvider":"nano-gpt"},"nano-gpt/sakana/fugu-ultra-v1.1":{"id":"sakana/fugu-ultra-v1.1","name":"Fugu Ultra v1.1","description":"Sakana AI's upgraded Fugu Ultra release with stronger coding, agentic task execution, and advanced reasoning through dynamic orchestration of frontier models.","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":16384},"cost":{"input":5.25,"output":31.5,"cache_read":0.525},"sourceProvider":"nano-gpt"},"nano-gpt/Salesforce/Llama-xLAM-2-70b-fc-r":{"id":"Salesforce/Llama-xLAM-2-70b-fc-r","name":"Llama-xLAM-2 70B fc-r","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-04-13","last_updated":"2025-04-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":2.5,"output":2.5,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/Sao10K/L3-8B-Stheno-v3.2":{"id":"Sao10K/L3-8B-Stheno-v3.2","name":"Sao10K Stheno 8b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-11-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/Sao10K/L3.1-70B-Euryale-v2.2":{"id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Llama 3.1 70B Euryale","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":20480,"input":20480,"output":16384},"cost":{"input":0.306,"output":0.357,"cache_read":0.153},"sourceProvider":"nano-gpt"},"nano-gpt/Sao10K/L3.1-70B-Hanami-x1":{"id":"Sao10K/L3.1-70B-Hanami-x1","name":"Llama 3.1 70B Hanami","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/Sao10K/L3.3-70B-Euryale-v2.3":{"id":"Sao10K/L3.3-70B-Euryale-v2.3","name":"Llama 3.3 70B Euryale","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":20480,"input":20480,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/sarvam-105b":{"id":"nano-gpt/sarvam-105b","name":"Sarvam 105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":4096},"cost":{"input":0.045,"output":0.177,"cache_read":0.028},"sourceProvider":"nano-gpt"},"nano-gpt/sarvam-30b":{"id":"nano-gpt/sarvam-30b","name":"Sarvam 30B","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":4096},"cost":{"input":0.028,"output":0.111,"cache_read":0.017},"sourceProvider":"nano-gpt"},"nano-gpt/shisa-ai/shisa-v2-llama3.3-70b":{"id":"shisa-ai/shisa-v2-llama3.3-70b","name":"Shisa V2 Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/shisa-ai/shisa-v2.1-llama3.3-70b":{"id":"shisa-ai/shisa-v2.1-llama3.3-70b","name":"Shisa V2.1 Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":4096},"cost":{"input":0.5,"output":0.5,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/sonar":{"id":"nano-gpt/sonar","name":"Perplexity Simple","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"input":127000,"output":128000},"cost":{"input":1,"output":1,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/sonar-deep-research":{"id":"nano-gpt/sonar-deep-research","name":"Perplexity Deep Research","description":"Sonar search model for autonomous research and citation-backed long-form reports","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":60000,"input":60000,"output":128000},"cost":{"input":3.4,"output":13.6,"cache_read":1.7},"sourceProvider":"nano-gpt"},"nano-gpt/sonar-pro":{"id":"nano-gpt/sonar-pro","name":"Perplexity Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":3,"output":15,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/sonar-reasoning-pro":{"id":"nano-gpt/sonar-reasoning-pro","name":"Perplexity Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"input":127000,"output":128000},"cost":{"input":2,"output":8,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/soob3123/amoral-gemma3-27B-v2":{"id":"soob3123/amoral-gemma3-27B-v2","name":"Amoral Gemma3 27B v2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-05-23","last_updated":"2025-05-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/soob3123/GrayLine-Qwen3-8B":{"id":"soob3123/GrayLine-Qwen3-8B","name":"Grayline Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":32768},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/soob3123/Veiled-Calla-12B":{"id":"soob3123/Veiled-Calla-12B","name":"Veiled Calla 12B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-04-13","last_updated":"2025-04-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":8192},"cost":{"input":0.3,"output":0.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/stealth/ox-alpha":{"id":"stealth/ox-alpha","name":"Ox Alpha","description":"Ox Alpha is an experimental stealth model with long-context reasoning, vision, tool calling, and structured output support. Prompts and responses are logged and retained by the provider.","family":"alpha","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":32768},"cost":{"input":0.05,"output":0.05,"cache_read":0.025},"sourceProvider":"nano-gpt"},"nano-gpt/Steelskull/L3.3-Cu-Mai-R1-70b":{"id":"Steelskull/L3.3-Cu-Mai-R1-70b","name":"Llama 3.3 70B Cu Mai","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/Steelskull/L3.3-Electra-R1-70b":{"id":"Steelskull/L3.3-Electra-R1-70b","name":"Steelskull Electra R1 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.69989,"output":0.69989,"cache_read":0.349945},"sourceProvider":"nano-gpt"},"nano-gpt/Steelskull/L3.3-MS-Evayale-70B":{"id":"Steelskull/L3.3-MS-Evayale-70B","name":"Evayale 70b ","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/Steelskull/L3.3-MS-Nevoria-70b":{"id":"Steelskull/L3.3-MS-Nevoria-70b","name":"Steelskull Nevoria 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/Steelskull/L3.3-Nevoria-R1-70b":{"id":"Steelskull/L3.3-Nevoria-R1-70b","name":"Steelskull Nevoria R1 70b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":16384},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/step-r1-v-mini":{"id":"nano-gpt/step-r1-v-mini","name":"Step R1 V Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"step","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":2.5,"output":11,"cache_read":1.25},"sourceProvider":"nano-gpt"},"nano-gpt/stepfun-ai/step-3.5-flash":{"id":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/stepfun-ai/step-3.5-flash-2603":{"id":"stepfun-ai/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/stepfun/step-3.7-flash:thinking":{"id":"stepfun/step-3.7-flash:thinking","name":"Step 3.7 Flash Thinking","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/deepseek-v3.2":{"id":"TEE/deepseek-v3.2","name":"DeepSeek V3.2 TEE","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"input":164000,"output":65536},"cost":{"input":0.5,"output":1,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/deepseek-v4-flash":{"id":"TEE/deepseek-v4-flash","name":"DeepSeek V4 Flash TEE","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":1048576},"cost":{"input":0.2,"output":0.4,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gemma-3-27b-it":{"id":"TEE/gemma-3-27b-it","name":"Gemma 3 27B TEE","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.2,"output":0.8,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gemma-4-26b-a4b-uncensored":{"id":"TEE/gemma-4-26b-a4b-uncensored","name":"Gemma 4 26B A4B Uncensored TEE","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-05-23","last_updated":"2026-05-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":65536},"cost":{"input":0.15,"output":0.7,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gemma-4-31b-it":{"id":"TEE/gemma-4-31b-it","name":"Gemma 4 31B IT TEE","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.15,"output":0.46,"cache_read":0.075},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gemma4-31b":{"id":"TEE/gemma4-31b","name":"Gemma 4 31B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-04","last_updated":"2026-04-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.4,"output":1,"cache_read":0.4},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gemma4-31b:thinking":{"id":"TEE/gemma4-31b:thinking","name":"Gemma 4 31B Thinking TEE","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-05-02","last_updated":"2026-05-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":131072},"cost":{"input":0.4,"output":1,"cache_read":0.4},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/glm-4.7":{"id":"TEE/glm-4.7","name":"GLM 4.7 TEE","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"input":131000,"output":65535},"cost":{"input":0.85,"output":3.3,"cache_read":0.425},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/glm-5.1":{"id":"TEE/glm-5.1","name":"GLM 5.1 TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"input":202752,"output":65535},"cost":{"input":1.5,"output":5.25,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/glm-5.1-thinking":{"id":"TEE/glm-5.1-thinking","name":"GLM 5.1 Thinking TEE","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"input":202752,"output":65535},"cost":{"input":1.5,"output":5.25,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/glm-5.2":{"id":"TEE/glm-5.2","name":"GLM 5.2 TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.6,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/glm-5.2:thinking":{"id":"TEE/glm-5.2:thinking","name":"GLM 5.2 Thinking TEE","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.6,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gpt-oss-120b":{"id":"TEE/gpt-oss-120b","name":"GPT-OSS 120B TEE","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":2,"output":2,"cache_read":2},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/gpt-oss-20b":{"id":"TEE/gpt-oss-20b","name":"GPT-OSS 20B TEE","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":8192},"cost":{"input":0.2,"output":0.8,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/kimi-k2.6":{"id":"TEE/kimi-k2.6","name":"Kimi K2.6 TEE","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":1.5,"output":5.25,"cache_read":0.375},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/kimi-k2.7-code":{"id":"TEE/kimi-k2.7-code","name":"Kimi K2.7 Code TEE","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/kimi-k3":{"id":"TEE/kimi-k3","name":"Kimi K3 TEE","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":1.5},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/llama3-3-70b":{"id":"TEE/llama3-3-70b","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-03","last_updated":"2025-07-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":1.75,"output":2.75,"cache_read":1.75},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/muse-glimmer-30b":{"id":"TEE/muse-glimmer-30b","name":"Muse Glimmer 30B TEE","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen2.5-vl-72b-instruct":{"id":"TEE/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":8192},"cost":{"input":0.7,"output":0.7,"cache_read":0.35},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.5-122b-a10b":{"id":"TEE/qwen3.5-122b-a10b","name":"Qwen3.5 122B A10B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.46,"output":3.68,"cache_read":0.23},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.5-27b":{"id":"TEE/qwen3.5-27b","name":"Qwen3.5 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.3,"output":2.4,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.5-397b-a17b":{"id":"TEE/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B TEE","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.55,"output":3.5,"cache_read":0.275},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.6-27b":{"id":"TEE/qwen3.6-27b","name":"Qwen3.6 27B TEE","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":65536},"cost":{"input":0.32,"output":2.7,"cache_read":0.16},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.6-35b-a3b":{"id":"TEE/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B TEE","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.2,"output":1.27,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/TEE/qwen3.6-35b-a3b-uncensored":{"id":"TEE/qwen3.6-35b-a3b-uncensored","name":"Qwen3.6 35B A3B Uncensored TEE","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":131072}],"tool_call":true,"structured_output":true,"release_date":"2026-05-23","last_updated":"2026-05-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.3,"output":1.5,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/tencent/Hunyuan-MT-7B":{"id":"tencent/Hunyuan-MT-7B","name":"Hunyuan MT 7B","description":"Translation model for multilingual conversion, localization, and cross-language workflows","family":"hunyuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-15","last_updated":"2025-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":10,"output":20,"cache_read":5},"sourceProvider":"nano-gpt"},"nano-gpt/tencent/hy3":{"id":"tencent/hy3","name":"Tencent Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.066,"output":0.26,"cache_read":0.029},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Anubis-70B-v1":{"id":"TheDrummer/Anubis-70B-v1","name":"Anubis 70B v1","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":65536,"output":16384},"cost":{"input":0.31,"output":0.31,"cache_read":0.155},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Anubis-70B-v1.1":{"id":"TheDrummer/Anubis-70B-v1.1","name":"Anubis 70B v1.1","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":16384},"cost":{"input":0.31,"output":0.31,"cache_read":0.155},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Cydonia-24B-v2":{"id":"TheDrummer/Cydonia-24B-v2","name":"The Drummer Cydonia 24B v2","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":32768},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Cydonia-24B-v4":{"id":"TheDrummer/Cydonia-24B-v4","name":"The Drummer Cydonia 24B v4","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":32768},"cost":{"input":0.2006,"output":0.2414,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Cydonia-24B-v4.1":{"id":"TheDrummer/Cydonia-24B-v4.1","name":"The Drummer Cydonia 24B v4.1","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":131072,"output":131072},"cost":{"input":0.35,"output":0.55,"cache_read":0.16},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Cydonia-24B-v4.3":{"id":"TheDrummer/Cydonia-24B-v4.3","name":"The Drummer Cydonia 24B v4.3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-25","last_updated":"2025-12-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.12,"output":0.15,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Magidonia-24B-v4.3":{"id":"TheDrummer/Magidonia-24B-v4.3","name":"The Drummer Magidonia 24B v4.3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-25","last_updated":"2025-12-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0.1003,"output":0.1207,"cache_read":0.05015},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/Rocinante-12B-v1.1":{"id":"TheDrummer/Rocinante-12B-v1.1","name":"Rocinante 12b","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.408,"output":0.595,"cache_read":0.204},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/skyfall-36b-v2":{"id":"TheDrummer/skyfall-36b-v2","name":"TheDrummer Skyfall 36B V2","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":32768},"cost":{"input":0.55,"output":0.8,"cache_read":0.25},"sourceProvider":"nano-gpt"},"nano-gpt/TheDrummer/UnslopNemo-12B-v4.1":{"id":"TheDrummer/UnslopNemo-12B-v4.1","name":"UnslopNemo 12b v4","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-01-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"input":8192,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"input":1048000,"output":32768},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"nano-gpt"},"nano-gpt/thinkingmachines/Inkling-Small":{"id":"thinkingmachines/Inkling-Small","name":"Inkling Small","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/thinkingmachines/Inkling-Small:thinking":{"id":"thinkingmachines/Inkling-Small:thinking","name":"Inkling Small Thinking","description":"Multimodal MoE reasoning model (276B total, 12B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"input":524288,"output":32768},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/thinkingmachines/inkling:thinking":{"id":"thinkingmachines/inkling:thinking","name":"Inkling Thinking","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048000,"input":1048000,"output":32768},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"nano-gpt"},"nano-gpt/THUDM/GLM-4-32B-0414":{"id":"THUDM/GLM-4-32B-0414","name":"GLM 4 32B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/THUDM/GLM-4-9B-0414":{"id":"THUDM/GLM-4-9B-0414","name":"GLM 4 9B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8000},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/THUDM/GLM-Z1-9B-0414":{"id":"THUDM/GLM-Z1-9B-0414","name":"GLM Z1 9B 0414","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm-z","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-04-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":32000,"output":8000},"cost":{"input":0.2,"output":0.2,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/Tongyi-Zhiwen/QwenLong-L1-32B":{"id":"Tongyi-Zhiwen/QwenLong-L1-32B","name":"QwenLong L1 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":40960},"cost":{"input":0.14,"output":0.6,"cache_read":0.07},"sourceProvider":"nano-gpt"},"nano-gpt/undi95/remm-slerp-l2-13b":{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-01-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":6144,"input":6144,"output":4096},"cost":{"input":0.799,"output":1.207,"cache_read":0.3995},"sourceProvider":"nano-gpt"},"nano-gpt/universal-summarizer":{"id":"nano-gpt/universal-summarizer","name":"Universal Summarizer","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-23","last_updated":"2024-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":30,"output":30},"sourceProvider":"nano-gpt"},"nano-gpt/unsloth/gemma-3-12b-it":{"id":"unsloth/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":131072},"cost":{"input":0.272,"output":0.272,"cache_read":0.136},"sourceProvider":"nano-gpt"},"nano-gpt/unsloth/gemma-3-27b-it":{"id":"unsloth/gemma-3-27b-it","name":"Gemma 3 27B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":96000},"cost":{"input":0.2992,"output":0.2992,"cache_read":0.1496},"sourceProvider":"nano-gpt"},"nano-gpt/unsloth/gemma-3-4b-it":{"id":"unsloth/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"unsloth","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2025-03-10","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/upstage/solar-pro-3":{"id":"upstage/solar-pro-3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":128000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"nano-gpt"},"nano-gpt/upstage/solar-pro4":{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.03,"output":0.12,"cache_read":0.006},"sourceProvider":"nano-gpt"},"nano-gpt/upstage/solar-pro4:thinking":{"id":"upstage/solar-pro4:thinking","name":"Solar Pro 4 Thinking","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"input":524288,"output":131072},"cost":{"input":0.03,"output":0.12,"cache_read":0.006},"sourceProvider":"nano-gpt"},"nano-gpt/venice-uncensored":{"id":"nano-gpt/venice-uncensored","name":"Venice Uncensored","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"venice","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-10-01","last_updated":"2025-02-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":8192},"cost":{"input":0.4,"output":1.8,"cache_read":0.4},"sourceProvider":"nano-gpt"},"nano-gpt/VongolaChouko/Starcannon-Unleashed-12B-v1.0":{"id":"VongolaChouko/Starcannon-Unleashed-12B-v1.0","name":"Mistral Nemo Starcannon 12b v1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":0.493,"output":0.493,"cache_read":0.2465},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-4.20":{"id":"x-ai/grok-4.20","name":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"input":2000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-4.20-multi-agent":{"id":"x-ai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"input":2000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":1},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-4.6":{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/x-ai/grok-latest":{"id":"x-ai/grok-latest","name":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"input":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5-pro-crof":{"id":"xiaomi/mimo-v2.5-pro-crof","name":"MiMo V2.5 Pro (Crof)","description":"MiMo V2.5 Pro is Xiaomi's long-context flagship general model for coding and agentic orchestration. This separately served variant is intended for users concerned about censorship on the regular Xiaomi MiMo V2.5 Pro, and it is included in the NanoGPT subscription.","family":"mimo-v2.5-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.4,"output":0.8,"cache_read":0.003},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5-pro-crof:thinking":{"id":"xiaomi/mimo-v2.5-pro-crof:thinking","name":"MiMo V2.5 Pro Thinking (Crof)","description":"MiMo V2.5 Pro with Xiaomi thinking enabled for coding, long-context reasoning, and agentic orchestration. This separately served thinking variant is intended for users concerned about censorship on the regular Xiaomi MiMo V2.5 Pro, and it is included in the NanoGPT subscription.","family":"mimo-v2.5-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":131072},"cost":{"input":0.4,"output":0.8,"cache_read":0.003},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5-pro:thinking":{"id":"xiaomi/mimo-v2.5-pro:thinking","name":"MiMo V2.5 Pro Thinking","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0},"sourceProvider":"nano-gpt"},"nano-gpt/xiaomi/mimo-v2.5:thinking":{"id":"xiaomi/mimo-v2.5:thinking","name":"MiMo V2.5 Thinking","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0},"sourceProvider":"nano-gpt"},"nano-gpt/yi-large":{"id":"nano-gpt/yi-large","name":"Yi Large","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"yi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"input":32000,"output":4096},"cost":{"input":3.196,"output":3.196,"cache_read":1.598},"sourceProvider":"nano-gpt"},"nano-gpt/yi-lightning":{"id":"nano-gpt/yi-lightning","name":"Yi Lightning","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"yi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-06-15","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":12000,"input":12000,"output":4096},"cost":{"input":0.2006,"output":0.2006,"cache_read":0.1003},"sourceProvider":"nano-gpt"},"nano-gpt/yi-medium-200k":{"id":"nano-gpt/yi-medium-200k","name":"Yi Medium 200k","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"yi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2024-01-01","last_updated":"2024-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":4096},"cost":{"input":2.499,"output":2.499,"cache_read":1.2495},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-4.5v":{"id":"z-ai/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"input":64000,"output":96000},"cost":{"input":0.6,"output":1.8,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-4.5v:thinking":{"id":"z-ai/glm-4.5v:thinking","name":"GLM 4.5V Thinking","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"input":64000,"output":96000},"cost":{"input":0.6,"output":1.8,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.35,"output":1.4,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-4.6:thinking":{"id":"z-ai/glm-4.6:thinking","name":"GLM 4.6 Thinking","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.35,"output":1.4,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"nano-gpt"},"nano-gpt/z-ai/glm-5v-turbo:thinking":{"id":"z-ai/glm-5v-turbo:thinking","name":"GLM 5V Turbo Thinking","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"input":202800,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.5":{"id":"zai-org/glm-4.5","name":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/GLM-4.5-Air":{"id":"zai-org/GLM-4.5-Air","name":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":98304},"cost":{"input":0.12,"output":0.8,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/GLM-4.5-Air:thinking":{"id":"zai-org/GLM-4.5-Air:thinking","name":"GLM 4.5 Air (Thinking)","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":98304},"cost":{"input":0.12,"output":0.8,"cache_read":0.06},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/GLM-4.5:thinking":{"id":"zai-org/GLM-4.5:thinking","name":"GLM 4.5 (Thinking)","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":65536},"cost":{"input":0.3,"output":1.3,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.6-original":{"id":"zai-org/glm-4.6-original","name":"GLM 4.6 Original","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":65535},"cost":{"input":0.35,"output":1.4,"cache_read":0.175},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/GLM-4.6-turbo":{"id":"zai-org/GLM-4.6-turbo","name":"GLM 4.6 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":204800},"cost":{"input":1,"output":3,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/GLM-4.6-turbo:thinking":{"id":"zai-org/GLM-4.6-turbo:thinking","name":"GLM 4.6 Turbo (Thinking)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":204800},"cost":{"input":1,"output":3,"cache_read":0.5},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.6v":{"id":"zai-org/glm-4.6v","name":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":24000},"cost":{"input":0.3,"output":0.9,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.6v-flash-original":{"id":"zai-org/glm-4.6v-flash-original","name":"GLM 4.6V Flash","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":24000},"cost":{"input":0.1,"output":0.4,"cache_read":0.05},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.6v-original":{"id":"zai-org/glm-4.6v-original","name":"GLM 4.6V Original","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":128000,"output":24000},"cost":{"input":0.6,"output":0.9,"cache_read":0.3},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7":{"id":"zai-org/glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.2,"output":0.8,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-flash":{"id":"zai-org/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-flash-original":{"id":"zai-org/glm-4.7-flash-original","name":"GLM 4.7 Flash Original","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-flash-original:thinking":{"id":"zai-org/glm-4.7-flash-original:thinking","name":"GLM 4.7 Flash Original Thinking","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-flash:thinking":{"id":"zai-org/glm-4.7-flash:thinking","name":"GLM 4.7 Flash Thinking","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-original":{"id":"zai-org/glm-4.7-original","name":"GLM 4.7 Original","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7-original:thinking":{"id":"zai-org/glm-4.7-original:thinking","name":"GLM 4.7 Original Thinking","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-4.7:thinking":{"id":"zai-org/glm-4.7:thinking","name":"GLM 4.7 Thinking","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":65535},"cost":{"input":0.2,"output":0.8,"cache_read":0.1},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5":{"id":"zai-org/glm-5","name":"GLM 5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.5,"output":2.55,"cache_read":0.13},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5-original":{"id":"zai-org/glm-5-original","name":"GLM 5 Original","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5-original:thinking":{"id":"zai-org/glm-5-original:thinking","name":"GLM 5 Original Thinking","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5:thinking":{"id":"zai-org/glm-5:thinking","name":"GLM 5 Thinking","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":128000},"cost":{"input":0.5,"output":2.55,"cache_read":0.13},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.1":{"id":"zai-org/glm-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.75,"output":2.6,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.1:thinking":{"id":"zai-org/glm-5.1:thinking","name":"GLM 5.1 Thinking","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"input":200000,"output":131072},"cost":{"input":0.75,"output":2.6,"cache_read":0.15},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.42,"output":1.32,"cache_read":0.078},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.2:thinking":{"id":"zai-org/glm-5.2:thinking","name":"GLM 5.2 Thinking","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.42,"output":1.32,"cache_read":0.078},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.3":{"id":"zai-org/glm-5.3","name":"GLM 5.3 Preview","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-5.3:thinking":{"id":"zai-org/glm-5.3:thinking","name":"GLM 5.3 Preview Thinking","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"nano-gpt"},"nano-gpt/zai-org/glm-latest":{"id":"zai-org/glm-latest","name":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"release_date":"2026-05-03","last_updated":"2026-05-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"input":1048576,"output":131072},"cost":{"input":0.42,"output":1.32,"cache_read":0.078},"sourceProvider":"nano-gpt"},"nearai/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"nearai"},"nearai/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"nearai"},"nearai/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"nearai"},"nearai/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15.5,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"nearai"},"nearai/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"nearai"},"nearai/black-forest-labs/FLUX.2-klein-4B":{"id":"black-forest-labs/FLUX.2-klein-4B","name":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["image"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":1,"output":1},"sourceProvider":"nearai"},"nearai/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"nearai"},"nearai/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"nearai"},"nearai/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"nearai"},"nearai/google/gemini-3-pro":{"id":"google/gemini-3-pro","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":15,"cache_read":0},"sourceProvider":"nearai"},"nearai/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"nearai"},"nearai/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"nearai"},"nearai/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.4,"cache_read":0.026},"sourceProvider":"nearai"},"nearai/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"nearai"},"nearai/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"nearai"},"nearai/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"nearai"},"nearai/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nearai"},"nearai/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"nearai"},"nearai/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"nearai"},"nearai/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"nearai"},"nearai/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.8,"output":15.5,"cache_read":0.18},"sourceProvider":"nearai"},"nearai/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"nearai"},"nearai/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"nearai"},"nearai/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"nearai"},"nearai/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"nearai"},"nearai/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":32768},"cost":{"input":0.15,"output":0.55},"sourceProvider":"nearai"},"nearai/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"nearai"},"nearai/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"nearai"},"nearai/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"nearai"},"nearai/openai/whisper-large-v3":{"id":"openai/whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":448},"cost":{"input":0.01,"output":0},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B-A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":0.55},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3-Embedding-0.6B":{"id":"Qwen/Qwen3-Embedding-0.6B","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":1024},"cost":{"input":0.01,"output":0},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3-Reranker-0.6B":{"id":"Qwen/Qwen3-Reranker-0.6B","name":"Qwen3 Reranker 0.6B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":1024},"cost":{"input":0.01,"output":0.01},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3-VL-30B-A3B-Instruct":{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3-VL 30B-A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.15,"output":0.55},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3.5-122B-A10B":{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":3.2},"sourceProvider":"nearai"},"nearai/Qwen/Qwen3.6-35B-A3B-FP8":{"id":"Qwen/Qwen3.6-35B-A3B-FP8","name":"Qwen 3.6 35B A3B FP8","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.17,"output":1.1,"cache_read":0.056},"sourceProvider":"nearai"},"nearai/zai-org/GLM-5.1-FP8":{"id":"zai-org/GLM-5.1-FP8","name":"GLM-5.1 FP8","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.85,"output":3.3},"sourceProvider":"nearai"},"nebius/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"DeepSeek-V3.2","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-01-20","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163000,"input":160000,"output":16384},"status":"deprecated","cost":{"input":0.3,"output":0.45,"reasoning":0.45,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"nebius"},"nebius/deepseek-ai/DeepSeek-V3.2-fast":{"id":"deepseek-ai/DeepSeek-V3.2-fast","name":"DeepSeek-V3.2-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-27","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.4,"output":2,"cache_read":0.04,"cache_write":0.5},"sourceProvider":"nebius"},"nebius/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.14},"sourceProvider":"nebius"},"nebius/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.75,"output":3.5,"cache_read":0.15},"sourceProvider":"nebius"},"nebius/google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Gemma-3-27b-it","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-10","release_date":"2026-01-20","last_updated":"2026-02-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":110000,"input":100000,"output":8192},"cost":{"input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nebius"},"nebius/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-12-05","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":0.13,"output":0.4,"cache_read":0.013,"cache_write":0.16},"sourceProvider":"nebius"},"nebius/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"input":190000,"output":8192},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"nebius"},"nebius/MiniMaxAI/MiniMax-M2.5-fast":{"id":"MiniMaxAI/MiniMax-M2.5-fast","name":"MiniMax-M2.5-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"nebius"},"nebius/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.3,"output":1.2},"sourceProvider":"nebius"},"nebius/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi-K2.5","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-12-15","last_updated":"2026-02-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"status":"deprecated","cost":{"input":0.5,"output":2.5,"reasoning":2.5,"cache_read":0.05,"cache_write":0.625},"sourceProvider":"nebius"},"nebius/moonshotai/Kimi-K2.5-fast":{"id":"moonshotai/Kimi-K2.5-fast","name":"Kimi-K2.5-fast","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-12-15","last_updated":"2026-02-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":8192},"status":"deprecated","cost":{"input":0.5,"output":2.5,"cache_read":0.05,"cache_write":0.625},"sourceProvider":"nebius"},"nebius/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8000},"cost":{"input":0.95,"output":4},"sourceProvider":"nebius"},"nebius/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8000},"cost":{"input":3,"output":15,"cache_read":3},"sourceProvider":"nebius"},"nebius/NousResearch/Hermes-4-405B":{"id":"NousResearch/Hermes-4-405B","name":"Hermes-4-405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-01-30","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":1,"output":3,"reasoning":3,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"nebius"},"nebius/NousResearch/Hermes-4-70B":{"id":"NousResearch/Hermes-4-70B","name":"Hermes-4-70B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-01-30","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":0.13,"output":0.4,"reasoning":0.4,"cache_read":0.013,"cache_write":0.16},"sourceProvider":"nebius"},"nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1":{"id":"nvidia/Llama-3_1-Nemotron-Ultra-253B-v1","name":"Llama-3.1-Nemotron-Ultra-253B-v1","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-15","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":4096},"cost":{"input":0.6,"output":1.8,"cache_read":0.06,"cache_write":0.75},"sourceProvider":"nebius"},"nebius/nvidia/Nemotron-3-Nano-Omni":{"id":"nvidia/Nemotron-3-Nano-Omni","name":"Nemotron-3-Nano-Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-01-20","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"input":60000,"output":8192},"cost":{"input":0.06,"output":0.24,"cache_read":0.006,"cache_write":0.075},"sourceProvider":"nebius"},"nebius/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron-3-Super-120B-A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":32768},"cost":{"input":0.3,"output":0.9},"sourceProvider":"nebius"},"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B":{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","name":"Nemotron-3-Nano-30B-A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-08-10","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"input":30000,"output":4096},"cost":{"input":0.06,"output":0.24,"cache_read":0.006,"cache_write":0.075},"sourceProvider":"nebius"},"nebius/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-01-10","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":124000,"output":8192},"cost":{"input":0.15,"output":0.6,"reasoning":0.6,"cache_read":0.015,"cache_write":0.18},"sourceProvider":"nebius"},"nebius/openai/gpt-oss-120b-fast":{"id":"openai/gpt-oss-120b-fast","name":"gpt-oss-120b-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-10","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.1,"output":0.5,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nebius"},"nebius/PrimeIntellect/INTELLECT-3":{"id":"PrimeIntellect/INTELLECT-3","name":"INTELLECT-3","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-10","release_date":"2026-01-25","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"status":"deprecated","cost":{"input":0.2,"output":1.1,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"nebius"},"nebius/Qwen/Qwen2.5-VL-72B-Instruct":{"id":"Qwen/Qwen2.5-VL-72B-Instruct","name":"Qwen2.5-VL-72B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-01-20","last_updated":"2026-02-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0.31},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0.2,"output":0.6},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507-fast","name":"Qwen3-235B-A22B-Thinking-2507-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.5,"output":2,"cache_read":0.05,"cache_write":0.625},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-28","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-28","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":8192},"cost":{"input":0.1,"output":0.3,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-Embedding-8B":{"id":"Qwen/Qwen3-Embedding-8B","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2025-10","release_date":"2026-01-10","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"input":32768,"output":0},"cost":{"input":0.01,"output":0},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-Next-80B-A3B-Thinking":{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking","name":"Qwen3-Next-80B-A3B-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-12","release_date":"2026-01-28","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"input":120000,"output":16384},"cost":{"input":0.15,"output":1.2,"reasoning":1.2,"cache_read":0.015,"cache_write":0.18},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast":{"id":"Qwen/Qwen3-Next-80B-A3B-Thinking-fast","name":"Qwen3-Next-80B-A3B-Thinking-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.15,"output":1.2,"cache_read":0.015,"cache_write":0.1875},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5-397B-A17B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-15","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":250000,"output":8192},"cost":{"input":0.6,"output":3.6,"cache_read":0.06,"cache_write":0.75},"sourceProvider":"nebius"},"nebius/Qwen/Qwen3.5-397B-A17B-fast":{"id":"Qwen/Qwen3.5-397B-A17B-fast","name":"Qwen3.5-397B-A17B-fast","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-15","last_updated":"2026-05-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8000,"input":7000,"output":8192},"status":"deprecated","cost":{"input":0.6,"output":3.6,"cache_read":0.06,"cache_write":0.75},"sourceProvider":"nebius"},"nebius/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"Legacy model retained for compatibility with older integrations","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-03-01","last_updated":"2026-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":16384},"status":"deprecated","cost":{"input":1,"output":3.2,"cache_read":0.1,"cache_write":1},"sourceProvider":"nebius"},"nebius/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":432000,"output":432000},"cost":{"input":1.4,"output":4.4},"sourceProvider":"nebius"},"neon/claude-fable-5":{"id":"neon/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"neon"},"neon/claude-haiku-4-5":{"id":"neon/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"neon"},"neon/claude-opus-4-1":{"id":"neon/claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"neon"},"neon/claude-opus-4-5":{"id":"neon/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"neon"},"neon/claude-opus-4-6":{"id":"neon/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":127999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"neon"},"neon/claude-opus-4-7":{"id":"neon/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"neon"},"neon/claude-opus-4-8":{"id":"neon/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"neon"},"neon/claude-opus-5":{"id":"neon/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"neon"},"neon/claude-sonnet-4-5":{"id":"neon/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"neon"},"neon/claude-sonnet-4-6":{"id":"neon/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"neon"},"neon/claude-sonnet-5":{"id":"neon/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"neon"},"neon/gemini-3-1-flash-lite":{"id":"neon/gemini-3-1-flash-lite","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"neon"},"neon/gemini-3-1-pro":{"id":"neon/gemini-3-1-pro","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"neon"},"neon/gemini-3-5-flash":{"id":"neon/gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"neon"},"neon/gemini-3-5-flash-lite":{"id":"neon/gemini-3-5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"neon"},"neon/gemini-3-6-flash":{"id":"neon/gemini-3-6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"neon"},"neon/gemini-3-flash":{"id":"neon/gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"neon"},"neon/gemma-3-12b":{"id":"neon/gemma-3-12b","name":"Gemma 3 12B","description":"Google's open-weight Gemma 3 vision-language model for text and image understanding","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.5},"sourceProvider":"neon"},"neon/glm-5-2":{"id":"neon/glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"neon"},"neon/gpt-5":{"id":"neon/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"neon"},"neon/gpt-5-1":{"id":"neon/gpt-5-1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"neon"},"neon/gpt-5-2":{"id":"neon/gpt-5-2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"neon"},"neon/gpt-5-3-codex":{"id":"neon/gpt-5-3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"neon"},"neon/gpt-5-4":{"id":"neon/gpt-5-4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"neon"},"neon/gpt-5-4-mini":{"id":"neon/gpt-5-4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"neon"},"neon/gpt-5-4-nano":{"id":"neon/gpt-5-4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"neon"},"neon/gpt-5-5":{"id":"neon/gpt-5-5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"neon"},"neon/gpt-5-5-pro":{"id":"neon/gpt-5-5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"neon"},"neon/gpt-5-6-luna":{"id":"neon/gpt-5-6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":1,"output":6,"cache_read":0.1,"tiers":[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2}},"sourceProvider":"neon"},"neon/gpt-5-6-sol":{"id":"neon/gpt-5-6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"neon"},"neon/gpt-5-6-terra":{"id":"neon/gpt-5-6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"neon"},"neon/gpt-5-mini":{"id":"neon/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"neon"},"neon/gpt-5-nano":{"id":"neon/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"${NEON_AI_GATEWAY_BASE_URL}/openai/v1","shape":"responses"},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"neon"},"neon/gpt-oss-120b":{"id":"neon/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":25000},"cost":{"input":0.072,"output":0.28},"sourceProvider":"neon"},"neon/gpt-oss-20b":{"id":"neon/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":25000},"cost":{"input":0.05,"output":0.2},"sourceProvider":"neon"},"neon/inkling":{"id":"neon/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"sourceProvider":"neon"},"neon/kimi-k3":{"id":"neon/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"neon"},"neon/llama-4-maverick":{"id":"neon/llama-4-maverick","name":"Llama 4 Maverick 17B Instruct","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":8192},"cost":{"input":0.5,"output":1.5},"sourceProvider":"neon"},"neon/meta-llama-3-1-8b-instruct":{"id":"neon/meta-llama-3-1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Meta's compact open-weight Llama 3.1 model for fast, low-cost text generation","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.15,"output":0.45},"sourceProvider":"neon"},"neon/meta-llama-3-3-70b-instruct":{"id":"neon/meta-llama-3-3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.5,"output":1.5},"sourceProvider":"neon"},"neon/qwen3-next-80b-a3b-instruct":{"id":"neon/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":10000},"cost":{"input":0.15,"output":1.2},"sourceProvider":"neon"},"neon/qwen35-122b-a10b":{"id":"neon/qwen35-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":25000},"cost":{"input":0.22,"output":2.2},"sourceProvider":"neon"},"neuralwatt/deepseek-v4-flash":{"id":"neuralwatt/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":65536},"cost":{"input":0.104,"output":0.207,"cache_read":0.026},"sourceProvider":"neuralwatt"},"neuralwatt/gemma-4-31b":{"id":"neuralwatt/gemma-4-31b","name":"Gemma 4 31B","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":16384},"cost":{"input":0.144,"output":0.42,"cache_read":0.036},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2":{"id":"neuralwatt/glm-5.2","name":"GLM 5.2","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":1.45,"output":4.5,"cache_read":0.3625},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-fast":{"id":"neuralwatt/glm-5.2-fast","name":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":1.45,"output":4.5,"cache_read":0.3625},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-flex":{"id":"neuralwatt/glm-5.2-flex","name":"GLM 5.2 Flex","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":0.725,"output":2.25,"cache_read":0.18125},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-short":{"id":"neuralwatt/glm-5.2-short","name":"GLM 5.2 Short","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":199984},"cost":{"input":1.45,"output":4.5,"cache_read":0.3625},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-short-fast":{"id":"neuralwatt/glm-5.2-short-fast","name":"GLM 5.2 Short Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":199984},"cost":{"input":1.45,"output":4.5,"cache_read":0.3625},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-short-fast-flex":{"id":"neuralwatt/glm-5.2-short-fast-flex","name":"GLM 5.2 Short Fast Flex","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":199984},"cost":{"input":0.725,"output":2.25,"cache_read":0.18125},"sourceProvider":"neuralwatt"},"neuralwatt/glm-5.2-short-flex":{"id":"neuralwatt/glm-5.2-short-flex","name":"GLM 5.2 Short Flex","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":199984,"output":199984},"cost":{"input":0.725,"output":2.25,"cache_read":0.18125},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k2.5-fast":{"id":"neuralwatt/kimi-k2.5-fast","name":"Kimi K2.5 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.52,"output":2.59,"cache_read":0.13},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k2.6-fast":{"id":"neuralwatt/kimi-k2.6-fast","name":"Kimi K2.6 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.69,"output":3.22,"cache_read":0.1725},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k2.6-flex":{"id":"neuralwatt/kimi-k2.6-flex","name":"Kimi K2.6 Flex","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.345,"output":1.61,"cache_read":0.08625},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k2.7-code-flex":{"id":"neuralwatt/kimi-k2.7-code-flex","name":"Kimi K2.7 Code Flex","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.475,"output":2,"cache_read":0.11875},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k3":{"id":"neuralwatt/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"neuralwatt"},"neuralwatt/kimi-k3-fast":{"id":"neuralwatt/kimi-k3-fast","name":"Kimi K3 Fast","description":"Kimi K3 with thinking disabled for low-latency tool calling, vision, and JSON work","family":"kimi-k3","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048560,"output":1048560},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"neuralwatt"},"neuralwatt/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.52,"output":2.59,"cache_read":0.13},"sourceProvider":"neuralwatt"},"neuralwatt/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.69,"output":3.22,"cache_read":0.1725},"sourceProvider":"neuralwatt"},"neuralwatt/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.2375},"sourceProvider":"neuralwatt"},"neuralwatt/Qwen/Qwen3.5-397B-A17B-FP8":{"id":"Qwen/Qwen3.5-397B-A17B-FP8","name":"Qwen3.5 397B A17B FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.69,"output":4.14,"cache_read":0.1725},"sourceProvider":"neuralwatt"},"neuralwatt/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131056,"output":131056},"cost":{"input":0.29,"output":1.15,"cache_read":0.0725},"sourceProvider":"neuralwatt"},"neuralwatt/qwen3.5-397b-fast":{"id":"neuralwatt/qwen3.5-397b-fast","name":"Qwen3.5 397B Fast","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262128,"output":262128},"cost":{"input":0.69,"output":4.14,"cache_read":0.1725},"sourceProvider":"neuralwatt"},"neuralwatt/qwen3.6-35b-fast":{"id":"neuralwatt/qwen3.6-35b-fast","name":"Qwen3.6 35B Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"qwen3.6","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131056,"output":131056},"cost":{"input":0.29,"output":1.15,"cache_read":0.0725},"sourceProvider":"neuralwatt"},"nova/nova-2-lite-v1":{"id":"nova/nova-2-lite-v1","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"reasoning":0},"sourceProvider":"nova"},"nova/nova-2-pro-v1":{"id":"nova/nova-2-pro-v1","name":"Nova 2 Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2026-01-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0,"output":0,"reasoning":0},"sourceProvider":"nova"},"novita-ai/baichuan/baichuan-m2-32b":{"id":"baichuan/baichuan-m2-32b","name":"baichuan-m2-32b","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"baichuan","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.07,"output":0.07},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-21B-a3b":{"id":"baidu/ernie-4.5-21B-a3b","name":"ERNIE 4.5 21B A3B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ernie","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":120000,"output":8000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-21B-a3b-thinking":{"id":"baidu/ernie-4.5-21B-a3b-thinking","name":"ERNIE-4.5-21B-A3B-Thinking","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ernie","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2025-03","release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.07,"output":0.28},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-300b-a47b-paddle":{"id":"baidu/ernie-4.5-300b-a47b-paddle","name":"ERNIE 4.5 300B A47B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":123000,"output":12000},"cost":{"input":0.28,"output":1.1},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-vl-28b-a3b":{"id":"baidu/ernie-4.5-vl-28b-a3b","name":"ERNIE 4.5 VL 28B A3B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2026-06-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":30000,"output":8000},"cost":{"input":0.14,"output":0.56},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-vl-28b-a3b-thinking":{"id":"baidu/ernie-4.5-vl-28b-a3b-thinking","name":"ERNIE-4.5-VL-28B-A3B-Thinking","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-26","last_updated":"2025-11-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.39,"output":0.39},"sourceProvider":"novita-ai"},"novita-ai/baidu/ernie-4.5-vl-424b-a47b":{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-ocr":{"id":"deepseek/deepseek-ocr","name":"DeepSeek-OCR","description":"OCR model for extracting structured text from documents and screenshots","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-24","last_updated":"2025-10-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.03,"output":0.03},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-ocr-2":{"id":"deepseek/deepseek-ocr-2","name":"deepseek/deepseek-ocr-2","description":"OCR model for extracting structured text from documents and screenshots","attachment":true,"reasoning":false,"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.03,"output":0.03},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-prover-v2-671b":{"id":"deepseek/deepseek-prover-v2-671b","name":"Deepseek Prover V2 671B","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":160000},"cost":{"input":0.7,"output":2.5},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.7,"output":2.5,"cache_read":0.35},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-0528-qwen3-8b":{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek R1 0528 Qwen3 8B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.06,"output":0.09},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-distill-llama-70b":{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek R1 Distill LLama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.8,"output":0.8},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-distill-qwen-14b":{"id":"deepseek/deepseek-r1-distill-qwen-14b","name":"DeepSeek R1 Distill Qwen 14B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.15,"output":0.15},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-distill-qwen-32b":{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek R1 Distill Qwen 32B","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"deepseek-thinking","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-01-20","last_updated":"2025-01-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":32000},"cost":{"input":0.3,"output":0.3},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-r1-turbo":{"id":"deepseek/deepseek-r1-turbo","name":"DeepSeek R1 (Turbo)\t","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.7,"output":2.5},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3-0324":{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.27,"output":1.12,"cache_read":0.135},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3-turbo":{"id":"deepseek/deepseek-v3-turbo","name":"DeepSeek V3 (Turbo)\t","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-05","last_updated":"2025-03-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.4,"output":1.3},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3.1":{"id":"deepseek/deepseek-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"Deepseek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"Deepseek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.269,"output":0.4,"cache_read":0.1345},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"Deepseek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.41},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"novita-ai"},"novita-ai/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":1.6,"output":3.2,"cache_read":0.135},"sourceProvider":"novita-ai"},"novita-ai/google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.05,"output":0.1},"sourceProvider":"novita-ai"},"novita-ai/google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":98304,"output":16384},"cost":{"input":0.119,"output":0.2},"sourceProvider":"novita-ai"},"novita-ai/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.13,"output":0.4},"sourceProvider":"novita-ai"},"novita-ai/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"sourceProvider":"novita-ai"},"novita-ai/gryphe/mythomax-l2-13b":{"id":"gryphe/mythomax-l2-13b","name":"Mythomax L2 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-25","last_updated":"2024-04-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":3200},"cost":{"input":0.09,"output":0.09},"sourceProvider":"novita-ai"},"novita-ai/inclusionai/ling-2.6-1t":{"id":"inclusionai/ling-2.6-1t","name":"Ling-2.6-1T","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-23","last_updated":"2026-06-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"novita-ai"},"novita-ai/inclusionai/ling-2.6-flash":{"id":"inclusionai/ling-2.6-flash","name":"Ling-2.6-flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"novita-ai"},"novita-ai/inclusionai/ring-2.6-1t":{"id":"inclusionai/ring-2.6-1t","name":"Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-08","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"novita-ai"},"novita-ai/kwaipilot/kat-coder-pro":{"id":"kwaipilot/kat-coder-pro","name":"Kat Coder Pro","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-05","last_updated":"2026-01-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-3-70b-instruct":{"id":"meta-llama/llama-3-70b-instruct","name":"Llama3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-04-25","last_updated":"2024-04-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8000},"cost":{"input":0.51,"output":0.74},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-3-8b-instruct":{"id":"meta-llama/llama-3-8b-instruct","name":"Llama 3 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-25","last_updated":"2024-04-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.04,"output":0.04},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-3.1-8b-instruct":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-07-24","last_updated":"2024-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.05},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-3.2-3b-instruct":{"id":"meta-llama/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0.03,"output":0.05},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-3.3-70b-instruct":{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-07","last_updated":"2024-12-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":120000},"cost":{"input":0.135,"output":0.4},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-4-maverick-17b-128e-instruct-fp8":{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-06","last_updated":"2025-04-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":8192},"cost":{"input":0.27,"output":0.85},"sourceProvider":"novita-ai"},"novita-ai/meta-llama/llama-4-scout-17b-16e-instruct":{"id":"meta-llama/llama-4-scout-17b-16e-instruct","name":"Llama 4 Scout Instruct","description":"Open multimodal Llama model for long-context analysis and efficient agents","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-06","last_updated":"2025-04-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.18,"output":0.59},"sourceProvider":"novita-ai"},"novita-ai/microsoft/wizardlm-2-8x22b":{"id":"microsoft/wizardlm-2-8x22b","name":"Wizardlm 2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-24","last_updated":"2024-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65535,"output":8000},"cost":{"input":0.62,"output":0.62},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"Minimax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131100},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax-m2.5","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.03},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.7","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"novita-ai"},"novita-ai/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"novita-ai"},"novita-ai/minimaxai/minimax-m1-80k":{"id":"minimaxai/minimax-m1-80k","name":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":40000},"cost":{"input":0.55,"output":2.2},"sourceProvider":"novita-ai"},"novita-ai/mistralai/mistral-nemo":{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-07-30","last_updated":"2024-07-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60288,"output":16000},"cost":{"input":0.04,"output":0.17},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2-instruct":{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.57,"output":2.3},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-11-07","last_updated":"2026-06-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.8,"output":3.4,"cache_read":0.16},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"novita-ai"},"novita-ai/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"novita-ai"},"novita-ai/nousresearch/hermes-2-pro-llama-3-8b":{"id":"nousresearch/hermes-2-pro-llama-3-8b","name":"Hermes 2 Pro Llama 3 8B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-06-27","last_updated":"2024-06-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.14,"output":0.14},"sourceProvider":"novita-ai"},"novita-ai/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.05,"output":0.25},"sourceProvider":"novita-ai"},"novita-ai/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"OpenAI: GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.04,"output":0.15},"sourceProvider":"novita-ai"},"novita-ai/paddlepaddle/paddleocr-vl":{"id":"paddlepaddle/paddleocr-vl","name":"PaddleOCR-VL","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-22","last_updated":"2025-10-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.02,"output":0.02},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen-2.5-72b-instruct":{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen 2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-10-15","last_updated":"2024-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":8192},"cost":{"input":0.38,"output":0.4},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen-mt-plus":{"id":"qwen/qwen-mt-plus","name":"Qwen MT Plus","description":"Translation model for multilingual conversion, localization, and cross-language workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-03","last_updated":"2025-09-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":8192},"cost":{"input":0.25,"output":0.75},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen2.5-7b-instruct":{"id":"qwen/qwen2.5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.07,"output":0.07},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen2.5-vl-72b-instruct":{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-25","last_updated":"2025-03-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.8,"output":0.8},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-235b-a22b-fp8":{"id":"qwen/qwen3-235b-a22b-fp8","name":"Qwen3 235B A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.2,"output":0.8},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-235b-a22b-instruct-2507":{"id":"qwen/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.09,"output":0.58},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-235b-a22b-thinking-2507":{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22b Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":3},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-30b-a3b-fp8":{"id":"qwen/qwen3-30b-a3b-fp8","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.09,"output":0.45},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-32b-fp8":{"id":"qwen/qwen3-32b-fp8","name":"Qwen3 32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":20000},"cost":{"input":0.1,"output":0.45},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-4b-fp8":{"id":"qwen/qwen3-4b-fp8","name":"Qwen3 4B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":20000},"cost":{"input":0.03,"output":0.03},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-8b-fp8":{"id":"qwen/qwen3-8b-fp8","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":20000},"cost":{"input":0.035,"output":0.138},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3 Coder 30b A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-09","last_updated":"2025-10-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":32768},"cost":{"input":0.07,"output":0.27},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-coder-480b-a35b-instruct":{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.38,"output":1.55},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":2.11,"output":8.45},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-10","last_updated":"2025-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-10","last_updated":"2025-09-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.5},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-omni-30b-a3b-instruct":{"id":"qwen/qwen3-omni-30b-a3b-instruct","name":"Qwen3 Omni 30B A3B Instruct","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text","video","audio","image"],"output":["text","audio"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.25,"output":0.97,"input_audio":2.2,"output_audio":1.788},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-omni-30b-a3b-thinking":{"id":"qwen/qwen3-omni-30b-a3b-thinking","name":"Qwen3 Omni 30B A3B Thinking","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text","audio","video","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.25,"output":0.97,"input_audio":2.2,"output_audio":1.788},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":1.5},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.98,"output":3.95},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-vl-30b-a3b-instruct":{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"qwen/qwen3-vl-30b-a3b-instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-10-11","modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":0.7},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-vl-30b-a3b-thinking":{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"qwen/qwen3-vl-30b-a3b-thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-10-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.2,"output":1},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3-vl-8b-instruct":{"id":"qwen/qwen3-vl-8b-instruct","name":"qwen/qwen3-vl-8b-instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-17","last_updated":"2025-10-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.08,"output":0.5},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5-122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.4,"output":3.2},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5-27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2.4},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5-35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.25,"output":2},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"cost":{"input":0.6,"output":3.6},"sourceProvider":"novita-ai"},"novita-ai/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7-Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.5625},"sourceProvider":"novita-ai"},"novita-ai/sao10K/l3-70b-euryale-v2.1":{"id":"sao10K/l3-70b-euryale-v2.1","name":"L3 70B Euryale V2.1\t","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-06-18","last_updated":"2024-06-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":1.48,"output":1.48},"sourceProvider":"novita-ai"},"novita-ai/sao10K/l3-8b-lunaris":{"id":"sao10K/l3-8b-lunaris","name":"Sao10k L3 8B Lunaris\t","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-11-28","last_updated":"2024-11-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.05,"output":0.05},"sourceProvider":"novita-ai"},"novita-ai/sao10K/L3-8B-stheno-v3.2":{"id":"sao10K/L3-8B-stheno-v3.2","name":"L3 8B Stheno V3.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-11-29","last_updated":"2024-11-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":32000},"cost":{"input":0.05,"output":0.05},"sourceProvider":"novita-ai"},"novita-ai/sao10K/l31-70b-euryale-v2.2":{"id":"sao10K/l31-70b-euryale-v2.2","name":"L31 70B Euryale V2.2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":1.48,"output":1.48},"sourceProvider":"novita-ai"},"novita-ai/xiaomimimo/mimo-v2-flash":{"id":"xiaomimimo/mimo-v2-flash","name":"XiaomiMiMo/MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.1,"output":0.3,"cache_read":0.3},"sourceProvider":"novita-ai"},"novita-ai/xiaomimimo/mimo-v2-pro":{"id":"xiaomimimo/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.4,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"novita-ai"},"novita-ai/xiaomimimo/mimo-v2.5-pro":{"id":"xiaomimimo/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.522,"output":1.044,"cache_read":0.0043,"tiers":[{"input":0.522,"output":1.044,"cache_read":0.0043,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.522,"output":1.044,"cache_read":0.0043}},"sourceProvider":"novita-ai"},"novita-ai/zai-org/autoglm-phone-9b-multilingual":{"id":"zai-org/autoglm-phone-9b-multilingual","name":"AutoGLM-Phone-9B-Multilingual","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.035,"output":0.138},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.5":{"id":"zai-org/glm-4.5","name":"GLM-4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.5-air":{"id":"zai-org/glm-4.5-air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-10-13","last_updated":"2025-10-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.5v":{"id":"zai-org/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.6":{"id":"zai-org/glm-4.6","name":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.55,"output":2.2,"cache_read":0.11},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.6v":{"id":"zai-org/glm-4.6v","name":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glmv","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.7":{"id":"zai-org/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-4.7-flash":{"id":"zai-org/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.07,"output":0.4,"cache_read":0.01},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-5":{"id":"zai-org/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-5.1":{"id":"zai-org/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.38,"output":4.4,"cache_read":0.26},"sourceProvider":"novita-ai"},"novita-ai/zai-org/glm-5.2":{"id":"zai-org/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"novita-ai"},"nvidia/abacusai/dracarys-llama-3.1-70b-instruct":{"id":"abacusai/dracarys-llama-3.1-70b-instruct","name":"dracarys-llama-3.1-70b-instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-09-11","last_updated":"2025-05-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/active-speaker-detection":{"id":"nvidia/active-speaker-detection","name":"Active Speaker Detection","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/baai/bge-m3":{"id":"baai/bge-m3","name":"BGE M3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"bge","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-01-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":1024},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/bevformer":{"id":"nvidia/bevformer","name":"bevformer","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-07-20","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/black-forest-labs/flux_1-kontext-dev":{"id":"black-forest-labs/flux_1-kontext-dev","name":"FLUX.1-Kontext-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text","image"],"output":["image"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/black-forest-labs/flux_1-schnell":{"id":"black-forest-labs/flux_1-schnell","name":"FLUX.1-schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"knowledge":"2024-07","release_date":"2024-08-01","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["image"]},"open_weights":true,"limit":{"context":77,"input":77,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/black-forest-labs/flux_2-klein-4b":{"id":"black-forest-labs/flux_2-klein-4b","name":"FLUX.2 Klein 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-06","release_date":"2026-01-14","last_updated":"2026-01-31","modalities":{"input":["image","text"],"output":["image"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/black-forest-labs/flux.1-dev":{"id":"black-forest-labs/flux.1-dev","name":"FLUX.1-dev","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-08","release_date":"2024-08-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":4096,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/bytedance/seed-oss-36b-instruct":{"id":"bytedance/seed-oss-36b-instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/cosmos-predict1-5b":{"id":"nvidia/cosmos-predict1-5b","name":"cosmos-predict1-5b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-03-18","last_updated":"2025-03-18","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/cosmos-reason2-8b":{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","description":"Vision language model for physical-world understanding with structured reasoning on video and images","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/cosmos-transfer1-7b":{"id":"nvidia/cosmos-transfer1-7b","name":"cosmos-transfer1-7b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-13","last_updated":"2025-06-30","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/cosmos-transfer2_5-2b":{"id":"nvidia/cosmos-transfer2_5-2b","name":"cosmos-transfer2.5-2b","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/deepseek-ai/deepseek-v4-flash":{"id":"deepseek-ai/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"nvidia"},"nvidia/deepseek-ai/deepseek-v4-flash-0731":{"id":"deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/deepseek-ai/deepseek-v4-pro":{"id":"deepseek-ai/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393216},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"nvidia"},"nvidia/gliner-pii":{"id":"nvidia/gliner-pii","name":"gliner-pii","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-2-2b-it":{"id":"google/gemma-2-2b-it","name":"Gemma 2 2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-16","last_updated":"2024-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-3n-e2b-it":{"id":"google/gemma-3n-e2b-it","name":"Gemma 3n E2b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-06-12","last_updated":"2025-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-3n-e4b-it":{"id":"google/gemma-3n-e4b-it","name":"Gemma 3n E4b It","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-06-03","last_updated":"2025-06-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma-4-31B-IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/google/google-paligemma":{"id":"google/google-paligemma","name":"paligemma","description":"Gemini multimodal model for text, image, audio, video, and document tasks","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-05-14","last_updated":"2024-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3_2-nemoretriever-300m-embed-v1":{"id":"nvidia/llama-3_2-nemoretriever-300m-embed-v1","name":"llama-3_2-nemoretriever-300m-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-07-24","last_updated":"2025-07-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.1-nemotron-70b-instruct":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.1-nemotron-nano-8b-v1":{"id":"nvidia/llama-3.1-nemotron-nano-8b-v1","name":"Llama 3.1 Nemotron Nano 8B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.1-nemotron-nano-vl-8b-v1":{"id":"nvidia/llama-3.1-nemotron-nano-vl-8b-v1","name":"Llama 3.1 Nemotron Nano VL 8B v1","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-04-10","last_updated":"2025-04-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.1-nemotron-safety-guard-8b-v3":{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"llama-3.1-nemotron-safety-guard-8b-v3","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.1-nemotron-ultra-253b-v1":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.3-nemotron-super-49b-v1":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-04-07","last_updated":"2025-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-3.3-nemotron-super-49b-v1.5":{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-nemotron-embed-vl-1b-v2":{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"llama-nemotron-embed-vl-1b-v2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"nemotron","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-02-10","last_updated":"2026-02-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/llama-nemotron-rerank-vl-1b-v2":{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"llama-nemotron-rerank-vl-1b-v2","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"nemotron","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/magpie-tts-zeroshot":{"id":"nvidia/magpie-tts-zeroshot","name":"magpie-tts-zeroshot","description":"Speech generation model for controllable voice, narration, and audio delivery","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-22","last_updated":"2025-06-12","modalities":{"input":["text","audio"],"output":["audio"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/esm2-650m":{"id":"meta/esm2-650m","name":"esm2-650m","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-08-29","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/esmfold":{"id":"meta/esmfold","name":"esmfold","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-03-15","last_updated":"2025-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.1-70b-instruct":{"id":"meta/llama-3.1-70b-instruct","name":"Llama 3.1 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-16","last_updated":"2024-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.1-8b-instruct":{"id":"meta/llama-3.1-8b-instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2025-01-01","last_updated":"2025-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.2-11b-vision-instruct":{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11b Vision Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.2-1b-instruct":{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.2-3b-instruct":{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2024-09-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32000},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.2-90b-vision-instruct":{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","description":"Open Llama multimodal model for image understanding and text reasoning","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-3.3-70b-instruct":{"id":"meta/llama-3.3-70b-instruct","name":"Llama 3.3 70b Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-26","last_updated":"2024-11-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-4-maverick-17b-128e-instruct":{"id":"meta/llama-4-maverick-17b-128e-instruct","name":"Llama 4 Maverick 17b 128e Instruct","description":"Open multimodal Llama model for strong reasoning and fast responses","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-02","release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/llama-guard-4-12b":{"id":"meta/llama-guard-4-12b","name":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-05","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/microsoft/phi-4-mini-instruct":{"id":"microsoft/phi-4-mini-instruct","name":"Phi-4-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"phi","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/microsoft/phi-4-multimodal-instruct":{"id":"microsoft/phi-4-multimodal-instruct","name":"Phi 4 Multimodal","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-07-26","last_updated":"2025-07-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/minimaxai/minimax-m2.7":{"id":"minimaxai/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/minimaxai/minimax-m3":{"id":"minimaxai/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/magistral-small-2506":{"id":"mistralai/magistral-small-2506","name":"Magistral Small 2506","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/ministral-14b-instruct-2512":{"id":"mistralai/ministral-14b-instruct-2512","name":"Ministral 3 14B Instruct 2512","description":"Compact Mistral VLM for chat and instruction-based workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-7b-instruct-v0.3":{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-large-3-675b-instruct-2512":{"id":"mistralai/mistral-large-3-675b-instruct-2512","name":"Mistral Large 3 675B Instruct 2512","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-medium-3-instruct":{"id":"mistralai/mistral-medium-3-instruct","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"release_date":"2025-09-25","last_updated":"2025-09-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-medium-3.5-128b":{"id":"mistralai/mistral-medium-3.5-128b","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-nemotron":{"id":"mistralai/mistral-nemotron","name":"mistral-nemotron","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-11","last_updated":"2025-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mistral-small-4-119b-2603":{"id":"mistralai/mistral-small-4-119b-2603","name":"mistral-small-4-119b-2603","description":"Efficient Mistral model for fast chat, extraction, and production assistants","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mixtral-8x22b-instruct":{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":13108},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/mistralai/mixtral-8x7b-instruct":{"id":"mistralai/mixtral-8x7b-instruct","name":"Mistral: Mixtral 8x7B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2023-12-10","last_updated":"2026-03-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/moonshotai/kimi-k2-instruct-0905":{"id":"moonshotai/kimi-k2-instruct-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-3-content-safety":{"id":"nvidia/nemotron-3-content-safety","name":"nemotron-3-content-safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"nemotron-3-nano-30b-a3b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-12","last_updated":"2024-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":-1,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.8},"sourceProvider":"nvidia"},"nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.15},"sourceProvider":"nvidia"},"nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-content-safety-reasoning-4b":{"id":"nvidia/nemotron-content-safety-reasoning-4b","name":"nemotron-content-safety-reasoning-4b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":false,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-mini-4b-instruct":{"id":"nvidia/nemotron-mini-4b-instruct","name":"nemotron-mini-4b-instruct","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-08-21","last_updated":"2024-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-nano-12b-v2-vl":{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nemotron Nano 12B v2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nemotron-voicechat":{"id":"nvidia/nemotron-voicechat","name":"nemotron-voicechat","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nv-embed-v1":{"id":"nvidia/nv-embed-v1","name":"nv-embed-v1","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-06-07","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nv-embedcode-7b-v1":{"id":"nvidia/nv-embedcode-7b-v1","name":"nv-embedcode-7b-v1","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-03-17","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":2048},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/nvidia-nemotron-nano-9b-v2":{"id":"nvidia/nvidia-nemotron-nano-9b-v2","name":"nvidia-nemotron-nano-9b-v2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT-OSS-120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-04","last_updated":"2025-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/openai/whisper-large-v3":{"id":"openai/whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2023-09","release_date":"2023-09-01","last_updated":"2025-09-05","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen-image":{"id":"qwen/qwen-image","name":"Qwen Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen-image-edit":{"id":"qwen/qwen-image-edit","name":"Qwen Image Edit","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen2.5-coder-32b-instruct":{"id":"qwen/qwen2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32b Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-06","last_updated":"2024-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen3-coder-480b-a35b-instruct":{"id":"qwen/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":66536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next-80B-A3B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2024-12-01","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/rerank-qa-mistral-4b":{"id":"nvidia/rerank-qa-mistral-4b","name":"rerank-qa-mistral-4b","description":"Reranking model for improving retrieval quality in search and recommendation systems","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-03-17","last_updated":"2025-01-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/riva-translate-4b-instruct-v1.1":{"id":"nvidia/riva-translate-4b-instruct-v1.1","name":"riva-translate-4b-instruct-v1_1","description":"Translation model for multilingual conversion, localization, and cross-language workflows","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-12","last_updated":"2025-12-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/sarvamai/sarvam-m":{"id":"sarvamai/sarvam-m","name":"sarvam-m","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/sparsedrive":{"id":"nvidia/sparsedrive","name":"sparsedrive","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-03-18","last_updated":"2025-07-20","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/stepfun-ai/step-3.5-flash":{"id":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/stepfun-ai/step-3.7-flash":{"id":"stepfun-ai/step-3.7-flash","name":"Step 3.7 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/streampetr":{"id":"nvidia/streampetr","name":"streampetr","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/studiovoice":{"id":"nvidia/studiovoice","name":"studiovoice","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-03","last_updated":"2025-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/synthetic-video-detector":{"id":"nvidia/synthetic-video-detector","name":"synthetic-video-detector","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["video"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/upstage/solar-10.7b-instruct":{"id":"upstage/solar-10.7b-instruct","name":"solar-10.7b-instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-06-05","last_updated":"2025-04-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/usdcode":{"id":"nvidia/usdcode","name":"usdcode","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-01","last_updated":"2026-01-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/usdvalidate":{"id":"nvidia/usdvalidate","name":"usdvalidate","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-07-24","last_updated":"2025-01-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"nvidia/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"nvidia"},"ofox/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"ofox"},"ofox/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"ofox"},"ofox/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"ofox"},"ofox/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"ofox"},"ofox/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://api.ofox.ai/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"ofox"},"ofox/bailian/qwen-flash":{"id":"bailian/qwen-flash","name":"Qwen Flash","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.022,"output":0.22,"cache_read":0.0043,"cache_write":0.027},"sourceProvider":"ofox"},"ofox/bailian/qwen-max":{"id":"bailian/qwen-max","name":"Qwen Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-03","last_updated":"2025-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.35,"output":1.38,"cache_read":0.069},"sourceProvider":"ofox"},"ofox/bailian/qwen-plus":{"id":"bailian/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"sourceProvider":"ofox"},"ofox/bailian/qwen-turbo":{"id":"bailian/qwen-turbo","name":"Qwen Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-11-01","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.05,"output":0.09,"cache_read":0.0086},"sourceProvider":"ofox"},"ofox/bailian/qwen-vl-max":{"id":"bailian/qwen-vl-max","name":"Qwen-VL Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-04-08","last_updated":"2025-08-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.23,"output":0.58,"cache_read":0.046},"sourceProvider":"ofox"},"ofox/bailian/qwen3-coder-flash":{"id":"bailian/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2.5,"cache_read":0.06,"cache_write":0.27},"sourceProvider":"ofox"},"ofox/bailian/qwen3-coder-next":{"id":"bailian/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.2,"output":1.5},"sourceProvider":"ofox"},"ofox/bailian/qwen3-coder-plus":{"id":"bailian/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.8,"output":9,"cache_read":0.2,"cache_write":1},"sourceProvider":"ofox"},"ofox/bailian/qwen3-max":{"id":"bailian/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.36,"output":1.43,"cache_read":0.072},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-122b-a10b":{"id":"bailian/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.29,"output":2.29,"cache_read":0.29},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-27b":{"id":"bailian/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":2.05,"cache_read":0.29},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-35b-a3b":{"id":"bailian/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":1.83,"cache_read":0.29},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-397b-a17b":{"id":"bailian/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.55,"output":3.5,"cache_read":0.55},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-flash":{"id":"bailian/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"cache_write":0.125},"sourceProvider":"ofox"},"ofox/bailian/qwen3.5-plus":{"id":"bailian/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.4},"sourceProvider":"ofox"},"ofox/bailian/qwen3.6-27b":{"id":"bailian/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.6,"output":3.6},"sourceProvider":"ofox"},"ofox/bailian/qwen3.6-flash":{"id":"bailian/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":0.31},"sourceProvider":"ofox"},"ofox/bailian/qwen3.6-max-preview":{"id":"bailian/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":2.15,"output":12.86,"cache_read":0.2,"cache_write":1.17},"sourceProvider":"ofox"},"ofox/bailian/qwen3.6-plus":{"id":"bailian/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"sourceProvider":"ofox"},"ofox/bailian/qwen3.7-max":{"id":"bailian/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"ofox"},"ofox/bailian/qwen3.7-plus":{"id":"bailian/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"ofox"},"ofox/bailian/qwen3.8-27b":{"id":"bailian/qwen3.8-27b","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1131072,"output":131072},"cost":{"input":0.45,"output":3.2,"cache_read":0.05,"cache_write":0.5625},"sourceProvider":"ofox"},"ofox/bailian/qwen3.8-max":{"id":"bailian/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32000},"cost":{"input":0.29,"output":0.43,"cache_read":0.06},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"status":"beta","cost":{"input":0.44,"output":1.32,"cache_read":0.014},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-pro-0423":{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek V4 Pro 0423","description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"ofox"},"ofox/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"ofox"},"ofox/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":1,"input_audio":1},"sourceProvider":"ofox"},"ofox/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.025,"cache_write":1,"input_audio":0.3},"sourceProvider":"ofox"},"ofox/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":4.5},"sourceProvider":"ofox"},"ofox/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":1},"sourceProvider":"ofox"},"ofox/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1,"input_audio":0.5},"sourceProvider":"ofox"},"ofox/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":4.5},"sourceProvider":"ofox"},"ofox/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083,"input_audio":3},"sourceProvider":"ofox"},"ofox/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083},"sourceProvider":"ofox"},"ofox/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"input_audio":1.5},"sourceProvider":"ofox"},"ofox/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google","api":"https://api.ofox.ai/gemini/v1beta"},"cost":{"input":0.75,"output":3.75,"cache_read":0.075,"cache_write":0.0415,"input_audio":1.5},"sourceProvider":"ofox"},"ofox/minimax/m2-her":{"id":"minimax/m2-her","name":"MiniMax-M2 Her","description":"MiniMax M2 variant tuned for conversational and character-driven agent interactions","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131000},"cost":{"input":0.3,"output":1.2},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.1-lightning":{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax-M2.1 Lightning","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.5-lightning":{"id":"minimax/minimax-m2.5-lightning","name":"MiniMax-M2.5 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"ofox"},"ofox/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"sourceProvider":"ofox"},"ofox/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"ofox"},"ofox/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"ofox"},"ofox/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"ofox"},"ofox/moonshotai/kimi-k2.7-code-highspeed":{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"ofox"},"ofox/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"ofox"},"ofox/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"ofox"},"ofox/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"ofox"},"ofox/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"ofox"},"ofox/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"ofox"},"ofox/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"ofox"},"ofox/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32768},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"ofox"},"ofox/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.05,"output":0.4,"cache_read":0.01},"sourceProvider":"ofox"},"ofox/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"ofox"},"ofox/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"ofox"},"ofox/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"ofox"},"ofox/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"sourceProvider":"ofox"},"ofox/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"sourceProvider":"ofox"},"ofox/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.18},"sourceProvider":"ofox"},"ofox/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"ofox"},"ofox/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"ofox"},"ofox/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"ofox"},"ofox/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":30,"output":180},"sourceProvider":"ofox"},"ofox/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"ofox"},"ofox/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"ofox"},"ofox/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"ofox"},"ofox/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://api.ofox.ai/v1"},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-1-6":{"id":"volcengine/doubao-seed-1-6","name":"Seed 1.6","description":"ByteDance Seed model for long-context reasoning, instruction following, and tool-assisted tasks","family":"seed","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-1-6-flash":{"id":"volcengine/doubao-seed-1-6-flash","name":"Seed 1.6 Flash","description":"Low-latency ByteDance Seed model for high-throughput chat, extraction, and lightweight tool use","family":"seed","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.03,"output":0.22,"cache_read":0.0043},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-1-6-vision":{"id":"volcengine/doubao-seed-1-6-vision","name":"Seed 1.6 Vision","description":"ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks","family":"seed","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.12,"output":1.15,"cache_read":0.023},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-1-8":{"id":"volcengine/doubao-seed-1-8","name":"Seed 1.8","description":"ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows","family":"seed","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-28","last_updated":"2025-12-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.12,"output":0.29,"cache_read":0.023},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.0-code":{"id":"volcengine/doubao-seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.0-lite":{"id":"volcengine/doubao-seed-2.0-lite","name":"Seed 2.0 Lite","description":"Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.13,"output":0.76,"cache_read":0.03,"cache_write":0.0024},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.0-mini":{"id":"volcengine/doubao-seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.06,"output":0.56,"cache_read":0.02,"cache_write":0.0024},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.0-pro":{"id":"volcengine/doubao-seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.67,"output":3.36,"cache_read":0.14,"cache_write":0.0024},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.1-pro":{"id":"volcengine/doubao-seed-2.1-pro","name":"Seed 2.1 Pro","description":"Flagship ByteDance Seed 2.1 model for complex multimodal reasoning, coding, and agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.7072,"output":3.536,"cache_read":0.1416,"cache_write":0.002},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-2.1-turbo":{"id":"volcengine/doubao-seed-2.1-turbo","name":"Seed 2.1 Turbo","description":"Faster ByteDance Seed 2.1 model for multimodal reasoning and latency-sensitive agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3536,"output":1.7696,"cache_read":0.068,"cache_write":0.0019},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-character":{"id":"volcengine/doubao-seed-character","name":"Seed Character","description":"ByteDance Seed model optimized for character-driven dialogue and consistent conversational behavior","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.177,"output":0.884,"cache_read":0.024,"cache_write":0.0025},"sourceProvider":"ofox"},"ofox/volcengine/doubao-seed-evolving":{"id":"volcengine/doubao-seed-evolving","name":"Seed Evolving","description":"Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.884,"output":4.42,"cache_read":0.177,"cache_write":0.0025},"sourceProvider":"ofox"},"ofox/x-ai/grok-4.1-fast":{"id":"x-ai/grok-4.1-fast","name":"Grok 4.1 Fast","description":"xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"ofox"},"ofox/x-ai/grok-4.20":{"id":"x-ai/grok-4.20","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":4,"output":12,"cache_read":0.4},"sourceProvider":"ofox"},"ofox/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"ofox"},"ofox/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"ofox"},"ofox/x-ai/grok-4.6":{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"ofox"},"ofox/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.4,"output":1.9,"cache_read":0.11},"sourceProvider":"ofox"},"ofox/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.08},"sourceProvider":"ofox"},"ofox/z-ai/glm-4.7-flashx":{"id":"z-ai/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.072,"output":0.43,"cache_read":0.015},"sourceProvider":"ofox"},"ofox/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"ofox"},"ofox/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"ofox"},"ofox/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"ofox"},"ofox/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.98,"output":3.08,"cache_read":0.182},"sourceProvider":"ofox"},"ofox/z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"sourceProvider":"ofox"},"ofox/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"ofox"},"ollama-cloud/deepseek-v4-flash":{"id":"ollama-cloud/deepseek-v4-flash","name":"deepseek-v4-flash","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"sourceProvider":"ollama-cloud"},"ollama-cloud/deepseek-v4-flash:0731":{"id":"ollama-cloud/deepseek-v4-flash:0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"sourceProvider":"ollama-cloud"},"ollama-cloud/deepseek-v4-pro":{"id":"ollama-cloud/deepseek-v4-pro","name":"deepseek-v4-pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"sourceProvider":"ollama-cloud"},"ollama-cloud/gemma4:31b":{"id":"ollama-cloud/gemma4:31b","name":"gemma4:31b","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"ollama-cloud"},"ollama-cloud/glm-5.1":{"id":"ollama-cloud/glm-5.1","name":"glm-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"release_date":"2026-03-27","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/glm-5.2":{"id":"ollama-cloud/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":976000,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/gpt-oss:120b":{"id":"ollama-cloud/gpt-oss:120b","name":"gpt-oss:120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"sourceProvider":"ollama-cloud"},"ollama-cloud/gpt-oss:20b":{"id":"ollama-cloud/gpt-oss:20b","name":"gpt-oss:20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"release_date":"2025-08-05","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"sourceProvider":"ollama-cloud"},"ollama-cloud/kimi-k2.5":{"id":"ollama-cloud/kimi-k2.5","name":"kimi-k2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"ollama-cloud"},"ollama-cloud/kimi-k2.6":{"id":"ollama-cloud/kimi-k2.6","name":"kimi-k2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"ollama-cloud"},"ollama-cloud/kimi-k2.7-code":{"id":"ollama-cloud/kimi-k2.7-code","name":"kimi-k2.7-code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"ollama-cloud"},"ollama-cloud/kimi-k3":{"id":"ollama-cloud/kimi-k3","name":"kimi-k3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/minimax-m2.5":{"id":"ollama-cloud/minimax-m2.5","name":"minimax-m2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/minimax-m2.7":{"id":"ollama-cloud/minimax-m2.7","name":"minimax-m2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"sourceProvider":"ollama-cloud"},"ollama-cloud/minimax-m3":{"id":"ollama-cloud/minimax-m3","name":"minimax-m3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/mistral-large-3:675b":{"id":"ollama-cloud/mistral-large-3:675b","name":"mistral-large-3:675b","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2025-12-02","last_updated":"2026-01-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"ollama-cloud"},"ollama-cloud/nemotron-3-nano:30b":{"id":"ollama-cloud/nemotron-3-nano:30b","name":"nemotron-3-nano:30b","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"sourceProvider":"ollama-cloud"},"ollama-cloud/nemotron-3-super":{"id":"ollama-cloud/nemotron-3-super","name":"nemotron-3-super","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"sourceProvider":"ollama-cloud"},"ollama-cloud/nemotron-3-ultra":{"id":"ollama-cloud/nemotron-3-ultra","name":"nemotron-3-ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"sourceProvider":"ollama-cloud"},"ollama-cloud/qwen3.5:397b":{"id":"ollama-cloud/qwen3.5:397b","name":"qwen3.5:397b","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"release_date":"2026-02-15","last_updated":"2026-02-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"sourceProvider":"ollama-cloud"},"openai/chatgpt-image-latest":{"id":"openai/chatgpt-image-latest","name":"chatgpt-image-latest","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":0,"input":0,"output":0},"sourceProvider":"openai"},"openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"status":"deprecated","cost":{"input":0.5,"output":1.5,"cache_read":0},"sourceProvider":"openai"},"openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"status":"deprecated","cost":{"input":30,"output":60},"sourceProvider":"openai"},"openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"openai"},"openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"openai"},"openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"openai"},"openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"openai"},"openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openai"},"openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":5,"output":15},"sourceProvider":"openai"},"openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openai"},"openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openai"},"openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"openai"},"openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"openai"},"openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"openai"},"openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"openai"},"openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"openai"},"openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"openai"},"openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openai"},"openai/gpt-5.2-chat-latest":{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openai"},"openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"openai"},"openai/gpt-5.3-chat-latest":{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openai"},"openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openai"},"openai/gpt-5.3-codex-spark":{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":100000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openai"},"openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"openai"},"openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"openai"},"openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"openai"},"openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"openai"},"openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"openai"},"openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"openai"},"openai/gpt-5.6":{"id":"openai/gpt-5.6","name":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":60,"cache_read":1,"cache_write":12.5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"openai"},"openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"openai"},"openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":10,"output":60,"cache_read":1,"cache_write":12.5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"openai"},"openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":5},"provider":{"body":{"service_tier":"priority"}}},"pro":{"provider":{"body":{"reasoning":{"mode":"pro"}}}}}},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openai"},"openai/gpt-image-1":{"id":"openai/gpt-image-1","name":"gpt-image-1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"input":0,"output":0},"status":"deprecated","sourceProvider":"openai"},"openai/gpt-image-1-mini":{"id":"openai/gpt-image-1-mini","name":"gpt-image-1-mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":0,"input":0,"output":0},"sourceProvider":"openai"},"openai/gpt-image-1.5":{"id":"openai/gpt-image-1.5","name":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":0,"input":0,"output":0},"sourceProvider":"openai"},"openai/gpt-image-2":{"id":"openai/gpt-image-2","name":"gpt-image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"input":0,"output":0},"cost":{"input":5,"output":30,"cache_read":1.25},"sourceProvider":"openai"},"openai/gpt-realtime-2.1":{"id":"openai/gpt-realtime-2.1","name":"GPT-Realtime-2.1","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2024-09-30","release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","audio","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"input":96000,"output":32000},"cost":{"input":4,"output":24,"cache_read":0.4,"input_audio":32,"output_audio":64},"sourceProvider":"openai"},"openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"openai"},"openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":150,"output":600},"sourceProvider":"openai"},"openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"openai"},"openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"openai"},"openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"openai"},"openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"openai"},"openai/text-embedding-3-large":{"id":"openai/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-01","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.13,"output":0},"sourceProvider":"openai"},"openai/text-embedding-3-small":{"id":"openai/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2024-01","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"sourceProvider":"openai"},"openai/text-embedding-ada-002":{"id":"openai/text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2022-12","release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.1,"output":0},"sourceProvider":"openai"},"opencode-go/deepseek-v4-flash":{"id":"opencode-go/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"opencode-go"},"opencode-go/deepseek-v4-flash-vision-exp":{"id":"opencode-go/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"opencode-go"},"opencode-go/deepseek-v4-pro":{"id":"opencode-go/deepseek-v4-pro","name":"DeepSeek V4 Pro (New)","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.66,"output":1.98,"cache_read":0.022},"sourceProvider":"opencode-go"},"opencode-go/glm-5":{"id":"opencode-go/glm-5","name":"GLM-5","description":"Legacy model retained for compatibility with older integrations","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":32768},"status":"deprecated","cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"opencode-go"},"opencode-go/glm-5.1":{"id":"opencode-go/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":32768},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"opencode-go"},"opencode-go/glm-5.2":{"id":"opencode-go/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"opencode-go"},"opencode-go/glm-5.3":{"id":"opencode-go/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"opencode-go"},"opencode-go/gpt-5.6-luna":{"id":"opencode-go/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"opencode-go"},"opencode-go/grok-4.5":{"id":"opencode-go/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"opencode-go"},"opencode-go/hy3":{"id":"opencode-go/hy3","name":"Hy3 (8x usage)","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.0175,"output":0.0725,"cache_read":0.004375},"sourceProvider":"opencode-go"},"opencode-go/kimi-k2.5":{"id":"opencode-go/kimi-k2.5","name":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"opencode-go"},"opencode-go/kimi-k2.6":{"id":"opencode-go/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"opencode-go"},"opencode-go/kimi-k2.7-code":{"id":"opencode-go/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"opencode-go"},"opencode-go/kimi-k3":{"id":"opencode-go/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"opencode-go"},"opencode-go/mimo-v2-omni":{"id":"opencode-go/mimo-v2-omni","name":"MiMo V2 Omni","description":"Legacy model retained for compatibility with older integrations","family":"mimo-v2-omni","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"status":"deprecated","cost":{"input":0.4,"output":2,"cache_read":0.08},"sourceProvider":"opencode-go"},"opencode-go/mimo-v2-pro":{"id":"opencode-go/mimo-v2-pro","name":"MiMo V2 Pro","description":"Legacy model retained for compatibility with older integrations","family":"mimo-v2-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"status":"deprecated","cost":{"input":1,"output":3,"cache_read":0.2,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"opencode-go"},"opencode-go/mimo-v2.5":{"id":"opencode-go/mimo-v2.5","name":"MiMo V2.5","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo-v2.5","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"opencode-go"},"opencode-go/mimo-v2.5-pro":{"id":"opencode-go/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo-v2.5-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"opencode-go"},"opencode-go/minimax-m2.5":{"id":"opencode-go/minimax-m2.5","name":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","family":"minimax-m2.5","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"opencode-go"},"opencode-go/minimax-m2.7":{"id":"opencode-go/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax-m2.7","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"opencode-go"},"opencode-go/minimax-m3":{"id":"opencode-go/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"tiers":[{"input":0.6,"output":2.4,"cache_read":0.12,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.6,"output":2.4,"cache_read":0.12}},"sourceProvider":"opencode-go"},"opencode-go/muse-spark-1.2-contributor":{"id":"opencode-go/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"opencode-go"},"opencode-go/ox-alpha-free":{"id":"opencode-go/ox-alpha-free","name":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode-go"},"opencode-go/qwen3.5-plus":{"id":"opencode-go/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Legacy model retained for compatibility with older integrations","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"opencode-go"},"opencode-go/qwen3.6-plus":{"id":"opencode-go/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"opencode-go"},"opencode-go/qwen3.7-max":{"id":"opencode-go/qwen3.7-max","name":"Qwen3.7 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"qwen3.7-max","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"opencode-go"},"opencode-go/qwen3.7-plus":{"id":"opencode-go/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.7-plus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":1.5}},"sourceProvider":"opencode-go"},"opencode-go/qwen3.8-max":{"id":"opencode-go/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter multimodal flagship for coding, professional work, and long-horizon agentic workflows","family":"qwen3.8-max","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"opencode-go"},"opencode/big-pickle":{"id":"opencode/big-pickle","name":"Big Pickle","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"big-pickle","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-10-17","last_updated":"2025-10-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":160000,"output":32000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"opencode"},"opencode/claude-3-5-haiku":{"id":"opencode/claude-3-5-haiku","name":"Claude Haiku 3.5","description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.8,"output":4,"cache_read":0.08,"cache_write":1},"sourceProvider":"opencode"},"opencode/claude-fable-5":{"id":"opencode/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"opencode"},"opencode/claude-haiku-4-5":{"id":"opencode/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"opencode"},"opencode/claude-opus-4-1":{"id":"opencode/claude-opus-4-1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"opencode"},"opencode/claude-opus-4-5":{"id":"opencode/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opencode"},"opencode/claude-opus-4-6":{"id":"opencode/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opencode"},"opencode/claude-opus-4-7":{"id":"opencode/claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opencode"},"opencode/claude-opus-4-8":{"id":"opencode/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opencode"},"opencode/claude-opus-5":{"id":"opencode/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opencode"},"opencode/claude-sonnet-4":{"id":"opencode/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"opencode"},"opencode/claude-sonnet-4-5":{"id":"opencode/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"opencode"},"opencode/claude-sonnet-4-6":{"id":"opencode/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"opencode"},"opencode/claude-sonnet-5":{"id":"opencode/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"opencode"},"opencode/deepseek-v4-flash":{"id":"opencode/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"opencode"},"opencode/deepseek-v4-flash-free":{"id":"opencode/deepseek-v4-flash-free","name":"DeepSeek V4 Flash Free","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/deepseek-v4-pro":{"id":"opencode/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.84,"cache_read":0.145},"sourceProvider":"opencode"},"opencode/gemini-3-flash":{"id":"opencode/gemini-3-flash","name":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"opencode"},"opencode/gemini-3-pro":{"id":"opencode/gemini-3-pro","name":"Gemini 3 Pro","description":"Legacy model retained for compatibility with older integrations","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/google"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"opencode"},"opencode/gemini-3.1-pro":{"id":"opencode/gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"opencode"},"opencode/gemini-3.5-flash":{"id":"opencode/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"opencode"},"opencode/gemini-3.5-flash-lite":{"id":"opencode/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"opencode"},"opencode/gemini-3.6-flash":{"id":"opencode/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"opencode"},"opencode/gemini-3.7-flash":{"id":"opencode/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/google"},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"opencode"},"opencode/glm-4.6":{"id":"opencode/glm-4.6","name":"GLM-4.6","description":"Legacy model retained for compatibility with older integrations","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0.6,"output":2.2,"cache_read":0.1},"sourceProvider":"opencode"},"opencode/glm-4.7":{"id":"opencode/glm-4.7","name":"GLM-4.7","description":"Legacy model retained for compatibility with older integrations","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0.6,"output":2.2,"cache_read":0.1},"sourceProvider":"opencode"},"opencode/glm-4.7-free":{"id":"opencode/glm-4.7-free","name":"GLM-4.7 Free","description":"Legacy model retained for compatibility with older integrations","family":"glm-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/glm-5":{"id":"opencode/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"opencode"},"opencode/glm-5-free":{"id":"opencode/glm-5-free","name":"GLM-5 Free","description":"Legacy model retained for compatibility with older integrations","family":"glm-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/glm-5.1":{"id":"opencode/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"opencode"},"opencode/glm-5.2":{"id":"opencode/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"opencode"},"opencode/gpt-5":{"id":"opencode/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"sourceProvider":"opencode"},"opencode/gpt-5-codex":{"id":"opencode/gpt-5-codex","name":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"sourceProvider":"opencode"},"opencode/gpt-5-nano":{"id":"opencode/gpt-5-nano","name":"GPT-5 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"opencode"},"opencode/gpt-5.1":{"id":"opencode/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"sourceProvider":"opencode"},"opencode/gpt-5.1-codex":{"id":"opencode/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.07,"output":8.5,"cache_read":0.107},"sourceProvider":"opencode"},"opencode/gpt-5.1-codex-max":{"id":"opencode/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"opencode"},"opencode/gpt-5.1-codex-mini":{"id":"opencode/gpt-5.1-codex-mini","name":"GPT-5.1 Codex Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"opencode"},"opencode/gpt-5.2":{"id":"opencode/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opencode"},"opencode/gpt-5.2-codex":{"id":"opencode/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opencode"},"opencode/gpt-5.3-codex":{"id":"opencode/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opencode"},"opencode/gpt-5.3-codex-spark":{"id":"opencode/gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex-spark","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opencode"},"opencode/gpt-5.4":{"id":"opencode/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"opencode"},"opencode/gpt-5.4-mini":{"id":"opencode/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"opencode"},"opencode/gpt-5.4-nano":{"id":"opencode/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"opencode"},"opencode/gpt-5.4-pro":{"id":"opencode/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":30,"output":180,"cache_read":30},"sourceProvider":"opencode"},"opencode/gpt-5.5":{"id":"opencode/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"opencode"},"opencode/gpt-5.5-pro":{"id":"opencode/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":30,"output":180,"cache_read":30},"sourceProvider":"opencode"},"opencode/gpt-5.6-luna":{"id":"opencode/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"opencode"},"opencode/gpt-5.6-sol":{"id":"opencode/gpt-5.6-sol","name":"GPT-5.6 Sol (50% Off)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"sourceProvider":"opencode"},"opencode/gpt-5.6-terra":{"id":"opencode/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"sourceProvider":"opencode"},"opencode/grok-4.5":{"id":"opencode/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"opencode"},"opencode/grok-4.6":{"id":"opencode/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"opencode"},"opencode/grok-build-0.1":{"id":"opencode/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"opencode"},"opencode/grok-code":{"id":"opencode/grok-code","name":"Grok Code Fast 1","description":"Legacy model retained for compatibility with older integrations","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-20","last_updated":"2025-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"opencode"},"opencode/hy3-free":{"id":"opencode/hy3-free","name":"Hy3 Free","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hy3-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":190000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/hy3-preview-free":{"id":"opencode/hy3-preview-free","name":"Hy3 preview Free","description":"Legacy model retained for compatibility with older integrations","family":"hy3-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/kimi-k2":{"id":"opencode/kimi-k2","name":"Kimi K2","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2.5,"cache_read":0.4},"sourceProvider":"opencode"},"opencode/kimi-k2-thinking":{"id":"opencode/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Legacy model retained for compatibility with older integrations","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2025-09-05","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.4,"output":2.5,"cache_read":0.4},"sourceProvider":"opencode"},"opencode/kimi-k2.5":{"id":"opencode/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.6,"output":3,"cache_read":0.08},"sourceProvider":"opencode"},"opencode/kimi-k2.5-free":{"id":"opencode/kimi-k2.5-free","name":"Kimi K2.5 Free","description":"Legacy model retained for compatibility with older integrations","family":"kimi-free","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/kimi-k2.6":{"id":"opencode/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"opencode"},"opencode/kimi-k2.7-code":{"id":"opencode/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"opencode"},"opencode/kimi-k3":{"id":"opencode/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"opencode"},"opencode/laguna-s-2.1-free":{"id":"opencode/laguna-s-2.1-free","name":"Laguna S 2.1 Free","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/ling-2.6-flash-free":{"id":"opencode/ling-2.6-flash-free","name":"Ling 2.6 Flash Free","description":"Legacy model retained for compatibility with older integrations","family":"ling-flash-free","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":32800},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"opencode"},"opencode/ling-3.0-flash-free":{"id":"opencode/ling-3.0-flash-free","name":"Ling-3.0-flash Free","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/ling-3.0-tiny-free":{"id":"opencode/ling-3.0-tiny-free","name":"Ling-3.0-tiny Free","description":"Compact MoE model for responsive agents, instruction following, and multi-turn conversations","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"opencode"},"opencode/longcat-2.0-free":{"id":"opencode/longcat-2.0-free","name":"LongCat-2.0 Free","description":"Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/mimo-v2-flash-free":{"id":"opencode/mimo-v2-flash-free","name":"MiMo V2 Flash Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-flash-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/mimo-v2-omni-free":{"id":"opencode/mimo-v2-omni-free","name":"MiMo V2 Omni Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-omni-free","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text","image","audio","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":64000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/mimo-v2-pro-free":{"id":"opencode/mimo-v2-pro-free","name":"MiMo V2 Pro Free","description":"Legacy model retained for compatibility with older integrations","family":"mimo-pro-free","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":64000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/mimo-v2.5-free":{"id":"opencode/mimo-v2.5-free","name":"MiMo V2.5 Free","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo-v2.5-free","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/minimax-m2.1":{"id":"opencode/minimax-m2.1","name":"MiniMax-M2.1","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0.3,"output":1.2,"cache_read":0.1},"sourceProvider":"opencode"},"opencode/minimax-m2.1-free":{"id":"opencode/minimax-m2.1-free","name":"MiniMax-M2.1 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/minimax-m2.5":{"id":"opencode/minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"opencode"},"opencode/minimax-m2.5-free":{"id":"opencode/minimax-m2.5-free","name":"MiniMax-M2.5 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/minimax-m2.7":{"id":"opencode/minimax-m2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"opencode"},"opencode/minimax-m3":{"id":"opencode/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"opencode"},"opencode/minimax-m3-free":{"id":"opencode/minimax-m3-free","name":"MiniMax-M3 Free","description":"Legacy model retained for compatibility with older integrations","family":"minimax-m3-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/muse-spark-1.2":{"id":"opencode/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"opencode"},"opencode/muse-spark-1.2-contributor-free":{"id":"opencode/muse-spark-1.2-contributor-free","name":"Muse Spark 1.2 Free","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse-free","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"provider":{"npm":"@ai-sdk/openai"},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/nemotron-3-super-free":{"id":"opencode/nemotron-3-super-free","name":"Nemotron 3 Super Free","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/nemotron-3-ultra-free":{"id":"opencode/nemotron-3-ultra-free","name":"Nemotron 3 Ultra Free","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-02","release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/nemotron-3.5-lightning-free":{"id":"opencode/nemotron-3.5-lightning-free","name":"Nemotron 3.5 Lightning Free","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/north-mini-code-free":{"id":"opencode/north-mini-code-free","name":"North Mini Code Free","description":"Cohere coding model for practical software engineering and agentic edits","family":"north-free","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-09-23","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"opencode"},"opencode/qwen3-coder":{"id":"opencode/qwen3-coder","name":"Qwen3 Coder","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.45,"output":1.8},"sourceProvider":"opencode"},"opencode/qwen3.5-plus":{"id":"opencode/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"opencode"},"opencode/qwen3.6-plus":{"id":"opencode/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"sourceProvider":"opencode"},"opencode/qwen3.6-plus-free":{"id":"opencode/qwen3.6-plus-free","name":"Qwen3.6 Plus Free","description":"Legacy model retained for compatibility with older integrations","family":"qwen-free","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic"},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"opencode/ring-2.6-1t-free":{"id":"opencode/ring-2.6-1t-free","name":"Ring 2.6 1T Free","description":"Legacy model retained for compatibility with older integrations","family":"ring-1t-free","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":66000},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"opencode"},"opencode/trinity-large-preview-free":{"id":"opencode/trinity-large-preview-free","name":"Trinity Large Preview","description":"Legacy model retained for compatibility with older integrations","family":"trinity","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-01-27","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0,"output":0},"sourceProvider":"opencode"},"opencode/x-preview-f-free":{"id":"opencode/x-preview-f-free","name":"Ox Alpha Free (Unlimited)","description":"Stealth reasoning model for coding, agentic tasks, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"opencode"},"openrouter/~anthropic/claude-fable-latest":{"id":"~anthropic/claude-fable-latest","name":"Claude Fable Latest","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"openrouter"},"openrouter/~anthropic/claude-haiku-latest":{"id":"~anthropic/claude-haiku-latest","name":"Anthropic Claude Haiku Latest","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"openrouter"},"openrouter/~anthropic/claude-opus-latest":{"id":"~anthropic/claude-opus-latest","name":"Claude Opus Latest","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"openrouter"},"openrouter/~anthropic/claude-sonnet-latest":{"id":"~anthropic/claude-sonnet-latest","name":"Anthropic Claude Sonnet Latest","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"openrouter"},"openrouter/~deepseek/deepseek-v4-flash-latest":{"id":"~deepseek/deepseek-v4-flash-latest","name":"DeepSeek V4 Flash Latest","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-01","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1310720,"output":1048576},"cost":{"input":0.04,"output":0.08,"cache_read":0.008},"sourceProvider":"openrouter"},"openrouter/~google/gemini-flash-latest":{"id":"~google/gemini-flash-latest","name":"Google Gemini Flash Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"reasoning":1.875,"cache_read":0.0375,"cache_write":0.020833},"sourceProvider":"openrouter"},"openrouter/~google/gemini-pro-latest":{"id":"~google/gemini-pro-latest","name":"Google Gemini Pro Latest","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["audio","pdf","image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/~moonshotai/kimi-latest":{"id":"~moonshotai/kimi-latest","name":"MoonshotAI Kimi Latest","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":974842},"cost":{"input":2.6,"output":13,"cache_read":0.29},"sourceProvider":"openrouter"},"openrouter/~openai/gpt-latest":{"id":"~openai/gpt-latest","name":"OpenAI GPT Latest","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openrouter"},"openrouter/~openai/gpt-mini-latest":{"id":"~openai/gpt-mini-latest","name":"OpenAI GPT Mini Latest","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"openrouter"},"openrouter/~x-ai/grok-latest":{"id":"~x-ai/grok-latest","name":"Grok Latest","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":1000000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"openrouter"},"openrouter/~z-ai/glm-latest":{"id":"~z-ai/glm-latest","name":"GLM Latest","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"openrouter"},"openrouter/aion-labs/aion-2.0":{"id":"aion-labs/aion-2.0","name":"Aion-2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.8,"output":1.6,"cache_read":0.2},"sourceProvider":"openrouter"},"openrouter/aion-labs/aion-3.0":{"id":"aion-labs/aion-3.0","name":"Aion-3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":3,"output":6,"cache_read":0.75},"sourceProvider":"openrouter"},"openrouter/aion-labs/aion-3.0-mini":{"id":"aion-labs/aion-3.0-mini","name":"Aion-3.0-Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.7,"output":1.4,"cache_read":0.18},"sourceProvider":"openrouter"},"openrouter/aion-labs/aion-rp-llama-3.1-8b":{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"Aion-RP 1.0 (8B)","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12-31","release_date":"2025-02-04","last_updated":"2025-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.8,"output":1.6},"sourceProvider":"openrouter"},"openrouter/allenai/olmo-3-32b-think":{"id":"allenai/olmo-3-32b-think","name":"Olmo 3 32B Think","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"allenai","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-11-21","last_updated":"2025-11-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.15,"output":0.5},"sourceProvider":"openrouter"},"openrouter/amazon/nova-2-lite-v1":{"id":"amazon/nova-2-lite-v1","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65535},"cost":{"input":0.3,"output":2.5},"sourceProvider":"openrouter"},"openrouter/amazon/nova-lite-v1":{"id":"amazon/nova-lite-v1","name":"Nova Lite 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.06,"output":0.24},"sourceProvider":"openrouter"},"openrouter/amazon/nova-micro-v1":{"id":"amazon/nova-micro-v1","name":"Nova Micro 1.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":5120},"cost":{"input":0.035,"output":0.14},"sourceProvider":"openrouter"},"openrouter/amazon/nova-premier-v1":{"id":"amazon/nova-premier-v1","name":"Nova Premier 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-31","last_updated":"2025-10-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":2.5,"output":12.5,"cache_read":0.625},"sourceProvider":"openrouter"},"openrouter/amazon/nova-pro-v1":{"id":"amazon/nova-pro-v1","name":"Nova Pro 1.0","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-10-31","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":5120},"cost":{"input":0.8,"output":3.2},"sourceProvider":"openrouter"},"openrouter/anthracite-org/magnum-v4-72b":{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":4096},"cost":{"input":3,"output":5},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-3-haiku":{"id":"anthropic/claude-3-haiku","name":"Claude 3 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":31999}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":10,"output":37.5,"cache_read":1,"cache_write":12.5}},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.7-fast":{"id":"anthropic/claude-opus-4.7-fast","name":"Claude Opus 4.7 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-4.8-fast":{"id":"anthropic/claude-opus-4.8-fast","name":"Claude Opus 4.8 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-opus-5-fast":{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024,"max":63999}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"openrouter"},"openrouter/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"openrouter"},"openrouter/arcee-ai/trinity-large-thinking":{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.22,"output":0.85,"cache_read":0.06},"sourceProvider":"openrouter"},"openrouter/arcee-ai/virtuoso-large":{"id":"arcee-ai/virtuoso-large","name":"Virtuoso Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-05","last_updated":"2025-05-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":64000},"cost":{"input":0.75,"output":1.2},"sourceProvider":"openrouter"},"openrouter/auto":{"id":"openrouter/auto","name":"Auto Router","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2023-11-08","last_updated":"2023-11-08","modalities":{"input":["text","image","audio","pdf","video"],"output":["text","image"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"openrouter"},"openrouter/baidu/ernie-4.5-vl-424b-a47b":{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"ERNIE 4.5 VL 424B A47B ","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ernie","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":123000,"output":16000},"cost":{"input":0.42,"output":1.25},"sourceProvider":"openrouter"},"openrouter/bodybuilder":{"id":"openrouter/bodybuilder","name":"Body Builder (beta)","description":"Preview model for early access evaluation, prototyping, and compatibility testing","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-12-05","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-1.6":{"id":"bytedance-seed/seed-1.6","name":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.25,"output":2,"tiers":[{"input":0.5,"output":4,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-1.6-flash":{"id":"bytedance-seed/seed-1.6-flash","name":"Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.3,"tiers":[{"input":0.1,"output":0.8,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-2-1-turbo":{"id":"bytedance-seed/seed-2-1-turbo","name":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.5},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-2.0-code":{"id":"bytedance-seed/seed-2.0-code","name":"Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":3,"tiers":[{"input":1,"output":6,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-2.0-lite":{"id":"bytedance-seed/seed-2.0-lite","name":"Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.25,"output":2,"tiers":[{"input":0.5,"output":4,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/bytedance-seed/seed-2.0-mini":{"id":"bytedance-seed/seed-2.0-mini","name":"Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.1,"output":0.4,"tiers":[{"input":0.2,"output":0.8,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/bytedance/ui-tars-1.5-7b":{"id":"bytedance/ui-tars-1.5-7b","name":"UI-TARS 7B ","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":2048},"cost":{"input":0.1,"output":0.2,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition":{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Uncensored","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04-30","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.9},"sourceProvider":"openrouter"},"openrouter/cohere/command-a":{"id":"cohere/command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command-a","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":2.5,"output":10},"sourceProvider":"openrouter"},"openrouter/cohere/command-r-08-2024":{"id":"cohere/command-r-08-2024","name":"Command R","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"openrouter"},"openrouter/cohere/command-r-plus-08-2024":{"id":"cohere/command-r-plus-08-2024","name":"Command R+","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","family":"command-r","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-08-30","last_updated":"2024-08-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":2.5,"output":10},"sourceProvider":"openrouter"},"openrouter/cohere/command-r7b-12-2024":{"id":"cohere/command-r7b-12-2024","name":"Command R7B","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","family":"command-r","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.0375,"output":0.15},"sourceProvider":"openrouter"},"openrouter/cohere/north-mini-code:free":{"id":"cohere/north-mini-code:free","name":"North Mini Code (free)","description":"Cohere coding model for practical software engineering and agentic edits","family":"north","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-17","last_updated":"2026-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":16000},"cost":{"input":0.2574,"output":1.0287},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-chat-v3-0324":{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07-31","release_date":"2025-03-24","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.25,"output":1},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-chat-v3.1":{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":161000},"cost":{"input":0.55,"output":1.65,"cache_read":0.55},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16000},"cost":{"input":0.7,"output":2.5},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.5,"output":2.15,"cache_read":0.35},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-r1-distill-llama-70b":{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"R1 Distill Llama 70B","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-07-31","release_date":"2025-01-23","last_updated":"2025-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.8,"output":0.8},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":32768},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.26,"output":0.38,"cache_read":0.13},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek V3.2 Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":65536},"cost":{"input":0.27,"output":0.41},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.0574,"output":0.1148,"cache_read":0.01148},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1310720,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.526176,"output":1.052352,"cache_read":0.043848},"sourceProvider":"openrouter"},"openrouter/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.122,"output":3.366,"cache_read":0.0374},"sourceProvider":"openrouter"},"openrouter/dots-studio/dots-3-note-preview:free":{"id":"dots-studio/dots-3-note-preview:free","name":"Dots3-Note Preview (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":512000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/free":{"id":"openrouter/free","name":"Free Models Router","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":200000,"output":8000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/fusion":{"id":"openrouter/fusion","name":"Fusion","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.1,"output":0.4,"reasoning":0.4,"cache_read":0.01,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-pro-preview":{"id":"google/gemini-2.5-pro-preview","name":"Gemini 2.5 Pro Preview 06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"openrouter"},"openrouter/google/gemini-2.5-pro-preview-05-06":{"id":"google/gemini-2.5-pro-preview-05-06","name":"Gemini 2.5 Pro Preview 05-06","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.25,"output":10,"reasoning":10,"cache_read":0.125,"cache_write":0.375,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"openrouter"},"openrouter/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"reasoning":3,"cache_read":0.05,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"openrouter"},"openrouter/google/gemini-3-pro-image-preview":{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["image","text"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.5,"output":3},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-flash-lite-image":{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","high"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":65536},"cost":{"input":0.25,"output":1.5},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"reasoning":1.5,"cache_read":0.025,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"reasoning":12,"cache_read":0.2,"cache_write":0.375,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"reasoning":9,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"reasoning":2.5,"cache_read":0.03,"cache_write":0.083333},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"reasoning":3.75,"cache_read":0.075,"cache_write":0.041667},"sourceProvider":"openrouter"},"openrouter/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.375,"output":1.875,"reasoning":1.875,"cache_read":0.0375,"cache_write":0.020833},"sourceProvider":"openrouter"},"openrouter/google/gemma-2-27b-it":{"id":"google/gemma-2-27b-it","name":"Gemma 2 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-07-13","last_updated":"2024-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":2048},"cost":{"input":0.65,"output":0.65},"sourceProvider":"openrouter"},"openrouter/google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.05,"output":0.15},"sourceProvider":"openrouter"},"openrouter/google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.08,"output":0.45,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.05,"output":0.1},"sourceProvider":"openrouter"},"openrouter/google/gemma-3n-e4b-it":{"id":"google/gemma-3n-e4b-it","name":"Gemma 3n 4B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.06,"output":0.12},"sourceProvider":"openrouter"},"openrouter/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.07,"output":0.34},"sourceProvider":"openrouter"},"openrouter/google/gemma-4-26b-a4b-it:free":{"id":"google/gemma-4-26b-a4b-it:free","name":"Gemma 4 26B A4B  (free)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.34,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/google/gemma-4-31b-it:free":{"id":"google/gemma-4-31b-it:free","name":"Gemma 4 31B (free)","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/google/lyria-3-clip-preview":{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/google/lyria-3-pro-preview":{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-03-25","last_updated":"2026-03-25","modalities":{"input":["text","image"],"output":["text","audio"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/gryphe/mythomax-l2-13b":{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-07-02","last_updated":"2023-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.06,"output":0.06},"sourceProvider":"openrouter"},"openrouter/ibm-granite/granite-4.0-h-micro":{"id":"ibm-granite/granite-4.0-h-micro","name":"Granite 4.0 Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"granite","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131000},"cost":{"input":0.017,"output":0.112},"sourceProvider":"openrouter"},"openrouter/ibm-granite/granite-4.1-8b":{"id":"ibm-granite/granite-4.1-8b","name":"Granite 4.1 8B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1,"cache_read":0.05},"sourceProvider":"openrouter"},"openrouter/inception/mercury-2":{"id":"inception/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.25,"output":0.75,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/inclusionai/ling-2.6-1t":{"id":"inclusionai/ling-2.6-1t","name":"Ling-2.6-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.075,"output":0.625,"cache_read":0.015},"sourceProvider":"openrouter"},"openrouter/inclusionai/ling-2.6-flash":{"id":"inclusionai/ling-2.6-flash","name":"Ling-2.6-flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.01,"output":0.03,"cache_read":0.002},"sourceProvider":"openrouter"},"openrouter/inclusionai/ling-3.0-flash":{"id":"inclusionai/ling-3.0-flash","name":"Ling-3.0-flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-23","last_updated":"2026-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.021,"output":0.063,"cache_read":0.0042},"sourceProvider":"openrouter"},"openrouter/inclusionai/ring-2.6-1t":{"id":"inclusionai/ring-2.6-1t","name":"Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.075,"output":0.625,"cache_read":0.015},"sourceProvider":"openrouter"},"openrouter/kwaipilot/kat-coder-air-v2.5":{"id":"kwaipilot/kat-coder-air-v2.5","name":"KAT-Coder-Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/kwaipilot/kat-coder-pro-v2":{"id":"kwaipilot/kat-coder-pro-v2","name":"KAT-Coder-Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"openrouter"},"openrouter/kwaipilot/kat-coder-pro-v2.5":{"id":"kwaipilot/kat-coder-pro-v2.5","name":"KAT-Coder-Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.74,"output":2.96,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/liquid/lfm-2.5-2.6b:free":{"id":"liquid/lfm-2.5-2.6b:free","name":"LFM2.5-2.6B (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"liquid","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/mancer/weaver":{"id":"mancer/weaver","name":"Weaver (alpha)","description":"General-purpose chat model for instruction following, writing, and analysis","family":"alpha","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-08-02","last_updated":"2023-08-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":6000},"cost":{"input":0.5,"output":0.75},"sourceProvider":"openrouter"},"openrouter/meituan/longcat-2.0":{"id":"meituan/longcat-2.0","name":"LongCat 2.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"longcat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-20","last_updated":"2026-07-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048756,"output":262144},"cost":{"input":0.3,"output":1.2,"cache_read":0.006},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-3.1-70b-instruct":{"id":"meta-llama/llama-3.1-70b-instruct","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.4,"output":0.4},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-3.1-8b-instruct":{"id":"meta-llama/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.08,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-3.2-1b-instruct":{"id":"meta-llama/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":60000,"output":60000},"cost":{"input":0.027,"output":0.201},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-3.2-3b-instruct":{"id":"meta-llama/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.33},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-3.3-70b-instruct":{"id":"meta-llama/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.1,"output":0.32},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-4-maverick":{"id":"meta-llama/llama-4-maverick","name":"Llama 4 Maverick","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.2,"output":0.8},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-4-scout":{"id":"meta-llama/llama-4-scout","name":"Llama 4 Scout","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1310720,"output":16384},"cost":{"input":0.1,"output":0.3},"sourceProvider":"openrouter"},"openrouter/meta-llama/llama-guard-4-12b":{"id":"meta-llama/llama-guard-4-12b","name":"Llama Guard 4 12B","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"llama","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-04-30","last_updated":"2025-04-30","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":16384},"cost":{"input":0.18,"output":0.18},"sourceProvider":"openrouter"},"openrouter/meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"openrouter"},"openrouter/microsoft/phi-4":{"id":"microsoft/phi-4","name":"Phi 4","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"phi","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-01-10","last_updated":"2025-01-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.07,"output":0.14},"sourceProvider":"openrouter"},"openrouter/microsoft/wizardlm-2-8x22b":{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-04-16","last_updated":"2024-04-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65535,"output":8000},"cost":{"input":0.62,"output":0.62},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-01":{"id":"minimax/minimax-01","name":"MiniMax-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-03-31","release_date":"2025-01-15","last_updated":"2025-01-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000192,"output":1000192},"cost":{"input":0.2,"output":1.1},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m1":{"id":"minimax/minimax-m1","name":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":40000},"cost":{"input":0.55,"output":2.2},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax-M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.255,"output":1.02},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m2-her":{"id":"minimax/minimax-m2-her","name":"MiniMax-M2 Her","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":2048},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax-M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.27,"output":1.08,"cache_read":0.027},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.24,"output":0.96,"cache_read":0.048},"sourceProvider":"openrouter"},"openrouter/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":512000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"openrouter"},"openrouter/mistralai/codestral-2508":{"id":"mistralai/codestral-2508","name":"Codestral 2508","description":"Mistral coding model for code completion, generation, and developer workflows","family":"codestral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-01","last_updated":"2025-08-01","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":0.9,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/mistralai/ministral-14b-2512":{"id":"mistralai/ministral-14b-2512","name":"Ministral 3 14B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.2,"cache_read":0.02},"sourceProvider":"openrouter"},"openrouter/mistralai/ministral-3b-2512":{"id":"mistralai/ministral-3b-2512","name":"Ministral 3 3B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1,"cache_read":0.01},"sourceProvider":"openrouter"},"openrouter/mistralai/ministral-8b":{"id":"mistralai/ministral-8b","name":"Ministral 8B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2024-10-17","last_updated":"2024-10-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.11,"output":0.11},"sourceProvider":"openrouter"},"openrouter/mistralai/ministral-8b-2512":{"id":"mistralai/ministral-8b-2512","name":"Ministral 3 8B 2512","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.15,"cache_read":0.015},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-large":{"id":"mistralai/mistral-large","name":"Mistral Large","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11-30","release_date":"2024-02-26","last_updated":"2024-02-26","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-large-2407":{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-03-31","release_date":"2024-11-19","last_updated":"2024-11-19","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-large-2512":{"id":"mistralai/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5,"cache_read":0.05},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-medium-3":{"id":"mistralai/mistral-medium-3","name":"Mistral Medium 3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-medium-3-5":{"id":"mistralai/mistral-medium-3-5","name":"Mistral Medium 3.5","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.5,"output":7.5},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-medium-3.1":{"id":"mistralai/mistral-medium-3.1","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":262144},"cost":{"input":0.4,"output":2,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-nemo":{"id":"mistralai/mistral-nemo","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.019,"output":0.03},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-saba":{"id":"mistralai/mistral-saba","name":"Saba","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-02-17","last_updated":"2025-02-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.6,"cache_read":0.02},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-small-24b-instruct-2501":{"id":"mistralai/mistral-small-24b-instruct-2501","name":"Mistral Small 3","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-01-30","last_updated":"2025-01-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.05,"output":0.08},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-small-2603":{"id":"mistralai/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-small-3.1-24b-instruct":{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral Small 3.1 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.351,"output":0.555},"sourceProvider":"openrouter"},"openrouter/mistralai/mistral-small-3.2-24b-instruct":{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2025-06-20","last_updated":"2025-06-20","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.075,"output":0.2},"sourceProvider":"openrouter"},"openrouter/mistralai/mixtral-8x22b-instruct":{"id":"mistralai/mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-01-31","release_date":"2024-04-17","last_updated":"2024-04-17","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"openrouter"},"openrouter/mistralai/voxtral-small-24b-2507":{"id":"mistralai/voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-30","last_updated":"2025-10-30","modalities":{"input":["text","audio","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2":{"id":"moonshotai/kimi-k2","name":"Kimi K2 0711","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12-31","release_date":"2025-07-11","last_updated":"2025-07-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":100352},"cost":{"input":0.57,"output":2.3},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12-31","release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":100352},"cost":{"input":0.6,"output":2.5},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":100352},"cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.67,"output":3.4,"cache_read":0.17},"sourceProvider":"openrouter"},"openrouter/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"openrouter"},"openrouter/morph/morph-v3-fast":{"id":"morph/morph-v3-fast","name":"Morph V3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":81920,"output":38000},"cost":{"input":0.8,"output":1.2},"sourceProvider":"openrouter"},"openrouter/morph/morph-v3-large":{"id":"morph/morph-v3-large","name":"Morph V3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-07-07","last_updated":"2025-07-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.9,"output":1.9},"sourceProvider":"openrouter"},"openrouter/nex-agi/nex-n2-mini":{"id":"nex-agi/nex-n2-mini","name":"Nex-N2-Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-24","last_updated":"2026-06-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.025,"output":0.1,"cache_read":0.0025},"sourceProvider":"openrouter"},"openrouter/nex-agi/nex-n2-pro":{"id":"nex-agi/nex-n2-pro","name":"Nex-N2-Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"agi","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-08","last_updated":"2026-06-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/nousresearch/hermes-3-llama-3.1-405b":{"id":"nousresearch/hermes-3-llama-3.1-405b","name":"Hermes 3 405B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-16","last_updated":"2024-08-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":1,"output":1},"sourceProvider":"openrouter"},"openrouter/nousresearch/hermes-3-llama-3.1-70b":{"id":"nousresearch/hermes-3-llama-3.1-70b","name":"Hermes 3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"nousresearch","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-18","last_updated":"2024-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.7,"output":0.7},"sourceProvider":"openrouter"},"openrouter/nousresearch/hermes-4-405b":{"id":"nousresearch/hermes-4-405b","name":"Hermes 4 405B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":1,"output":3},"sourceProvider":"openrouter"},"openrouter/nousresearch/hermes-4-70b":{"id":"nousresearch/hermes-4-70b","name":"Hermes 4 70B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"hermes","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-08-31","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.13,"output":0.4},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.2,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-nano-30b-a3b:free":{"id":"nvidia/nemotron-3-nano-30b-a3b:free","name":"Nemotron 3 Nano 30B A3B (free)","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","name":"Nemotron 3 Nano Omni (free)","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":16384},"cost":{"input":0.085,"output":0.4},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-super-120b-a12b:free":{"id":"nvidia/nemotron-3-super-120b-a12b:free","name":"Nemotron 3 Super (free)","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["medium","high"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512288,"output":16384},"cost":{"input":0.6,"output":3.6,"cache_read":0.2},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3-ultra-550b-a55b:free":{"id":"nvidia/nemotron-3-ultra-550b-a55b:free","name":"Nemotron 3 Ultra (free)","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["medium","high"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3.5-content-safety:free":{"id":"nvidia/nemotron-3.5-content-safety:free","name":"Nemotron 3.5 Content Safety (free)","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3.5-lightning":{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.08,"output":0.2,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-3.5-lightning:free":{"id":"nvidia/nemotron-3.5-lightning:free","name":"Nemotron 3.5 Lightning (free)","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-nano-12b-v2-vl:free":{"id":"nvidia/nemotron-nano-12b-v2-vl:free","name":"Nemotron Nano 12B 2 VL (free)","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/nvidia/nemotron-nano-9b-v2:free":{"id":"nvidia/nemotron-nano-9b-v2:free","name":"Nemotron Nano 9B V2 (free)","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"openrouter"},"openrouter/openai/gpt-3.5-turbo-0613":{"id":"openai/gpt-3.5-turbo-0613","name":"GPT-3.5 Turbo (older v0613)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-30","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":4096},"cost":{"input":1,"output":2},"sourceProvider":"openrouter"},"openrouter/openai/gpt-3.5-turbo-16k":{"id":"openai/gpt-3.5-turbo-16k","name":"GPT-3.5 Turbo 16k","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2021-09-30","release_date":"2023-08-28","last_updated":"2023-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":3,"output":4},"sourceProvider":"openrouter"},"openrouter/openai/gpt-3.5-turbo-instruct":{"id":"openai/gpt-3.5-turbo-instruct","name":"GPT-3.5 Turbo Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2021-09-30","release_date":"2023-09-28","last_updated":"2023-09-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4095,"output":4096},"cost":{"input":1.5,"output":2},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":4096},"cost":{"input":30,"output":60},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4-turbo-preview":{"id":"openai/gpt-4-turbo-preview","name":"GPT-4 Turbo Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"openrouter"},"openrouter/openai/gpt-4o-mini-2024-07-18":{"id":"openai/gpt-4o-mini-2024-07-18","name":"GPT-4o-mini (2024-07-18)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"o-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-10-31","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5-image":{"id":"openai/gpt-5-image","name":"GPT-5 Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-10-01","release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":10,"output":10,"cache_read":1.25},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5-image-mini":{"id":"openai/gpt-5-image-mini","name":"GPT-5 Image Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["pdf","image","text"],"output":["image","text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":2.5,"output":2,"cache_read":0.25},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":15,"output":120},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.2-chat":{"id":"openai/gpt-5.2-chat","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-10","last_updated":"2025-12-10","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.4-image-2":{"id":"openai/gpt-5.4-image-2","name":"GPT-5.4 Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["image","text","pdf"],"output":["image","text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":8,"output":15,"cache_read":2},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-luna-pro":{"id":"openai/gpt-5.6-luna-pro","name":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-sol-pro":{"id":"openai/gpt-5.6-sol-pro","name":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":15,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":15,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-5.6-terra-pro":{"id":"openai/gpt-5.6-terra-pro","name":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"openrouter"},"openrouter/openai/gpt-audio":{"id":"openai/gpt-audio","name":"GPT Audio","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10},"sourceProvider":"openrouter"},"openrouter/openai/gpt-audio-mini":{"id":"openai/gpt-audio-mini","name":"GPT Audio Mini","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":2.4},"sourceProvider":"openrouter"},"openrouter/openai/gpt-chat-latest":{"id":"openai/gpt-chat-latest","name":"GPT Chat Latest","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-05-05","last_updated":"2026-05-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"openrouter"},"openrouter/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.037,"output":0.17},"sourceProvider":"openrouter"},"openrouter/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.0375},"sourceProvider":"openrouter"},"openrouter/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"openrouter"},"openrouter/openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":150,"output":600},"sourceProvider":"openrouter"},"openrouter/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"openrouter"},"openrouter/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"openrouter"},"openrouter/openai/o3-mini-high":{"id":"openai/o3-mini-high","name":"o3 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-10-31","release_date":"2025-02-12","last_updated":"2025-02-12","modalities":{"input":["text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"openrouter"},"openrouter/openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","pdf","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"openrouter"},"openrouter/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"openrouter"},"openrouter/openai/o4-mini-high":{"id":"openai/o4-mini-high","name":"o4 Mini High","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-06-30","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"openrouter"},"openrouter/pareto-code":{"id":"openrouter/pareto-code","name":"Pareto Code Router","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":200000},"sourceProvider":"openrouter"},"openrouter/perceptron/perceptron-mk1":{"id":"perceptron/perceptron-mk1","name":"Perceptron Mk1","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-05-12","last_updated":"2026-05-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":8192},"cost":{"input":0.15,"output":1.5},"sourceProvider":"openrouter"},"openrouter/perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-01-27","last_updated":"2025-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127072,"output":127072},"cost":{"input":1,"output":1},"sourceProvider":"openrouter"},"openrouter/perplexity/sonar-deep-research":{"id":"perplexity/sonar-deep-research","name":"Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"openrouter"},"openrouter/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"sourceProvider":"openrouter"},"openrouter/perplexity/sonar-pro-search":{"id":"perplexity/sonar-pro-search","name":"Sonar Pro Search","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-10-30","last_updated":"2025-10-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"cost":{"input":3,"output":15},"sourceProvider":"openrouter"},"openrouter/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-03-07","last_updated":"2025-03-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":2,"output":8},"sourceProvider":"openrouter"},"openrouter/poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"laguna-s","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.09,"output":0.18,"cache_read":0.009},"sourceProvider":"openrouter"},"openrouter/poolside/laguna-s-2.1:free":{"id":"poolside/laguna-s-2.1:free","name":"Laguna S 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"laguna-s","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.12,"cache_read":0.03},"sourceProvider":"openrouter"},"openrouter/poolside/laguna-xs-2.1:free":{"id":"poolside/laguna-xs-2.1:free","name":"Laguna XS 2.1 (free)","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-2.5-72b-instruct":{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"cost":{"input":0.36,"output":0.4},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-2.5-7b-instruct":{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen2.5 7B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.2},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-2.5-coder-32b-instruct":{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-06-30","release_date":"2024-11-11","last_updated":"2024-11-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.66,"output":1},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-plus":{"id":"qwen/qwen-plus","name":"Qwen Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-01-25","last_updated":"2025-09-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78,"cache_read":0.052,"cache_write":0.325,"tiers":[{"input":0.78,"output":2.34,"cache_read":0.156,"cache_write":0.975,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.78,"output":2.34,"cache_read":0.156,"cache_write":0.975}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-plus-2025-07-28":{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen Plus 0728","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78,"tiers":[{"input":0.78,"output":2.34,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.78,"output":2.34}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen-plus-2025-07-28:thinking":{"id":"qwen/qwen-plus-2025-07-28:thinking","name":"Qwen Plus 0728 (thinking)","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":0.26,"output":0.78,"tiers":[{"input":0.78,"output":2.34,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.78,"output":2.34}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen2.5-vl-72b-instruct":{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-02-01","last_updated":"2025-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.8,"output":1,"cache_read":0.4},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-14b":{"id":"qwen/qwen3-14b","name":"Qwen3 14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.12,"output":0.24},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-235b-a22b":{"id":"qwen/qwen3-235b-a22b","name":"Qwen3 235B-A22B","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":38912}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.455,"output":1.82},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-235b-a22b-2507":{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.09,"output":0.55},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-235b-a22b-thinking-2507":{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.23,"output":2.3},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-30b-a3b":{"id":"qwen/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.12,"output":0.5},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-30b-a3b-instruct-2507":{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.04815,"output":0.19305},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-30b-a3b-thinking-2507":{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen3 30B A3B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":81920,"output":32768},"cost":{"input":0.2,"output":2.4},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-32b":{"id":"qwen/qwen3-32b","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.08,"output":0.28},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-8b":{"id":"qwen/qwen3-8b","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.117,"output":0.455},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-coder":{"id":"qwen/qwen3-coder","name":"Qwen3 Coder 480B A35B","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":1,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.07,"output":0.28},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-coder-flash":{"id":"qwen/qwen3-coder-flash","name":"Qwen3 Coder Flash","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375,"tiers":[{"input":0.325,"output":1.625,"cache_read":0.065,"cache_write":0.40625,"tier":{"type":"context","size":32000}},{"input":0.52,"output":2.6,"cache_read":0.104,"cache_write":0.65,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-coder-next":{"id":"qwen/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.12,"output":0.8,"cache_read":0.07},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.65,"output":3.25,"cache_read":0.13,"cache_write":0.8125,"tiers":[{"input":1.17,"output":5.85,"cache_read":0.234,"cache_write":1.4625,"tier":{"type":"context","size":32000}},{"input":1.95,"output":9.75,"cache_read":0.39,"cache_write":2.4375,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.78,"output":3.9,"cache_read":0.156,"cache_write":0.975,"tiers":[{"input":1.56,"output":7.8,"cache_read":0.312,"cache_write":1.95,"tier":{"type":"context","size":32000}},{"input":1.95,"output":9.75,"cache_read":0.39,"cache_write":2.4375,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-max-thinking":{"id":"qwen/qwen3-max-thinking","name":"Qwen3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-09","last_updated":"2026-02-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.78,"output":3.9,"tiers":[{"input":1.56,"output":7.8,"tier":{"type":"context","size":32000}},{"input":1.95,"output":9.75,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-next-80b-a3b-instruct":{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen3-Next 80B-A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":1.1,"cache_read":0.07},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-next-80b-a3b-thinking":{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen3-Next 80B-A3B (Thinking)","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.21,"output":1.9,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-235b-a22b-thinking":{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":4},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-30b-a3b-instruct":{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.52},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-30b-a3b-thinking":{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen3 VL 30B A3B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.2,"output":2.4},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-32b-instruct":{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen3 VL 32B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-23","last_updated":"2025-10-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.104,"output":0.416},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-8b-instruct":{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen3 VL 8B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.117,"output":0.455},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3-vl-8b-thinking":{"id":"qwen/qwen3-vl-8b-thinking","name":"Qwen3 VL 8B Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-14","last_updated":"2025-10-14","modalities":{"input":["image","text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.18,"output":2.1},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.26,"output":2.08},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.195,"output":1.56},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.25,"cache_read":0.25},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":3.6,"cache_read":0.3},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.15},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-flash-02-23":{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen3.5-Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.065,"output":0.26},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-plus-02-15":{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen3.5 Plus 2026-02-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.26,"output":1.56,"tiers":[{"input":0.325,"output":1.95,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.325,"output":1.95}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.5-plus-20260420":{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen3.5 Plus 2026-04-20","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.3,"output":1.8,"cache_write":0.375,"tiers":[{"input":0.375,"output":2.25,"cache_write":0.46875,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.375,"output":2.25,"cache_write":0.46875}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.6-27b":{"id":"qwen/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":81920},"cost":{"input":0.32,"output":3.2},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.6-35b-a3b":{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.14,"output":1,"cache_read":0.05},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.6-flash":{"id":"qwen/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_write":0.234375,"tiers":[{"input":0.75,"output":3,"cache_write":0.9375,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.75,"output":3,"cache_write":0.9375}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.6-max-preview":{"id":"qwen/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.027,"output":6.162,"cache_write":1.28375,"tiers":[{"input":1.58,"output":9.48,"cache_write":1.975,"tier":{"type":"context","size":128000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.325,"output":1.95,"cache_write":0.40625,"tiers":[{"input":1.3,"output":3.9,"cache_write":1.625,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.3,"output":3.9,"cache_write":1.625}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.7-flash":{"id":"qwen/qwen3.7-flash","name":"Qwen3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":991000,"output":65536},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038,"tiers":[{"input":0.1,"output":0.4,"cache_read":0.02,"cache_write":0.125,"tier":{"type":"context","size":32000}},{"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0.25,"tier":{"type":"context","size":256000}}]},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4,"tiers":[{"input":0.96,"output":3.84,"cache_read":0.192,"cache_write":1.2,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.96,"output":3.84,"cache_read":0.192,"cache_write":1.2}},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.8-2.4t-a95b":{"id":"qwen/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.8-27b":{"id":"qwen/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.4,"output":3,"cache_read":0.05},"sourceProvider":"openrouter"},"openrouter/qwen/qwen3.8-max":{"id":"qwen/qwen3.8-max","name":"Qwen3.8 Max","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"openrouter"},"openrouter/rekaai/reka-edge":{"id":"rekaai/reka-edge","name":"Reka Edge","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"reka","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.1,"output":0.1},"sourceProvider":"openrouter"},"openrouter/rekaai/reka-flash-3":{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"reka","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-01-31","release_date":"2025-03-12","last_updated":"2025-03-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.1,"output":0.2},"sourceProvider":"openrouter"},"openrouter/relace/relace-apply-3":{"id":"relace/relace-apply-3","name":"Relace Apply 3","description":"General-purpose chat model for instruction following, writing, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.85,"output":1.25},"sourceProvider":"openrouter"},"openrouter/relace/relace-search":{"id":"relace/relace-search","name":"Relace Search","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":1,"output":3},"sourceProvider":"openrouter"},"openrouter/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"openrouter"},"openrouter/sakana/sakana-namazu":{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"sakana-namazu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/sao10k/l3-lunaris-8b":{"id":"sao10k/l3-lunaris-8b","name":"Llama 3 8B Lunaris","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-13","last_updated":"2024-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":16384},"cost":{"input":0.04,"output":0.05},"sourceProvider":"openrouter"},"openrouter/sao10k/l3.1-euryale-70b":{"id":"sao10k/l3.1-euryale-70b","name":"Llama 3.1 Euryale 70B v2.2","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-28","last_updated":"2024-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.85,"output":0.85},"sourceProvider":"openrouter"},"openrouter/sao10k/l3.3-euryale-70b":{"id":"sao10k/l3.3-euryale-70b","name":"Llama 3.3 Euryale 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-12-31","release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.65,"output":0.75},"sourceProvider":"openrouter"},"openrouter/stealth/ox-alpha":{"id":"stealth/ox-alpha","name":"Ox Alpha","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"alpha","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.3},"sourceProvider":"openrouter"},"openrouter/stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"openrouter"},"openrouter/tencent/hunyuan-a13b-instruct":{"id":"tencent/hunyuan-a13b-instruct","name":"Hunyuan A13B Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-07-08","last_updated":"2025-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.14,"output":0.57},"sourceProvider":"openrouter"},"openrouter/tencent/hy-mt2-1.8b":{"id":"tencent/hy-mt2-1.8b","name":"Hy-MT2-1.8B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.044,"output":0.177},"sourceProvider":"openrouter"},"openrouter/tencent/hy-mt2-30b-a3b":{"id":"tencent/hy-mt2-30b-a3b","name":"Hy-MT2-30B-A3B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-20","last_updated":"2026-08-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"sourceProvider":"openrouter"},"openrouter/tencent/hy-mt2-7b":{"id":"tencent/hy-mt2-7b","name":"Hy-MT2-7B","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-08-19","last_updated":"2026-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.074,"output":0.295},"sourceProvider":"openrouter"},"openrouter/tencent/hy3":{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":128000},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"sourceProvider":"openrouter"},"openrouter/tencent/hy3-preview":{"id":"tencent/hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.18,"output":0.6,"cache_read":0.06},"sourceProvider":"openrouter"},"openrouter/thedrummer/cydonia-24b-v4.1":{"id":"thedrummer/cydonia-24b-v4.1","name":"Cydonia 24B V4.1","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2025-09-27","last_updated":"2025-09-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.3,"output":0.5,"cache_read":0.15},"sourceProvider":"openrouter"},"openrouter/thedrummer/rocinante-12b":{"id":"thedrummer/rocinante-12b","name":"Rocinante 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-09-30","last_updated":"2024-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.25,"output":0.5},"sourceProvider":"openrouter"},"openrouter/thedrummer/skyfall-36b-v2":{"id":"thedrummer/skyfall-36b-v2","name":"Skyfall 36B V2","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-06-30","release_date":"2025-03-10","last_updated":"2025-03-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.55,"output":0.8,"cache_read":0.25},"sourceProvider":"openrouter"},"openrouter/thedrummer/unslopnemo-12b":{"id":"thedrummer/unslopnemo-12b","name":"UnslopNemo 12B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-11-08","last_updated":"2024-11-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1024000,"output":32768},"cost":{"input":0.4,"output":0.4},"sourceProvider":"openrouter"},"openrouter/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"openrouter"},"openrouter/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":0.45,"output":1.2,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/thinkingmachines/inkling-small:free":{"id":"thinkingmachines/inkling-small:free","name":"Inkling Small (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/thinkingmachines/inkling:free":{"id":"thinkingmachines/inkling:free","name":"Inkling (free)","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/undi95/remm-slerp-l2-13b":{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2023-06-30","release_date":"2023-07-22","last_updated":"2023-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":6144,"output":6144},"cost":{"input":0.45,"output":0.65},"sourceProvider":"openrouter"},"openrouter/upstage/solar-pro-3":{"id":"upstage/solar-pro-3","name":"Solar Pro 3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"openrouter"},"openrouter/upstage/solar-pro4":{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.03,"output":0.12,"cache_read":0.006},"sourceProvider":"openrouter"},"openrouter/writer/palmyra-x5":{"id":"writer/palmyra-x5","name":"Palmyra X5","description":"General-purpose chat model for instruction following, writing, and analysis","family":"palmyra","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-21","last_updated":"2026-01-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1040000,"output":8192},"cost":{"input":0.6,"output":6},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-4.20":{"id":"x-ai/grok-4.20","name":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-4.20-multi-agent":{"id":"x-ai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2026-03-31","last_updated":"2026-03-31","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-4.6":{"id":"x-ai/grok-4.6","name":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"openrouter"},"openrouter/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"openrouter"},"openrouter/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"openrouter"},"openrouter/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.5":{"id":"z-ai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.5-air":{"id":"z-ai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.13,"output":0.85,"cache_read":0.025},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.5v":{"id":"z-ai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":16384},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.5,"output":2,"cache_read":0.1},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.6v":{"id":"z-ai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.3,"output":0.9,"cache_read":0.055},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.4,"output":1.75,"cache_read":0.08},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-4.7-flash":{"id":"z-ai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_details"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":16384},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.6,"output":1.92,"cache_read":0.12},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":128000},"cost":{"input":0.966,"output":3.036,"cache_read":0.1794},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.966,"output":3.036,"cache_read":0.1932},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5.2:free":{"id":"z-ai/glm-5.2:free","name":"GLM 5.2 (free)","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0,"output":0},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5.3":{"id":"z-ai/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"openrouter"},"openrouter/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"openrouter"},"opper/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"opper"},"opper/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"opper"},"opper/anthropic/claude-opus-4-5":{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opper"},"opper/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opper"},"opper/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opper"},"opper/anthropic/claude-opus-4-8":{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opper"},"opper/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"opper"},"opper/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"opper"},"opper/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"opper"},"opper/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"opper"},"opper/gemini/gemini-3-flash-preview":{"id":"gemini/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"opper"},"opper/gemini/gemini-3.1-pro-preview":{"id":"gemini/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"opper"},"opper/gemini/gemini-3.5-flash":{"id":"gemini/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"opper"},"opper/gemini/gemini-3.5-flash-lite":{"id":"gemini/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"opper"},"opper/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"opper"},"opper/minimax/m3":{"id":"minimax/m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"tier":{"type":"context","size":524288}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24}},"sourceProvider":"opper"},"opper/mistral/devstral-2512":{"id":"mistral/devstral-2512","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":2},"sourceProvider":"opper"},"opper/mistral/mistral-large-2512":{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":1.5},"sourceProvider":"opper"},"opper/mistral/mistral-small-2603":{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.15,"output":0.6},"sourceProvider":"opper"},"opper/moonshot/kimi-k3":{"id":"moonshot/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"opper"},"opper/openai/gpt-5.3-chat-latest":{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opper"},"opper/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"opper"},"opper/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"opper"},"opper/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"opper"},"opper/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"opper"},"opper/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"opper"},"opper/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"opper"},"opper/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"opper"},"opper/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25,"tiers":[{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.4,"output":1.8,"cache_read":0.04,"cache_write":0.5}},"sourceProvider":"opper"},"opper/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"opper"},"opper/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5,"tiers":[{"input":4,"output":18,"cache_read":0.4,"cache_write":5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4,"cache_write":5}},"sourceProvider":"opper"},"opper/perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"opper"},"opper/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"opper"},"opper/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"opper"},"opper/vertexai/gemini-3.7-flash":{"id":"vertexai/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"opper"},"opper/vertexai/gemini-3.7-flash-eu":{"id":"vertexai/gemini-3.7-flash-eu","name":"Gemini 3.7 Flash (EU)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"opper"},"opper/xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"opper"},"opper/xai/grok-4.5":{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"sourceProvider":"opper"},"opper/xai/grok-4.6":{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"opper"},"opper/xai/grok-build-0.1":{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"opper"},"orcarouter/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Claude Opus 4 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"orcarouter"},"orcarouter/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"orcarouter"},"orcarouter/auto":{"id":"orcarouter/auto","name":"OrcaRouter Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-01-01","last_updated":"2026-05-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"orcarouter"},"orcarouter/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek Chat","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"orcarouter"},"orcarouter/deepseek/deepseek-reasoner":{"id":"deepseek/deepseek-reasoner","name":"DeepSeek Reasoner","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-09","release_date":"2025-12-01","last_updated":"2026-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.028},"sourceProvider":"orcarouter"},"orcarouter/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.19,"output":0.37,"cache_read":0.0028},"sourceProvider":"orcarouter"},"orcarouter/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.56,"output":1.12,"cache_read":0.003625},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2.5,"output":15,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"input_audio":1},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-3-pro-preview":{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-11-18","last_updated":"2025-11-18","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":18,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":18,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-3.1-pro-preview-customtools":{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":4,"output":18,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-flash-latest":{"id":"google/gemini-flash-latest","name":"Gemini Flash Latest","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"orcarouter"},"orcarouter/google/gemini-flash-lite-latest":{"id":"google/gemini-flash-lite-latest","name":"Gemini Flash-Lite Latest","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"orcarouter"},"orcarouter/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.06,"output":0.33},"sourceProvider":"orcarouter"},"orcarouter/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.13,"output":0.38},"sourceProvider":"orcarouter"},"orcarouter/grok/grok-4.3":{"id":"grok/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"orcarouter"},"orcarouter/kimi/kimi-k2.5":{"id":"kimi/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"orcarouter"},"orcarouter/kimi/kimi-k2.6":{"id":"kimi/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"orcarouter"},"orcarouter/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"orcarouter"},"orcarouter/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax-M2.5-highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"orcarouter"},"orcarouter/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"orcarouter"},"orcarouter/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09-01","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"output":4096},"cost":{"input":0.5,"output":1.5,"cache_read":0},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4":{"id":"openai/gpt-4","name":"GPT-4","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-11","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":8192},"cost":{"input":30,"output":60},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":10,"output":30},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4o-2024-05-13":{"id":"openai/gpt-4o-2024-05-13","name":"GPT-4o (2024-05-13)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":5,"output":15},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4o-2024-08-06":{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o (2024-08-06)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-08-06","last_updated":"2024-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4o-2024-11-20":{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o (2024-11-20)","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5-chat-latest":{"id":"openai/gpt-5-chat-latest","name":"GPT-5 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.1-chat-latest":{"id":"openai/gpt-5.1-chat-latest","name":"GPT-5.1 Chat","description":"Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.2-chat-latest":{"id":"openai/gpt-5.2-chat-latest","name":"GPT-5.2 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.3-chat-latest":{"id":"openai/gpt-5.3-chat-latest","name":"GPT-5.3 Chat (latest)","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":22.5,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":1.5,"output":9,"cache_read":0.15},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":60,"output":270,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"orcarouter"},"orcarouter/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.359,"output":1.434},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.115,"output":0.917},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.5-27b":{"id":"qwen/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.086,"output":0.688},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.5-35b-a3b":{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.057,"output":0.459},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.5-397b-a17b":{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.172,"output":1.032},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.5-plus":{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.115,"output":0.688,"reasoning":2.4},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.6-35b-a3b":{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.248,"output":1.485},"sourceProvider":"orcarouter"},"orcarouter/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-4.5":{"id":"z-ai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-4.5-air":{"id":"z-ai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"sourceProvider":"orcarouter"},"orcarouter/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"orcarouter"},"ovhcloud/gpt-oss-120b":{"id":"ovhcloud/gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.09,"output":0.47},"sourceProvider":"ovhcloud"},"ovhcloud/gpt-oss-20b":{"id":"ovhcloud/gpt-oss-20b","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2025-08-28","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.18},"sourceProvider":"ovhcloud"},"ovhcloud/meta-llama-3_3-70b-instruct":{"id":"ovhcloud/meta-llama-3_3-70b-instruct","name":"Meta-Llama-3_3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.74,"output":0.74},"sourceProvider":"ovhcloud"},"ovhcloud/mistral-7b-instruct-v0.3":{"id":"ovhcloud/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-01","last_updated":"2025-04-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.11,"output":0.11},"sourceProvider":"ovhcloud"},"ovhcloud/mistral-nemo-instruct-2407":{"id":"ovhcloud/mistral-nemo-instruct-2407","name":"Mistral-Nemo-Instruct-2407","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-11-20","last_updated":"2024-11-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":0.14,"output":0.14},"sourceProvider":"ovhcloud"},"ovhcloud/mistral-small-3.2-24b-instruct-2506":{"id":"ovhcloud/mistral-small-3.2-24b-instruct-2506","name":"Mistral-Small-3.2-24B-Instruct-2506","description":"Efficient Mistral model for fast chat, extraction, and production assistants","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-16","last_updated":"2025-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.31},"sourceProvider":"ovhcloud"},"ovhcloud/qwen2.5-vl-72b-instruct":{"id":"ovhcloud/qwen2.5-vl-72b-instruct","name":"Qwen2.5-VL-72B-Instruct","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":1.01,"output":1.01},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3-32b":{"id":"ovhcloud/qwen3-32b","name":"Qwen3-32B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-16","last_updated":"2025-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.09,"output":0.25},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3-coder-30b-a3b-instruct":{"id":"ovhcloud/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder-30B-A3B-Instruct","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.07,"output":0.26},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3.5-397b-a17b":{"id":"ovhcloud/qwen3.5-397b-a17b","name":"Qwen3.5-397B-A17B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-18","last_updated":"2026-05-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.71,"output":4.25},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3.5-9b":{"id":"ovhcloud/qwen3.5-9b","name":"Qwen3.5-9B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.12,"output":0.18},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3.6-27b":{"id":"ovhcloud/qwen3.6-27b","name":"Qwen3.6-27B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.47,"output":3.19},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3guard-gen-0.6b":{"id":"ovhcloud/qwen3guard-gen-0.6b","name":"Qwen3Guard-Gen-0.6B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"sourceProvider":"ovhcloud"},"ovhcloud/qwen3guard-gen-8b":{"id":"ovhcloud/qwen3guard-gen-8b","name":"Qwen3Guard-Gen-8B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":16384},"sourceProvider":"ovhcloud"},"perplexity-agent/anthropic/claude-haiku-4-5":{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1},"sourceProvider":"perplexity-agent"},"perplexity-agent/anthropic/claude-opus-4-5":{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"perplexity-agent"},"perplexity-agent/anthropic/claude-opus-4-6":{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"perplexity-agent"},"perplexity-agent/anthropic/claude-opus-4-7":{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5},"sourceProvider":"perplexity-agent"},"perplexity-agent/anthropic/claude-sonnet-4-5":{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"perplexity-agent"},"perplexity-agent/anthropic/claude-sonnet-4-6":{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"perplexity-agent"},"perplexity-agent/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"sourceProvider":"perplexity-agent"},"perplexity-agent/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"perplexity-agent"},"perplexity-agent/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-20","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"perplexity-agent"},"perplexity-agent/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.5,"output":3,"cache_read":0.05,"tiers":[{"input":0.5,"output":3,"cache_read":0.05,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.5,"output":3,"cache_read":0.05}},"sourceProvider":"perplexity-agent"},"perplexity-agent/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"perplexity-agent"},"perplexity-agent/moonshot-ai/kimi-k2.7-code":{"id":"moonshot-ai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-07-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"perplexity-agent"},"perplexity-agent/moonshot-ai/kimi-k3":{"id":"moonshot-ai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-30","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"perplexity-agent"},"perplexity-agent/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32000},"cost":{"input":0.25,"output":2.5},"sourceProvider":"perplexity-agent"},"perplexity-agent/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"perplexity-agent"},"perplexity-agent/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"perplexity-agent"},"perplexity-agent/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"perplexity-agent"},"perplexity-agent/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"perplexity-agent"},"perplexity-agent/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"perplexity-agent"},"perplexity-agent/perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.25,"output":2.5,"cache_read":0.0625},"sourceProvider":"perplexity-agent"},"perplexity-agent/xai/grok-4-1-fast-non-reasoning":{"id":"xai/grok-4-1-fast-non-reasoning","name":"Grok 4.1 Fast (Non-Reasoning)","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"perplexity-agent"},"perplexity-agent/xai/grok-4.6":{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"perplexity-agent"},"perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"perplexity"},"perplexity/sonar-deep-research":{"id":"perplexity/sonar-deep-research","name":"Perplexity Sonar Deep Research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"perplexity"},"perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"perplexity"},"perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","family":"sonar-reasoning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":2,"output":8},"sourceProvider":"perplexity"},"pioneer/auto":{"id":"pioneer/auto","name":"Pioneer Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2025-06-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":4096},"sourceProvider":"pioneer"},"pioneer/claude-3-7-sonnet-latest":{"id":"pioneer/claude-3-7-sonnet-latest","name":"Claude Sonnet 3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"pioneer"},"pioneer/claude-fable-5":{"id":"pioneer/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":11,"output":55,"cache_read":1.1,"cache_write":13.75},"sourceProvider":"pioneer"},"pioneer/claude-haiku-4-5":{"id":"pioneer/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"pioneer"},"pioneer/claude-opus-4-1":{"id":"pioneer/claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"pioneer"},"pioneer/claude-opus-4-5":{"id":"pioneer/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/claude-opus-4-6":{"id":"pioneer/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/claude-opus-4-7":{"id":"pioneer/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/claude-opus-4-8":{"id":"pioneer/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/claude-opus-5":{"id":"pioneer/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/claude-sonnet-4-5":{"id":"pioneer/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"pioneer"},"pioneer/claude-sonnet-4-6":{"id":"pioneer/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"pioneer"},"pioneer/claude-sonnet-5":{"id":"pioneer/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"pioneer"},"pioneer/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":8192},"cost":{"input":0.27,"output":1.12,"cache_read":0.135,"cache_write":0.27},"sourceProvider":"pioneer"},"pioneer/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek-V3.1","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":131072},"cost":{"input":0.56,"output":1.68,"cache_read":0.56,"cache_write":0.56},"sourceProvider":"pioneer"},"pioneer/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.0197,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":0.435},"sourceProvider":"pioneer"},"pioneer/devstral-2":{"id":"pioneer/devstral-2","name":"Devstral 2","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-12","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.4,"cache_write":0.4},"sourceProvider":"pioneer"},"pioneer/fastino/gliguard-LLMGuardrails-300M":{"id":"fastino/gliguard-LLMGuardrails-300M","name":"GLiGuard LLM Guardrails 300M","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/fastino/gliner2-base-v1":{"id":"fastino/gliner2-base-v1","name":"GLiNER2 Base","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/fastino/gliner2-large-v1":{"id":"fastino/gliner2-large-v1","name":"GLiNER2 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/fastino/gliner2-multi-large-v1":{"id":"fastino/gliner2-multi-large-v1","name":"GLiNER2 Multi Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-30","last_updated":"2025-11-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/fastino/gliner2-multi-v1":{"id":"fastino/gliner2-multi-v1","name":"GLiNER2 Multi","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-30","last_updated":"2025-11-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/fastino/gliner2-privacy-filter-PII-multi":{"id":"fastino/gliner2-privacy-filter-PII-multi","name":"GLiNER2 Privacy Filter PII (Multi)","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/gemini-3-flash":{"id":"pioneer/gemini-3-flash","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.083333},"sourceProvider":"pioneer"},"pioneer/gemini-3.1-flash-lite":{"id":"pioneer/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.25,"output":1.5,"cache_read":0.03,"cache_write":0.25},"sourceProvider":"pioneer"},"pioneer/gemini-3.1-pro":{"id":"pioneer/gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":0.375},"sourceProvider":"pioneer"},"pioneer/gemini-3.5-flash":{"id":"pioneer/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.083333},"sourceProvider":"pioneer"},"pioneer/gemini-3.5-flash-lite":{"id":"pioneer/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"pioneer"},"pioneer/gemini-3.6-flash":{"id":"pioneer/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":1.5},"sourceProvider":"pioneer"},"pioneer/google/diffusiongemma-26B-A4B-it":{"id":"google/diffusiongemma-26B-A4B-it","name":"DiffusionGemma 26B-A4B IT","description":"Gemini model for general assistance, reasoning, and multimodal workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/google/gemma-3-4b-pt":{"id":"google/gemma-3-4b-pt","name":"Gemma 3 4B (Pretrained)","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-02-28","last_updated":"2025-02-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/google/gemma-4-12B-it":{"id":"google/gemma-4-12B-it","name":"Gemma 4 12B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-31","last_updated":"2026-05-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.25,"output":0.25,"cache_read":0.25,"cache_write":0.25},"sourceProvider":"pioneer"},"pioneer/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/google/gemma-4-E2B-it":{"id":"google/gemma-4-E2B-it","name":"Gemma 4 E2B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/google/gemma-4-E4B-it":{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/gpt-4.1":{"id":"pioneer/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":1,"cache_write":2},"sourceProvider":"pioneer"},"pioneer/gpt-4.1-mini":{"id":"pioneer/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.2,"cache_write":0.4},"sourceProvider":"pioneer"},"pioneer/gpt-4.1-nano":{"id":"pioneer/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.05,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/gpt-4o":{"id":"pioneer/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":2.5},"sourceProvider":"pioneer"},"pioneer/gpt-4o-mini":{"id":"pioneer/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/gpt-5-mini":{"id":"pioneer/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025,"cache_write":0.25},"sourceProvider":"pioneer"},"pioneer/gpt-5-nano":{"id":"pioneer/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005,"cache_write":0.05},"sourceProvider":"pioneer"},"pioneer/gpt-5.1":{"id":"pioneer/gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":131072},"cost":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":1.25},"sourceProvider":"pioneer"},"pioneer/gpt-5.3-codex":{"id":"pioneer/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":1.75},"sourceProvider":"pioneer"},"pioneer/gpt-5.4":{"id":"pioneer/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"pioneer"},"pioneer/gpt-5.4-mini":{"id":"pioneer/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":0.75},"sourceProvider":"pioneer"},"pioneer/gpt-5.4-nano":{"id":"pioneer/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/gpt-5.5":{"id":"pioneer/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"sourceProvider":"pioneer"},"pioneer/gpt-5.6-luna":{"id":"pioneer/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"pioneer"},"pioneer/gpt-5.6-sol":{"id":"pioneer/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"pioneer"},"pioneer/gpt-5.6-terra":{"id":"pioneer/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"pioneer"},"pioneer/grok-4.5":{"id":"pioneer/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.5,"cache_write":2},"sourceProvider":"pioneer"},"pioneer/HuggingFaceTB/SmolLM3-3B-Base":{"id":"HuggingFaceTB/SmolLM3-3B-Base","name":"SmolLM3 3B Base","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-30","last_updated":"2025-06-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/LiquidAI/LFM2-24B-A2B":{"id":"LiquidAI/LFM2-24B-A2B","name":"LFM2 24B A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-01-31","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.03,"output":0.12,"cache_read":0.03,"cache_write":0.03},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.1-8B-Instruct":{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-06-30","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.2-1B":{"id":"meta-llama/Llama-3.2-1B","name":"Llama-3.2-1B","description":"Compact open Llama base model for lightweight and on-device use","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.2-1B-Instruct":{"id":"meta-llama/Llama-3.2-1B-Instruct","name":"Llama 3.2 1B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-31","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":60000},"cost":{"input":0.1,"output":0.201,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.2-3B":{"id":"meta-llama/Llama-3.2-3B","name":"Llama-3.2-3B","description":"Small open Llama base model for lightweight text generation and self-hosting","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2023-12","release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.2-3B-Instruct":{"id":"meta-llama/Llama-3.2-3B-Instruct","name":"Llama 3.2 3B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2023-12-31","release_date":"2024-08-31","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":80000},"cost":{"input":0.1,"output":0.335,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9},"sourceProvider":"pioneer"},"pioneer/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":1.25},"sourceProvider":"pioneer"},"pioneer/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.279,"output":1.2,"cache_read":0.279,"cache_write":0.279},"sourceProvider":"pioneer"},"pioneer/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.3},"sourceProvider":"pioneer"},"pioneer/mistral-large-3":{"id":"pioneer/mistral-large-3","name":"Mistral Large 3","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/mistral-medium-3.5":{"id":"pioneer/mistral-medium-3.5","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":131072},"cost":{"input":1.5,"output":7.5,"cache_read":1.5,"cache_write":1.5},"sourceProvider":"pioneer"},"pioneer/mistralai/Codestral-22B-v0.1":{"id":"mistralai/Codestral-22B-v0.1","name":"Codestral-22B-v0.1","description":"Open Mistral code model for fill-in-the-middle and 80+ programming languages","family":"codestral","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-05-29","last_updated":"2024-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.3,"output":0.9,"cache_read":0.3,"cache_write":0.3},"sourceProvider":"pioneer"},"pioneer/mistralai/Magistral-Small-2506":{"id":"mistralai/Magistral-Small-2506","name":"Magistral Small","description":"Open Mistral reasoning model for transparent step-by-step problem solving","family":"magistral","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0.5,"output":1.5,"cache_read":0.5,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/mistralai/Ministral-8B-Instruct-2410":{"id":"mistralai/Ministral-8B-Instruct-2410","name":"Ministral 8B Instruct","description":"Efficient open Mistral edge model for on-device chat and function calling","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-10-16","last_updated":"2024-10-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/mistralai/Mistral-7B-Instruct-v0.3":{"id":"mistralai/Mistral-7B-Instruct-v0.3","name":"Mistral 7B Instruct v0.3","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2023-04-30","last_updated":"2023-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/mistralai/Mistral-Nemo-Instruct-2407":{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"Mistral Nemo","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-07-01","last_updated":"2024-07-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.02,"output":0.03,"cache_read":0.02,"cache_write":0.02},"sourceProvider":"pioneer"},"pioneer/mistralai/Mistral-Small-4-119B-2603":{"id":"mistralai/Mistral-Small-4-119B-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/mistralai/Pixtral-12B-2409":{"id":"mistralai/Pixtral-12B-2409","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4000},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":131072},"cost":{"input":0.95,"output":4,"cache_read":0.34,"cache_write":0.95},"sourceProvider":"pioneer"},"pioneer/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":0.95},"sourceProvider":"pioneer"},"pioneer/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3},"sourceProvider":"pioneer"},"pioneer/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16":{"id":"nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.05,"output":0.2,"cache_read":0.05,"cache_write":0.05},"sourceProvider":"pioneer"},"pioneer/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8":{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.09,"output":0.45,"cache_read":0.09,"cache_write":0.09},"sourceProvider":"pioneer"},"pioneer/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":2.5,"cache_read":0.15,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16":{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":4096},"cost":{"input":0.5,"output":0.5,"cache_read":0.5,"cache_write":0.5},"sourceProvider":"pioneer"},"pioneer/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.07,"output":0.3,"cache_read":0.035,"cache_write":0.07},"sourceProvider":"pioneer"},"pioneer/poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen2.5-Coder-0.5B":{"id":"Qwen/Qwen2.5-Coder-0.5B","name":"Qwen2.5-Coder-0.5B","description":"Tiny open Qwen code model for lightweight completion and on-device coding","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-11-12","last_updated":"2024-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-1.7B-Base":{"id":"Qwen/Qwen3-1.7B-Base","name":"Qwen3 1.7B Base","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1,"cache_write":0.1},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":1.2,"output":1.2,"cache_read":1.2,"cache_write":1.2},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen3 32B","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.9,"output":0.9,"cache_read":0.9,"cache_write":0.9},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-4B-Base":{"id":"Qwen/Qwen3-4B-Base","name":"Qwen3 4B Base","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.15,"output":0.15,"cache_read":0.15,"cache_write":0.15},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-4B-Instruct-2507":{"id":"Qwen/Qwen3-4B-Instruct-2507","name":"Qwen3 4B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3-8B":{"id":"Qwen/Qwen3-8B","name":"Qwen3 8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-03-31","release_date":"2025-03-31","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":40960,"output":40960},"cost":{"input":0.2,"output":0.2,"cache_read":0.2,"cache_write":0.2},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":0.3,"cache_read":0.3,"cache_write":0.3},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.6,"output":0.6,"cache_read":0.6,"cache_write":0.6},"sourceProvider":"pioneer"},"pioneer/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":1,"cache_read":0.028,"cache_write":0.175},"sourceProvider":"pioneer"},"pioneer/qwen3.6-flash":{"id":"pioneer/qwen3.6-flash","name":"Qwen3.6 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-27","last_updated":"2026-04-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.1875,"output":1.125,"cache_read":0.0375,"cache_write":0.234375},"sourceProvider":"pioneer"},"pioneer/qwen3.6-max-preview":{"id":"pioneer/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":240000,"output":64000},"cost":{"input":1.04,"output":6.24,"cache_read":0.208,"cache_write":1.3},"sourceProvider":"pioneer"},"pioneer/qwen3.6-plus":{"id":"pioneer/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.325,"output":1.95,"cache_read":0.065,"cache_write":0.40625},"sourceProvider":"pioneer"},"pioneer/qwen3.7-max":{"id":"pioneer/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":1.25,"output":3.75,"cache_read":0.25,"cache_write":1.5625},"sourceProvider":"pioneer"},"pioneer/qwen3.7-plus":{"id":"pioneer/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.4},"sourceProvider":"pioneer"},"pioneer/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":5},"sourceProvider":"pioneer"},"pioneer/XiaomiMiMo/MiMo-V2.5":{"id":"XiaomiMiMo/MiMo-V2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":0.14},"sourceProvider":"pioneer"},"pioneer/XiaomiMiMo/MiMo-V2.5-Pro":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131000},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":0.435},"sourceProvider":"pioneer"},"pioneer/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202000,"output":131072},"cost":{"input":0.98,"output":3.08,"cache_read":0.182,"cache_write":0.98},"sourceProvider":"pioneer"},"pioneer/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1040000,"output":128000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":1.4},"sourceProvider":"pioneer"},"poe/anthropic/claude-haiku-3":{"id":"anthropic/claude-haiku-3","name":"Claude-Haiku-3","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-03-09","last_updated":"2024-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"cost":{"input":0.21,"output":1.1,"cache_read":0.021,"cache_write":0.26},"sourceProvider":"poe"},"poe/anthropic/claude-haiku-3.5":{"id":"anthropic/claude-haiku-3.5","name":"Claude-Haiku-3.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"cost":{"input":0.68,"output":3.4,"cache_read":0.068,"cache_write":0.85},"sourceProvider":"poe"},"poe/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude-Haiku-4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":63999}],"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":64000},"cost":{"input":0.85,"output":4.3,"cache_read":0.085,"cache_write":1.1},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Claude-Opus-4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":192512,"output":28672},"cost":{"input":13,"output":64,"cache_read":1.3,"cache_write":16},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude-Opus-4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":31999}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":32000},"cost":{"input":13,"output":64,"cache_read":1.3,"cache_write":16},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude-Opus-4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":0,"max":63999}],"tool_call":true,"temperature":false,"release_date":"2025-11-21","last_updated":"2025-11-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":64000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude-Opus-4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":128000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.3},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude-Opus-4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":128000},"cost":{"input":4.3,"output":21,"cache_read":0.43,"cache_write":5.4},"sourceProvider":"poe"},"poe/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude-Opus-4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":128000},"cost":{"input":4.2929,"output":21.4646},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-3.5":{"id":"anthropic/claude-sonnet-3.5","name":"Claude-Sonnet-3.5","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-06-05","last_updated":"2024-06-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"status":"deprecated","cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-3.5-june":{"id":"anthropic/claude-sonnet-3.5-june","name":"Claude-Sonnet-3.5-June","description":"Legacy model retained for compatibility with older integrations","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-11-18","last_updated":"2024-11-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":189096,"output":8192},"status":"deprecated","cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-3.7":{"id":"anthropic/claude-sonnet-3.7","name":"Claude-Sonnet-3.7","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude-Sonnet-4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":64000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude-Sonnet-4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":31999}],"tool_call":true,"temperature":false,"release_date":"2025-09-26","last_updated":"2025-09-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":32768},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude-Sonnet-4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":983040,"output":128000},"cost":{"input":2.6,"output":13,"cache_read":0.26,"cache_write":3.2},"sourceProvider":"poe"},"poe/cerebras/gpt-oss-120b-cs":{"id":"cerebras/gpt-oss-120b-cs","name":"GPT-OSS-120B-CS","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":0},"cost":{"input":0.35,"output":0.75},"sourceProvider":"poe"},"poe/cerebras/llama-3.1-8b-cs":{"id":"cerebras/llama-3.1-8b-cs","name":"Llama-3.1-8B-CS","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-05-13","last_updated":"2025-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":0},"cost":{"input":0.1,"output":0.1},"sourceProvider":"poe"},"poe/cerebras/llama-3.3-70b-cs":{"id":"cerebras/llama-3.3-70b-cs","name":"llama-3.3-70b-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-05-13","last_updated":"2025-05-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"status":"deprecated","sourceProvider":"poe"},"poe/cerebras/qwen3-235b-2507-cs":{"id":"cerebras/qwen3-235b-2507-cs","name":"qwen3-235b-2507-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"status":"deprecated","sourceProvider":"poe"},"poe/cerebras/qwen3-32b-cs":{"id":"cerebras/qwen3-32b-cs","name":"qwen3-32b-cs","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-05-15","last_updated":"2025-05-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"status":"deprecated","sourceProvider":"poe"},"poe/elevenlabs/elevenlabs-music":{"id":"elevenlabs/elevenlabs-music","name":"ElevenLabs-Music","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-08-29","last_updated":"2025-08-29","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":2000,"output":0},"sourceProvider":"poe"},"poe/elevenlabs/elevenlabs-v2.5-turbo":{"id":"elevenlabs/elevenlabs-v2.5-turbo","name":"ElevenLabs-v2.5-Turbo","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-10-28","last_updated":"2024-10-28","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":128000,"output":0},"sourceProvider":"poe"},"poe/elevenlabs/elevenlabs-v3":{"id":"elevenlabs/elevenlabs-v3","name":"ElevenLabs-v3","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"elevenlabs","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":128000,"output":0},"sourceProvider":"poe"},"poe/empiriolabs/deepseek-v4-flash-el":{"id":"empiriolabs/deepseek-v4-flash-el","name":"DeepSeek-V4-Flash-EL","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-05-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":0.14,"output":0.28},"sourceProvider":"poe"},"poe/empiriolabs/deepseek-v4-pro-el":{"id":"empiriolabs/deepseek-v4-pro-el","name":"DeepSeek-V4-Pro-EL","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-04-24","last_updated":"2026-05-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"input":1000000,"output":384000},"cost":{"input":1.67,"output":3.33},"sourceProvider":"poe"},"poe/fireworks-ai/kimi-k2.5-fw":{"id":"fireworks-ai/kimi-k2.5-fw","name":"Kimi-K2.5-FW","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"input":245760,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"poe"},"poe/google/gemini-2.0-flash":{"id":"google/gemini-2.0-flash","name":"Gemini-2.0-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-12-11","last_updated":"2024-12-11","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":990000,"output":8192},"cost":{"input":0.1,"output":0.42},"sourceProvider":"poe"},"poe/google/gemini-2.0-flash-lite":{"id":"google/gemini-2.0-flash-lite","name":"Gemini-2.0-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":990000,"output":8192},"cost":{"input":0.052,"output":0.21},"sourceProvider":"poe"},"poe/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini-2.5-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":false,"release_date":"2025-04-26","last_updated":"2025-04-26","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1065535,"output":65535},"cost":{"input":0.21,"output":1.8,"cache_read":0.021},"sourceProvider":"poe"},"poe/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini-2.5-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"temperature":false,"release_date":"2025-06-19","last_updated":"2025-06-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1024000,"output":64000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"poe"},"poe/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini-2.5-Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":0,"max":32768}],"tool_call":true,"temperature":false,"release_date":"2025-02-05","last_updated":"2025-02-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1065535,"output":65535},"cost":{"input":0.87,"output":7,"cache_read":0.087},"sourceProvider":"poe"},"poe/google/gemini-3-flash":{"id":"google/gemini-3-flash","name":"Gemini-3-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-10-07","last_updated":"2025-10-07","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.4,"output":2.4,"cache_read":0.04},"sourceProvider":"poe"},"poe/google/gemini-3-pro":{"id":"google/gemini-3-pro","name":"Gemini-3-Pro","description":"Legacy model retained for compatibility with older integrations","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-10-22","last_updated":"2025-10-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"status":"deprecated","cost":{"input":1.6,"output":9.6,"cache_read":0.16},"sourceProvider":"poe"},"poe/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini-3.1-Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5},"sourceProvider":"poe"},"poe/google/gemini-3.1-pro":{"id":"google/gemini-3.1-pro","name":"Gemini-3.1-Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"poe"},"poe/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini-3.5-Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5152,"output":9.0909,"cache_read":0.1515},"sourceProvider":"poe"},"poe/google/gemini-deep-research":{"id":"google/gemini-deep-research","name":"gemini-deep-research","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":0},"status":"deprecated","cost":{"input":1.6,"output":9.6},"sourceProvider":"poe"},"poe/google/gemma-4-31b":{"id":"google/gemma-4-31b","name":"Gemma-4-31B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"poe"},"poe/google/imagen-3":{"id":"google/imagen-3","name":"Imagen-3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-10-15","last_updated":"2024-10-15","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/imagen-3-fast":{"id":"google/imagen-3-fast","name":"Imagen-3-Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-10-17","last_updated":"2024-10-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/imagen-4":{"id":"google/imagen-4","name":"Imagen-4","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/imagen-4-fast":{"id":"google/imagen-4-fast","name":"Imagen-4-Fast","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/imagen-4-ultra":{"id":"google/imagen-4-ultra","name":"Imagen-4-Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"imagen","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-05-24","last_updated":"2025-05-24","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/lyria":{"id":"google/lyria","name":"Lyria","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"lyria","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-06-04","last_updated":"2025-06-04","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/google/nano-banana":{"id":"google/nano-banana","name":"Nano-Banana","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"nano-banana","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":0},"cost":{"input":0.21,"output":1.8,"cache_read":0.021},"sourceProvider":"poe"},"poe/google/nano-banana-pro":{"id":"google/nano-banana-pro","name":"Nano-Banana-Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"nano-banana","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":65536,"output":0},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"poe"},"poe/google/veo-2":{"id":"google/veo-2","name":"Veo-2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/veo-3":{"id":"google/veo-3","name":"Veo-3","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-05-21","last_updated":"2025-05-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/veo-3-fast":{"id":"google/veo-3-fast","name":"Veo-3-Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-10-13","last_updated":"2025-10-13","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/veo-3.1":{"id":"google/veo-3.1","name":"Veo-3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/google/veo-3.1-fast":{"id":"google/veo-3.1-fast","name":"Veo-3.1-Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":480,"output":0},"sourceProvider":"poe"},"poe/ideogramai/ideogram":{"id":"ideogramai/ideogram","name":"Ideogram","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-04-03","last_updated":"2024-04-03","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":0},"sourceProvider":"poe"},"poe/ideogramai/ideogram-v2":{"id":"ideogramai/ideogram-v2","name":"Ideogram-v2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-08-21","last_updated":"2024-08-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":0},"sourceProvider":"poe"},"poe/ideogramai/ideogram-v2a":{"id":"ideogramai/ideogram-v2a","name":"Ideogram-v2a","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":0},"sourceProvider":"poe"},"poe/ideogramai/ideogram-v2a-turbo":{"id":"ideogramai/ideogram-v2a-turbo","name":"Ideogram-v2a-Turbo","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ideogram","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-02-27","last_updated":"2025-02-27","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":150,"output":0},"sourceProvider":"poe"},"poe/lumalabs/ray2":{"id":"lumalabs/ray2","name":"Ray2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ray","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-02-20","last_updated":"2025-02-20","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":5000,"output":0},"sourceProvider":"poe"},"poe/novita/deepseek-v3.2":{"id":"novita/deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":0},"cost":{"input":0.27,"output":0.4,"cache_read":0.13},"sourceProvider":"poe"},"poe/novita/glm-4.6":{"id":"novita/glm-4.6","name":"GLM-4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/novita/glm-4.6v":{"id":"novita/glm-4.6v","name":"glm-4.6v","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":32768},"sourceProvider":"poe"},"poe/novita/glm-4.7":{"id":"novita/glm-4.7","name":"glm-4.7","description":"Legacy model retained for compatibility with older integrations","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"status":"deprecated","sourceProvider":"poe"},"poe/novita/glm-4.7-flash":{"id":"novita/glm-4.7-flash","name":"glm-4.7-flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":65500},"sourceProvider":"poe"},"poe/novita/glm-4.7-n":{"id":"novita/glm-4.7-n","name":"glm-4.7-n","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"sourceProvider":"poe"},"poe/novita/glm-5":{"id":"novita/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"poe"},"poe/novita/kimi-k2-thinking":{"id":"novita/kimi-k2-thinking","name":"kimi-k2-thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-11-07","last_updated":"2025-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":0},"sourceProvider":"poe"},"poe/novita/kimi-k2.5":{"id":"novita/kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":262144},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"poe"},"poe/novita/kimi-k2.6":{"id":"novita/kimi-k2.6","name":"Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-20","last_updated":"2026-05-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.96,"output":4.04,"cache_read":0.16},"sourceProvider":"poe"},"poe/novita/minimax-m2.1":{"id":"novita/minimax-m2.1","name":"minimax-m2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":false,"release_date":"2025-12-26","last_updated":"2025-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":205000,"output":131072},"sourceProvider":"poe"},"poe/openai/chatgpt-4o-latest":{"id":"openai/chatgpt-4o-latest","name":"ChatGPT-4o-Latest","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-08-14","last_updated":"2024-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"status":"deprecated","cost":{"input":4.5,"output":14},"sourceProvider":"poe"},"poe/openai/dall-e-3":{"id":"openai/dall-e-3","name":"DALL-E-3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"dall-e","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":800,"output":0},"sourceProvider":"poe"},"poe/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-09-13","last_updated":"2023-09-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"output":2048},"cost":{"input":0.45,"output":1.4},"sourceProvider":"poe"},"poe/openai/gpt-3.5-turbo-instruct":{"id":"openai/gpt-3.5-turbo-instruct","name":"GPT-3.5-Turbo-Instruct","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-09-20","last_updated":"2023-09-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":3500,"output":1024},"cost":{"input":1.4,"output":1.8},"sourceProvider":"poe"},"poe/openai/gpt-3.5-turbo-raw":{"id":"openai/gpt-3.5-turbo-raw","name":"GPT-3.5-Turbo-Raw","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-09-27","last_updated":"2023-09-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":4524,"output":2048},"cost":{"input":0.45,"output":1.4},"sourceProvider":"poe"},"poe/openai/gpt-4-classic":{"id":"openai/gpt-4-classic","name":"GPT-4-Classic","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-03-25","last_updated":"2024-03-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"status":"deprecated","cost":{"input":27,"output":54},"sourceProvider":"poe"},"poe/openai/gpt-4-classic-0314":{"id":"openai/gpt-4-classic-0314","name":"GPT-4-Classic-0314","description":"Legacy model retained for compatibility with older integrations","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-08-26","last_updated":"2024-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"status":"deprecated","cost":{"input":27,"output":54},"sourceProvider":"poe"},"poe/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4-Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-09-13","last_updated":"2023-09-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":9,"output":27},"sourceProvider":"poe"},"poe/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"sourceProvider":"poe"},"poe/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.36,"output":1.4,"cache_read":0.09},"sourceProvider":"poe"},"poe/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.09,"output":0.36,"cache_read":0.022},"sourceProvider":"poe"},"poe/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-05-13","last_updated":"2024-05-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"sourceProvider":"poe"},"poe/openai/gpt-4o-aug":{"id":"openai/gpt-4o-aug","name":"GPT-4o-Aug","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-11-21","last_updated":"2024-11-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2.2,"output":9,"cache_read":1.1},"sourceProvider":"poe"},"poe/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":124096,"output":4096},"cost":{"input":0.14,"output":0.54,"cache_read":0.068},"sourceProvider":"poe"},"poe/openai/gpt-4o-mini-search":{"id":"openai/gpt-4o-mini-search","name":"GPT-4o-mini-Search","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-03-11","last_updated":"2025-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.14,"output":0.54},"sourceProvider":"poe"},"poe/openai/gpt-4o-search":{"id":"openai/gpt-4o-search","name":"GPT-4o-Search","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-03-11","last_updated":"2025-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":2.2,"output":9},"sourceProvider":"poe"},"poe/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5-chat":{"id":"openai/gpt-5-chat","name":"GPT-5-Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","family":"gpt-codex","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9},"sourceProvider":"poe"},"poe/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-06-25","last_updated":"2025-06-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"sourceProvider":"poe"},"poe/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.045,"output":0.36,"cache_read":0.0045},"sourceProvider":"poe"},"poe/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":14,"output":110},"sourceProvider":"poe"},"poe/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1-Codex-Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":0.22,"output":1.8,"cache_read":0.022},"sourceProvider":"poe"},"poe/openai/gpt-5.1-instant":{"id":"openai/gpt-5.1-instant","name":"GPT-5.1-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":9,"cache_read":0.11},"sourceProvider":"poe"},"poe/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"sourceProvider":"poe"},"poe/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"sourceProvider":"poe"},"poe/openai/gpt-5.2-instant":{"id":"openai/gpt-5.2-instant","name":"GPT-5.2-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.6,"output":13,"cache_read":0.16},"sourceProvider":"poe"},"poe/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":19,"output":150},"sourceProvider":"poe"},"poe/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-10","last_updated":"2026-02-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.6,"output":13,"cache_read":0.16},"sourceProvider":"poe"},"poe/openai/gpt-5.3-codex-spark":{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3-Codex-Spark","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"poe"},"poe/openai/gpt-5.3-instant":{"id":"openai/gpt-5.3-instant","name":"GPT-5.3-Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":1.6,"output":13,"cache_read":0.16},"sourceProvider":"poe"},"poe/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","pdf"],"output":["image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.2,"output":14,"cache_read":0.22},"sourceProvider":"poe"},"poe/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4-Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-12","last_updated":"2026-03-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.68,"output":4,"cache_read":0.068},"sourceProvider":"poe"},"poe/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4-Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.18,"output":1.1,"cache_read":0.018},"sourceProvider":"poe"},"poe/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4-Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":27,"output":160},"sourceProvider":"poe"},"poe/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":4.5455,"output":27.2727,"cache_read":0.4545},"sourceProvider":"poe"},"poe/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5-Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":27.2727,"output":163.6364},"sourceProvider":"poe"},"poe/openai/gpt-image-1":{"id":"openai/gpt-image-1","name":"GPT-Image-1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-03-31","last_updated":"2025-03-31","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":0},"sourceProvider":"poe"},"poe/openai/gpt-image-1-mini":{"id":"openai/gpt-image-1-mini","name":"GPT-Image-1-Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/openai/gpt-image-1.5":{"id":"openai/gpt-image-1.5","name":"gpt-image-1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":128000,"output":0},"sourceProvider":"poe"},"poe/openai/gpt-image-2":{"id":"openai/gpt-image-2","name":"GPT-Image-2","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5.0505,"output":32.3232,"cache_read":1.2626},"sourceProvider":"poe"},"poe/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2024-12-18","last_updated":"2024-12-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":14,"output":54},"sourceProvider":"poe"},"poe/openai/o1-pro":{"id":"openai/o1-pro","name":"o1-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-03-19","last_updated":"2025-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":140,"output":540},"sourceProvider":"poe"},"poe/openai/o3":{"id":"openai/o3","name":"o3","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"sourceProvider":"poe"},"poe/openai/o3-deep-research":{"id":"openai/o3-deep-research","name":"o3-deep-research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":9,"output":36,"cache_read":2.2},"sourceProvider":"poe"},"poe/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-01-31","last_updated":"2025-01-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4},"sourceProvider":"poe"},"poe/openai/o3-mini-high":{"id":"openai/o3-mini-high","name":"o3-mini-high","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-01-31","last_updated":"2025-01-31","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4},"sourceProvider":"poe"},"poe/openai/o3-pro":{"id":"openai/o3-pro","name":"o3-pro","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":18,"output":72},"sourceProvider":"poe"},"poe/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.99,"output":4,"cache_read":0.25},"sourceProvider":"poe"},"poe/openai/o4-mini-deep-research":{"id":"openai/o4-mini-deep-research","name":"o4-mini-deep-research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-06-27","last_updated":"2025-06-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.8,"output":7.2,"cache_read":0.45},"sourceProvider":"poe"},"poe/openai/sora-2":{"id":"openai/sora-2","name":"Sora-2","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"sora","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/openai/sora-2-pro":{"id":"openai/sora-2-pro","name":"Sora-2-Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"sora","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/poetools/claude-code":{"id":"poetools/claude-code","name":"claude-code","description":"Claude model for careful reasoning, writing, coding, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-27","last_updated":"2025-11-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"poe"},"poe/runwayml/runway":{"id":"runwayml/runway","name":"Runway","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"runway","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-10-11","last_updated":"2024-10-11","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":256,"output":0},"sourceProvider":"poe"},"poe/runwayml/runway-gen-4-turbo":{"id":"runwayml/runway-gen-4-turbo","name":"Runway-Gen-4-Turbo","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"runway","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-05-09","last_updated":"2025-05-09","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":256,"output":0},"sourceProvider":"poe"},"poe/stabilityai/stablediffusionxl":{"id":"stabilityai/stablediffusionxl","name":"StableDiffusionXL","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"stable-diffusion","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2023-07-09","last_updated":"2023-07-09","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":200,"output":0},"sourceProvider":"poe"},"poe/topazlabs-co/topazlabs":{"id":"topazlabs-co/topazlabs","name":"TopazLabs","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"topazlabs","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":204,"output":0},"sourceProvider":"poe"},"poe/trytako/tako":{"id":"trytako/tako","name":"Tako","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"tako","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":0},"sourceProvider":"poe"},"poe/xai/grok-3":{"id":"xai/grok-3","name":"Grok 3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-04-11","last_updated":"2025-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"poe"},"poe/xai/grok-3-mini":{"id":"xai/grok-3-mini","name":"Grok 3 Mini","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"release_date":"2025-04-11","last_updated":"2025-04-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.3,"output":0.5,"cache_read":0.075},"sourceProvider":"poe"},"poe/xai/grok-4":{"id":"xai/grok-4","name":"Grok-4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-07-10","last_updated":"2025-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"poe"},"poe/xai/grok-4-fast-non-reasoning":{"id":"xai/grok-4-fast-non-reasoning","name":"Grok-4-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-09-16","last_updated":"2025-09-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"poe"},"poe/xai/grok-4-fast-reasoning":{"id":"xai/grok-4-fast-reasoning","name":"Grok-4-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-09-16","last_updated":"2025-09-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"poe"},"poe/xai/grok-4.1-fast-non-reasoning":{"id":"xai/grok-4.1-fast-non-reasoning","name":"Grok-4.1-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"sourceProvider":"poe"},"poe/xai/grok-4.1-fast-reasoning":{"id":"xai/grok-4.1-fast-reasoning","name":"Grok-4.1-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"sourceProvider":"poe"},"poe/xai/grok-4.20-multi-agent":{"id":"xai/grok-4.20-multi-agent","name":"Grok-4.20-Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":false,"tool_call":true,"temperature":false,"release_date":"2026-03-13","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":0},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"poe"},"poe/xai/grok-code-fast-1":{"id":"xai/grok-code-fast-1","name":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"release_date":"2025-08-22","last_updated":"2025-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"cost":{"input":0.2,"output":1.5,"cache_read":0.02},"sourceProvider":"poe"},"poolside/laguna-m.1":{"id":"poolside/laguna-m.1","name":"Laguna M.1","description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"poolside"},"poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"poolside"},"poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":false,"temperature":true,"release_date":"2026-07-02","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"poolside"},"privatemode-ai/deepseek-ocr-2":{"id":"privatemode-ai/deepseek-ocr-2","name":"DeepSeek OCR 2","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","attachment":true,"reasoning":false,"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"status":"beta","cost":{"input":0.8897,"output":1.4675,"cache_read":0.0924},"sourceProvider":"privatemode-ai"},"privatemode-ai/gpt-oss-120b":{"id":"privatemode-ai/gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.4969,"output":1.9644,"cache_read":0.0462},"sourceProvider":"privatemode-ai"},"privatemode-ai/kimi-k2.6":{"id":"privatemode-ai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":262144},"cost":{"input":1.791,"output":8.9436,"cache_read":0.1733},"sourceProvider":"privatemode-ai"},"privatemode-ai/kimi-latest":{"id":"privatemode-ai/kimi-latest","name":"Kimi (latest)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":262144},"cost":{"input":1.791,"output":8.9436,"cache_read":0.1733},"sourceProvider":"privatemode-ai"},"privatemode-ai/qwen3-embedding-4b":{"id":"privatemode-ai/qwen3-embedding-4b","name":"Qwen3-Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-06","release_date":"2025-06-06","last_updated":"2025-06-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":2560},"cost":{"input":0.1502,"output":0},"sourceProvider":"privatemode-ai"},"privatemode-ai/voxtral-mini-3b":{"id":"privatemode-ai/voxtral-mini-3b","name":"Voxtral Mini 3B","description":"Speech-to-text model for audio transcription, translation, and audio understanding","family":"voxtral","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-07","last_updated":"2025-07","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":32000},"cost":{"input":0.00462,"output":0},"sourceProvider":"privatemode-ai"},"privatemode-ai/whisper-large-v3":{"id":"privatemode-ai/whisper-large-v3","name":"Whisper large-v3","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":true,"reasoning":false,"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0.01618,"output":0},"sourceProvider":"privatemode-ai"},"qihang-ai/claude-haiku-4-5-20251001":{"id":"qihang-ai/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-10-01","last_updated":"2025-10-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.14,"output":0.71},"sourceProvider":"qihang-ai"},"qihang-ai/claude-opus-4-5-20251101":{"id":"qihang-ai/claude-opus-4-5-20251101","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":0.71,"output":3.57},"sourceProvider":"qihang-ai"},"qihang-ai/claude-sonnet-4-5-20250929":{"id":"qihang-ai/claude-sonnet-4-5-20250929","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.43,"output":2.14},"sourceProvider":"qihang-ai"},"qihang-ai/gemini-2.5-flash":{"id":"qihang-ai/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.09,"output":0.71,"tiers":[{"input":0.09,"output":0.71,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.09,"output":0.71}},"sourceProvider":"qihang-ai"},"qihang-ai/gemini-3-flash-preview":{"id":"qihang-ai/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.07,"output":0.43,"tiers":[{"input":0.07,"output":0.43,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.07,"output":0.43}},"sourceProvider":"qihang-ai"},"qihang-ai/gemini-3-pro-preview":{"id":"qihang-ai/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-11","release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.57,"output":3.43},"sourceProvider":"qihang-ai"},"qihang-ai/gpt-5-mini":{"id":"qihang-ai/gpt-5-mini","name":"GPT-5-Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.04,"output":0.29},"sourceProvider":"qihang-ai"},"qihang-ai/gpt-5.2":{"id":"qihang-ai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2},"sourceProvider":"qihang-ai"},"qihang-ai/gpt-5.2-codex":{"id":"qihang-ai/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.14,"output":1.14},"sourceProvider":"qihang-ai"},"qiniu-ai/claude-3.5-haiku":{"id":"qiniu-ai/claude-3.5-haiku","name":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-3.5-sonnet":{"id":"qiniu-ai/claude-3.5-sonnet","name":"Claude 3.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-09","last_updated":"2025-09-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8200},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-3.7-sonnet":{"id":"qiniu-ai/claude-3.7-sonnet","name":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.0-opus":{"id":"qiniu-ai/claude-4.0-opus","name":"Claude 4.0 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.0-sonnet":{"id":"qiniu-ai/claude-4.0-sonnet","name":"Claude 4.0 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.1-opus":{"id":"qiniu-ai/claude-4.1-opus","name":"Claude 4.1 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.5-haiku":{"id":"qiniu-ai/claude-4.5-haiku","name":"Claude 4.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-16","last_updated":"2025-10-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.5-opus":{"id":"qiniu-ai/claude-4.5-opus","name":"Claude 4.5 Opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"sourceProvider":"qiniu-ai"},"qiniu-ai/claude-4.5-sonnet":{"id":"qiniu-ai/claude-4.5-sonnet","name":"Claude 4.5 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek-r1":{"id":"qiniu-ai/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek-r1-0528":{"id":"qiniu-ai/deepseek-r1-0528","name":"DeepSeek-R1-0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek-v3":{"id":"qiniu-ai/deepseek-v3","name":"DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek-v3-0324":{"id":"qiniu-ai/deepseek-v3-0324","name":"DeepSeek-V3-0324","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek-v3.1":{"id":"qiniu-ai/deepseek-v3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-19","last_updated":"2025-08-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-math-v2":{"id":"deepseek/deepseek-math-v2","name":"Deepseek/Deepseek-Math-V2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-12-04","last_updated":"2025-12-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":160000,"output":160000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-v3.1-terminus-thinking":{"id":"deepseek/deepseek-v3.1-terminus-thinking","name":"DeepSeek/DeepSeek-V3.1-Terminus-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-v3.2-251201":{"id":"deepseek/deepseek-v3.2-251201","name":"Deepseek/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/deepseek/deepseek-v3.2-exp-thinking":{"id":"deepseek/deepseek-v3.2-exp-thinking","name":"DeepSeek/DeepSeek-V3.2-Exp-Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-1.5-pro-32k":{"id":"qiniu-ai/doubao-1.5-pro-32k","name":"Doubao 1.5 Pro 32k","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":12000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-1.5-thinking-pro":{"id":"qiniu-ai/doubao-1.5-thinking-pro","name":"Doubao 1.5 Thinking Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-1.5-vision-pro":{"id":"qiniu-ai/doubao-1.5-vision-pro","name":"Doubao 1.5 Vision Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-1.6":{"id":"qiniu-ai/doubao-seed-1.6","name":"Doubao-Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-1.6-flash":{"id":"qiniu-ai/doubao-seed-1.6-flash","name":"Doubao-Seed 1.6 Flash","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-1.6-thinking":{"id":"qiniu-ai/doubao-seed-1.6-thinking","name":"Doubao-Seed 1.6 Thinking","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-15","last_updated":"2025-08-15","modalities":{"input":["image","text","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-2.0-code":{"id":"qiniu-ai/doubao-seed-2.0-code","name":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-2.0-lite":{"id":"qiniu-ai/doubao-seed-2.0-lite","name":"Doubao Seed 2.0 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-2.0-mini":{"id":"qiniu-ai/doubao-seed-2.0-mini","name":"Doubao Seed 2.0 Mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/doubao-seed-2.0-pro":{"id":"qiniu-ai/doubao-seed-2.0-pro","name":"Doubao Seed 2.0 Pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.0-flash":{"id":"qiniu-ai/gemini-2.0-flash","name":"Gemini 2.0 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.0-flash-lite":{"id":"qiniu-ai/gemini-2.0-flash-lite","name":"Gemini 2.0 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.5-flash":{"id":"qiniu-ai/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.5-flash-image":{"id":"qiniu-ai/gemini-2.5-flash-image","name":"Gemini 2.5 Flash Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-10-22","last_updated":"2025-10-22","modalities":{"input":["text","image"],"output":["image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.5-flash-lite":{"id":"qiniu-ai/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-2.5-pro":{"id":"qiniu-ai/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-3.0-flash-preview":{"id":"qiniu-ai/gemini-3.0-flash-preview","name":"Gemini 3.0 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-3.0-pro-image-preview":{"id":"qiniu-ai/gemini-3.0-pro-image-preview","name":"Gemini 3.0 Pro Image Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/gemini-3.0-pro-preview":{"id":"qiniu-ai/gemini-3.0-pro-preview","name":"Gemini 3.0 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","video","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/glm-4.5":{"id":"qiniu-ai/glm-4.5","name":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":98304},"sourceProvider":"qiniu-ai"},"qiniu-ai/glm-4.5-air":{"id":"qiniu-ai/glm-4.5-air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/gpt-oss-120b":{"id":"qiniu-ai/gpt-oss-120b","name":"gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/gpt-oss-20b":{"id":"qiniu-ai/gpt-oss-20b","name":"gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-06","last_updated":"2025-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/kimi-k2":{"id":"qiniu-ai/kimi-k2","name":"Kimi K2","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/kling-v2-6":{"id":"qiniu-ai/kling-v2-6","name":"Kling-V2 6","description":"Video model for prompt-guided generation, editing, and motion workflows","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-01-13","last_updated":"2026-01-13","modalities":{"input":["text","image","video"],"output":["video"]},"open_weights":false,"limit":{"context":99999999,"output":99999999},"sourceProvider":"qiniu-ai"},"qiniu-ai/meituan/longcat-flash-chat":{"id":"meituan/longcat-flash-chat","name":"Meituan/Longcat-Flash-Chat","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-11-05","last_updated":"2025-11-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"sourceProvider":"qiniu-ai"},"qiniu-ai/meituan/longcat-flash-lite":{"id":"meituan/longcat-flash-lite","name":"Meituan/Longcat-Flash-Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":320000},"sourceProvider":"qiniu-ai"},"qiniu-ai/mimo-v2-flash":{"id":"qiniu-ai/mimo-v2-flash","name":"Mimo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"sourceProvider":"qiniu-ai"},"qiniu-ai/MiniMax-M1":{"id":"qiniu-ai/MiniMax-M1","name":"MiniMax M1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":80000},"sourceProvider":"qiniu-ai"},"qiniu-ai/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"Minimax/Minimax-M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"Minimax/Minimax-M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"Minimax/Minimax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"Minimax/Minimax-M2.5 Highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-08","last_updated":"2025-09-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":100000},"sourceProvider":"qiniu-ai"},"qiniu-ai/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-07","last_updated":"2025-11-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":100000},"sourceProvider":"qiniu-ai"},"qiniu-ai/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"sourceProvider":"qiniu-ai"},"qiniu-ai/openai/gpt-5":{"id":"openai/gpt-5","name":"OpenAI/GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"OpenAI/GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen-max-2025-01-25":{"id":"qiniu-ai/qwen-max-2025-01-25","name":"Qwen2.5-Max-2025-01-25","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen-turbo":{"id":"qiniu-ai/qwen-turbo","name":"Qwen-Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen-vl-max-2025-01-25":{"id":"qiniu-ai/qwen-vl-max-2025-01-25","name":"Qwen VL-MAX-2025-01-25","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen2.5-vl-72b-instruct":{"id":"qiniu-ai/qwen2.5-vl-72b-instruct","name":"Qwen 2.5 VL 72B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen2.5-vl-7b-instruct":{"id":"qiniu-ai/qwen2.5-vl-7b-instruct","name":"Qwen 2.5 VL 7B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-235b-a22b":{"id":"qiniu-ai/qwen3-235b-a22b","name":"Qwen 3 235B A22B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-235b-a22b-instruct-2507":{"id":"qiniu-ai/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235b A22B Instruct 2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-235b-a22b-thinking-2507":{"id":"qiniu-ai/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B A22B Thinking 2507","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-12","last_updated":"2025-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-30b-a3b":{"id":"qiniu-ai/qwen3-30b-a3b","name":"Qwen3 30B A3B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-30b-a3b-instruct-2507":{"id":"qiniu-ai/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30b A3b Instruct 2507","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-30b-a3b-thinking-2507":{"id":"qiniu-ai/qwen3-30b-a3b-thinking-2507","name":"Qwen3 30b A3b Thinking 2507","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-04","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":126000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-32b":{"id":"qiniu-ai/qwen3-32b","name":"Qwen3 32B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-coder-480b-a35b-instruct":{"id":"qiniu-ai/qwen3-coder-480b-a35b-instruct","name":"Qwen3 Coder 480B A35B Instruct","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-14","last_updated":"2025-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-max":{"id":"qiniu-ai/qwen3-max","name":"Qwen3 Max","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-max-preview":{"id":"qiniu-ai/qwen3-max-preview","name":"Qwen3 Max Preview","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-06","last_updated":"2025-09-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-next-80b-a3b-instruct":{"id":"qiniu-ai/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-12","last_updated":"2025-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-next-80b-a3b-thinking":{"id":"qiniu-ai/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-12","last_updated":"2025-09-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3-vl-30b-a3b-thinking":{"id":"qiniu-ai/qwen3-vl-30b-a3b-thinking","name":"Qwen3-Vl 30b A3b Thinking","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-09","last_updated":"2026-02-09","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"sourceProvider":"qiniu-ai"},"qiniu-ai/qwen3.5-397b-a17b":{"id":"qiniu-ai/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-22","last_updated":"2026-02-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"sourceProvider":"qiniu-ai"},"qiniu-ai/stepfun-ai/gelab-zero-4b-preview":{"id":"stepfun-ai/gelab-zero-4b-preview","name":"Stepfun-Ai/Gelab Zero 4b Preview","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"Stepfun/Step-3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":64000,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4-fast":{"id":"x-ai/grok-4-fast","name":"x-AI/Grok-4-Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-20","last_updated":"2025-09-20","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4-fast-non-reasoning":{"id":"x-ai/grok-4-fast-non-reasoning","name":"X-Ai/Grok-4-Fast-Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4-fast-reasoning":{"id":"x-ai/grok-4-fast-reasoning","name":"X-Ai/Grok-4-Fast-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4.1-fast":{"id":"x-ai/grok-4.1-fast","name":"x-AI/Grok-4.1-Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4.1-fast-non-reasoning":{"id":"x-ai/grok-4.1-fast-non-reasoning","name":"X-Ai/Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-4.1-fast-reasoning":{"id":"x-ai/grok-4.1-fast-reasoning","name":"X-Ai/Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-19","last_updated":"2025-12-19","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":20000000,"output":2000000},"sourceProvider":"qiniu-ai"},"qiniu-ai/x-ai/grok-code-fast-1":{"id":"x-ai/grok-code-fast-1","name":"x-AI/Grok-Code-Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":10000},"sourceProvider":"qiniu-ai"},"qiniu-ai/xiaomi/mimo-v2-flash":{"id":"xiaomi/mimo-v2-flash","name":"Xiaomi/Mimo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"sourceProvider":"qiniu-ai"},"qiniu-ai/z-ai/autoglm-phone-9b":{"id":"z-ai/autoglm-phone-9b","name":"Z-Ai/Autoglm Phone 9b","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":12800,"output":4096},"sourceProvider":"qiniu-ai"},"qiniu-ai/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"Z-AI/GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-10-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"sourceProvider":"qiniu-ai"},"qiniu-ai/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"Z-Ai/GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":200000},"sourceProvider":"qiniu-ai"},"qiniu-ai/z-ai/glm-5":{"id":"z-ai/glm-5","name":"Z-Ai/GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"sourceProvider":"qiniu-ai"},"qvac/gemma4-31b":{"id":"qvac/gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/gpt-oss-120b":{"id":"qvac/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/gpt-oss-20b":{"id":"qvac/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.5-0.8b":{"id":"qvac/qwen3.5-0.8b","name":"Qwen3.5 0.8B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.5-2b":{"id":"qvac/qwen3.5-2b","name":"Qwen3.5 2B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.5-4b":{"id":"qvac/qwen3.5-4b","name":"Qwen3.5 4B","description":"Qwen instruction model for multilingual chat and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-01","last_updated":"2025-11-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.5-9b":{"id":"qvac/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.6-27b":{"id":"qvac/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"qvac/qwen3.6-35b-a3b":{"id":"qvac/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"qvac"},"regolo-ai/apertus-70b":{"id":"regolo-ai/apertus-70b","name":"Apertus 70B","description":"Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-02","last_updated":"2025-09-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":30000,"output":30000},"cost":{"input":0.46,"output":2.42},"sourceProvider":"regolo-ai"},"regolo-ai/brick-complexity-pro":{"id":"regolo-ai/brick-complexity-pro","name":"Brick Complexity Pro","description":"Complexity classifier that powers the Brick semantic router by extracting query difficulty","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":100000,"output":15000},"cost":{"input":0.12,"output":0.46},"sourceProvider":"regolo-ai"},"regolo-ai/brick-v1-beta":{"id":"regolo-ai/brick-v1-beta","name":"Brick v1 Beta","description":"Semantic router by Regolo.ai that directs each request to the most suitable model, optimizing costs and performance","family":"model-router","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":100000,"output":15000},"status":"beta","cost":{"input":0,"output":0},"sourceProvider":"regolo-ai"},"regolo-ai/deepseek-ocr-2":{"id":"regolo-ai/deepseek-ocr-2","name":"DeepSeek OCR 2","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","attachment":true,"reasoning":false,"tool_call":false,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":4000,"output":4000},"cost":{"input":0,"output":0},"sourceProvider":"regolo-ai"},"regolo-ai/faster-whisper-large-v3":{"id":"regolo-ai/faster-whisper-large-v3","name":"Faster Whisper Large v3","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2024-10-01","last_updated":"2024-10-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":448,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"regolo-ai"},"regolo-ai/gemma4-31b":{"id":"regolo-ai/gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":100000},"cost":{"input":0.46,"output":2.42},"sourceProvider":"regolo-ai"},"regolo-ai/glm5.2":{"id":"regolo-ai/glm5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":96000,"output":96000},"cost":{"input":2.31,"output":6},"sourceProvider":"regolo-ai"},"regolo-ai/gpt-oss-120b":{"id":"regolo-ai/gpt-oss-120b","name":"GPT-OSS-120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1,"output":4.2},"sourceProvider":"regolo-ai"},"regolo-ai/gpt-oss-20b":{"id":"regolo-ai/gpt-oss-20b","name":"GPT-OSS-20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.4,"output":1.8},"sourceProvider":"regolo-ai"},"regolo-ai/llama-3.3-70b-instruct":{"id":"regolo-ai/llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-04-28","last_updated":"2025-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.6,"output":2.7},"sourceProvider":"regolo-ai"},"regolo-ai/mistral-small-4-119b":{"id":"regolo-ai/mistral-small-4-119b","name":"Mistral Small 4 119B","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-03-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":16384},"cost":{"input":0.75,"output":3},"sourceProvider":"regolo-ai"},"regolo-ai/qwen-image":{"id":"regolo-ai/qwen-image","name":"Qwen-Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.5,"output":2},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3-coder-next":{"id":"regolo-ai/qwen3-coder-next","name":"Qwen3-Coder-Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.3,"output":1.2},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3-embedding-8b":{"id":"regolo-ai/qwen3-embedding-8b","name":"Qwen3-Embedding-8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.1,"output":0.1},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3-reranker-4b":{"id":"regolo-ai/qwen3-reranker-4b","name":"Qwen3-Reranker-4B","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":8192},"cost":{"input":0.12,"output":0.12},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3.5-122b":{"id":"regolo-ai/qwen3.5-122b","name":"Qwen3.5-122B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.9,"output":3.6},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3.5-9b":{"id":"regolo-ai/qwen3.5-9b","name":"Qwen3.5-9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-01","last_updated":"2026-02-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"regolo-ai"},"regolo-ai/qwen3.6-27b":{"id":"regolo-ai/qwen3.6-27b","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":120000,"output":120000},"cost":{"input":0.58,"output":2.42},"sourceProvider":"regolo-ai"},"requesty/claude-fable-5":{"id":"requesty/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":9,"output":45,"cache_read":0.9,"cache_write":11.25},"sourceProvider":"requesty"},"requesty/claude-fable-5@eu":{"id":"requesty/claude-fable-5@eu","name":"Claude Fable 5 (EU)","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":9.9,"output":49.5,"cache_read":0.99,"cache_write":12.375},"sourceProvider":"requesty"},"requesty/claude-haiku-4-5":{"id":"requesty/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.9,"output":4.5,"cache_read":0.09,"cache_write":1.125},"sourceProvider":"requesty"},"requesty/claude-haiku-4-5@eu":{"id":"requesty/claude-haiku-4-5@eu","name":"Claude Haiku 4.5 (latest) (EU)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.99,"output":4.95,"cache_read":0.099,"cache_write":1.2375},"sourceProvider":"requesty"},"requesty/claude-opus-4-1":{"id":"requesty/claude-opus-4-1","name":"Claude Opus 4.1 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"cost":{"input":13.5,"output":67.5,"cache_read":1.35,"cache_write":16.875},"sourceProvider":"requesty"},"requesty/claude-opus-4-5":{"id":"requesty/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":5.625},"sourceProvider":"requesty"},"requesty/claude-opus-4-5@eu":{"id":"requesty/claude-opus-4-5@eu","name":"Claude Opus 4.5 (latest) (EU)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":4.95,"output":24.75,"cache_read":0.495,"cache_write":6.1875},"sourceProvider":"requesty"},"requesty/claude-opus-4-6":{"id":"requesty/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":5.625},"sourceProvider":"requesty"},"requesty/claude-opus-4-6@eu":{"id":"requesty/claude-opus-4-6@eu","name":"Claude Opus 4.6 (EU)","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.95,"output":24.75,"cache_read":0.495,"cache_write":6.1875},"sourceProvider":"requesty"},"requesty/claude-opus-4-7":{"id":"requesty/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":5.625},"sourceProvider":"requesty"},"requesty/claude-opus-4-7@eu":{"id":"requesty/claude-opus-4-7@eu","name":"Claude Opus 4.7 (EU)","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.95,"output":24.75,"cache_read":0.495,"cache_write":6.1875},"sourceProvider":"requesty"},"requesty/claude-opus-4-8":{"id":"requesty/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":5.625},"sourceProvider":"requesty"},"requesty/claude-opus-4-8@eu":{"id":"requesty/claude-opus-4-8@eu","name":"Claude Opus 4.8 (EU)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.95,"output":24.75,"cache_read":0.495,"cache_write":6.1875},"sourceProvider":"requesty"},"requesty/claude-opus-5":{"id":"requesty/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.5,"output":22.5,"cache_read":0.45,"cache_write":5.625},"sourceProvider":"requesty"},"requesty/claude-opus-5@eu":{"id":"requesty/claude-opus-5@eu","name":"Claude Opus 5 (EU)","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":4.95,"output":24.75,"cache_read":0.495,"cache_write":6.1875},"sourceProvider":"requesty"},"requesty/claude-sonnet-4-5":{"id":"requesty/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.7,"output":13.5,"cache_read":0.27,"cache_write":3.375,"tiers":[{"input":5.4,"output":20.25,"cache_read":0.54,"cache_write":6.75,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":5.4,"output":20.25,"cache_read":0.54,"cache_write":6.75}},"sourceProvider":"requesty"},"requesty/claude-sonnet-4-5@eu":{"id":"requesty/claude-sonnet-4-5@eu","name":"Claude Sonnet 4.5 (latest) (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.97,"output":14.85,"cache_read":0.27,"cache_write":3.7125,"tiers":[{"input":5.94,"output":22.275,"cache_read":0.54,"cache_write":7.425,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":5.94,"output":22.275,"cache_read":0.54,"cache_write":7.425}},"sourceProvider":"requesty"},"requesty/claude-sonnet-4-6":{"id":"requesty/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2.7,"output":13.5,"cache_read":0.27,"cache_write":3.375},"sourceProvider":"requesty"},"requesty/claude-sonnet-4-6@eu":{"id":"requesty/claude-sonnet-4-6@eu","name":"Claude Sonnet 4.6 (EU)","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.97,"output":14.85,"cache_read":0.27,"cache_write":3.7125},"sourceProvider":"requesty"},"requesty/claude-sonnet-4@eu":{"id":"requesty/claude-sonnet-4@eu","name":"Claude Sonnet 4 (latest) (EU)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2.7,"output":13.5,"cache_read":0.27,"cache_write":3.375,"tiers":[{"input":5.4,"output":20.25,"cache_read":0.54,"cache_write":6.75,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":5.4,"output":20.25,"cache_read":0.54,"cache_write":6.75}},"sourceProvider":"requesty"},"requesty/claude-sonnet-5":{"id":"requesty/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.8,"output":9,"cache_read":0.18,"cache_write":2.25},"sourceProvider":"requesty"},"requesty/claude-sonnet-5@eu":{"id":"requesty/claude-sonnet-5@eu","name":"Claude Sonnet 5 (EU)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.98,"output":9.9,"cache_read":0.198,"cache_write":2.475},"sourceProvider":"requesty"},"requesty/deepseek-v4-flash":{"id":"requesty/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.396,"output":1.188,"cache_read":0.0126},"sourceProvider":"requesty"},"requesty/deepseek-v4-flash-0731":{"id":"requesty/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.126,"output":0.252,"cache_read":0.063},"sourceProvider":"requesty"},"requesty/deepseek-v4-flash-0731@eu":{"id":"requesty/deepseek-v4-flash-0731@eu","name":"DeepSeek V4 Flash 0731 (EU)","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.126,"output":0.252,"cache_read":0.063},"sourceProvider":"requesty"},"requesty/deepseek-v4-pro":{"id":"requesty/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.188,"output":3.564,"cache_read":0.0396},"sourceProvider":"requesty"},"requesty/deepseek-v4-pro-0813":{"id":"requesty/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.188,"output":3.564,"cache_read":0.0396},"sourceProvider":"requesty"},"requesty/deepseek-v4-pro@eu":{"id":"requesty/deepseek-v4-pro@eu","name":"DeepSeek V4 Pro (EU)","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.575,"output":3.15,"cache_read":0.396},"sourceProvider":"requesty"},"requesty/devstral-latest":{"id":"requesty/devstral-latest","name":"devstral-latest","description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.396,"output":1.98,"cache_read":0.396},"sourceProvider":"requesty"},"requesty/devstral-latest@eu":{"id":"requesty/devstral-latest@eu","name":"devstral-latest@eu","description":"An enterprise grade text model, that excels at using tools to explore codebases, editing multiple files and power software engineering agents.","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.396,"output":1.98,"cache_read":0.396},"sourceProvider":"requesty"},"requesty/fugu-ultra":{"id":"requesty/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":4.5,"output":27,"cache_read":0.45,"tiers":[{"input":9,"output":40.5,"cache_read":0.9,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":9,"output":40.5,"cache_read":0.9}},"sourceProvider":"requesty"},"requesty/gemini-2.5-flash@eu":{"id":"requesty/gemini-2.5-flash@eu","name":"Gemini 2.5 Flash (EU)","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.27,"output":2.25,"cache_read":0.0675,"cache_write":0.495},"sourceProvider":"requesty"},"requesty/gemini-3-pro-image":{"id":"requesty/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":1048576,"output":32768},"cost":{"input":1.8,"output":10.8,"cache_read":0.18,"cache_write":4.05,"tiers":[{"input":3.6,"output":16.2,"cache_read":0.18,"cache_write":4.05,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":3.6,"output":16.2,"cache_read":0.18,"cache_write":4.05}},"sourceProvider":"requesty"},"requesty/gemini-3.1-flash-image":{"id":"requesty/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.45,"output":1.8,"tiers":[{"input":0.45,"output":1.8,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.45,"output":1.8}},"sourceProvider":"requesty"},"requesty/gemini-3.1-flash-lite":{"id":"requesty/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.225,"output":1.35,"cache_read":0.0225,"cache_write":0.074997,"tiers":[{"input":0.45,"output":2.025,"cache_read":0.0225,"cache_write":0.074997,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.45,"output":2.025,"cache_read":0.0225,"cache_write":0.074997}},"sourceProvider":"requesty"},"requesty/gemini-3.1-flash-lite@eu":{"id":"requesty/gemini-3.1-flash-lite@eu","name":"Gemini 3.1 Flash Lite (EU)","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.2475,"output":1.485,"cache_read":0.02475,"cache_write":0.082497,"tiers":[{"input":0.495,"output":2.2275,"cache_read":0.02475,"cache_write":0.082497,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":0.495,"output":2.2275,"cache_read":0.02475,"cache_write":0.082497}},"sourceProvider":"requesty"},"requesty/gemini-3.1-pro-preview":{"id":"requesty/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.8,"output":10.8,"cache_read":0.18,"cache_write":4.05,"tiers":[{"input":3.6,"output":16.2,"cache_read":0.18,"cache_write":4.05,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":3.6,"output":16.2,"cache_read":0.18,"cache_write":4.05}},"sourceProvider":"requesty"},"requesty/gemini-3.5-flash":{"id":"requesty/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.35,"output":8.1,"cache_read":0.135,"cache_write":1.4247},"sourceProvider":"requesty"},"requesty/gemini-3.5-flash-lite":{"id":"requesty/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.27,"output":2.25,"cache_read":0.027},"sourceProvider":"requesty"},"requesty/gemini-3.5-flash-lite@eu":{"id":"requesty/gemini-3.5-flash-lite@eu","name":"Gemini 3.5 Flash Lite (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.297,"output":2.475,"cache_read":0.0297},"sourceProvider":"requesty"},"requesty/gemini-3.5-flash@eu":{"id":"requesty/gemini-3.5-flash@eu","name":"Gemini 3.5 Flash (EU)","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.485,"output":8.91,"cache_read":0.1485,"cache_write":1.56717},"sourceProvider":"requesty"},"requesty/gemini-3.6-flash":{"id":"requesty/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":1.35,"output":6.3,"cache_read":0.135},"sourceProvider":"requesty"},"requesty/gemini-3.7-flash":{"id":"requesty/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.6,"output":3,"cache_read":0.06},"sourceProvider":"requesty"},"requesty/gemini-3.7-flash@eu":{"id":"requesty/gemini-3.7-flash@eu","name":"Gemini 3.7 Flash (EU)","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65535},"cost":{"input":0.66,"output":3.3,"cache_read":0.066},"sourceProvider":"requesty"},"requesty/gemma-4-26b-a4b-it":{"id":"requesty/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.063,"output":0.306,"cache_read":0.063},"sourceProvider":"requesty"},"requesty/gemma-4-31b-it":{"id":"requesty/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/glm-5.1":{"id":"requesty/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"sourceProvider":"requesty"},"requesty/glm-5.1@eu":{"id":"requesty/glm-5.1@eu","name":"GLM-5.1 (EU)","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":200000},"cost":{"input":1.26,"output":3.96,"cache_read":1.26},"sourceProvider":"requesty"},"requesty/glm-5.2":{"id":"requesty/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.08,"output":3.78,"cache_read":0.234},"sourceProvider":"requesty"},"requesty/glm-5.2-fast":{"id":"requesty/glm-5.2-fast","name":"glm-5.2-fast","description":"GLM-5.2 introduces a robust 1M-token context and advanced, multi-effort coding capabilities to significantly enhance performance on long-horizon tasks. Its new IndexShare architecture and improved MTP layer simultaneously boost efficiency by reducing per-token FLOPs and increasing speculative decoding lengths. A 743B-parameter model in Zhipu AI's GLM series, designed to plan, execute, and iterate autonomously on extended, engineering-grade tasks.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-07-13","last_updated":"2026-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.89,"output":5.94,"cache_read":0.189},"sourceProvider":"requesty"},"requesty/glm-5.2@eu":{"id":"requesty/glm-5.2@eu","name":"GLM-5.2 (EU)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.08,"output":3.78,"cache_read":0.234},"sourceProvider":"requesty"},"requesty/glm-5.3":{"id":"requesty/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.26,"output":3.96,"cache_read":0.234},"sourceProvider":"requesty"},"requesty/gpt-4.1-mini@eu":{"id":"requesty/gpt-4.1-mini@eu","name":"GPT-4.1 mini (EU)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.396,"output":1.584,"cache_read":0.099},"sourceProvider":"requesty"},"requesty/gpt-4.1-nano@eu":{"id":"requesty/gpt-4.1-nano@eu","name":"GPT-4.1 nano (EU)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.099,"output":0.396,"cache_read":0.02475},"sourceProvider":"requesty"},"requesty/gpt-4.1@eu":{"id":"requesty/gpt-4.1@eu","name":"GPT-4.1 (EU)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":1.98,"output":7.92,"cache_read":0.495},"sourceProvider":"requesty"},"requesty/gpt-4o-mini@eu":{"id":"requesty/gpt-4o-mini@eu","name":"GPT-4o mini (EU)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16000},"cost":{"input":0.1485,"output":0.594,"cache_read":0.07425},"sourceProvider":"requesty"},"requesty/gpt-5-mini@eu":{"id":"requesty/gpt-5-mini@eu","name":"GPT-5 Mini (EU)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.2475,"output":1.98,"cache_read":0.02475},"sourceProvider":"requesty"},"requesty/gpt-5-nano@eu":{"id":"requesty/gpt-5-nano@eu","name":"GPT-5 Nano (EU)","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":0.0495,"output":0.396,"cache_read":0.00495},"sourceProvider":"requesty"},"requesty/gpt-5.1@eu":{"id":"requesty/gpt-5.1@eu","name":"GPT-5.1 (EU)","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.2375,"output":9.9,"cache_read":0.12375},"sourceProvider":"requesty"},"requesty/gpt-5.3-chat":{"id":"requesty/gpt-5.3-chat","name":"gpt-5.3-chat","description":"GPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful. It delivers more accurate answers with better contextualization and significantly reduces unnecessary refusals, caveats, and overly cautious phrasing that can interrupt conversational flow.","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":1.575,"output":12.6,"cache_read":0.1575},"sourceProvider":"requesty"},"requesty/gpt-5.3-codex":{"id":"requesty/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.575,"output":12.6,"cache_read":0.1575},"sourceProvider":"requesty"},"requesty/gpt-5.4":{"id":"requesty/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.475,"output":14.85,"cache_read":0.2475},"sourceProvider":"requesty"},"requesty/gpt-5.4-mini":{"id":"requesty/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.675,"output":4.05,"cache_read":0.0675},"sourceProvider":"requesty"},"requesty/gpt-5.4-nano":{"id":"requesty/gpt-5.4-nano","name":"GPT-5.4 nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.18,"output":1.125,"cache_read":0.018},"sourceProvider":"requesty"},"requesty/gpt-5.4-pro":{"id":"requesty/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":27,"output":162,"cache_read":27},"sourceProvider":"requesty"},"requesty/gpt-5.4@eu":{"id":"requesty/gpt-5.4@eu","name":"GPT-5.4 (EU)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.25,"output":13.5,"cache_read":0.225,"tiers":[{"input":4.5,"output":20.25,"cache_read":0.45,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":4.5,"output":20.25,"cache_read":0.45}},"sourceProvider":"requesty"},"requesty/gpt-5.5":{"id":"requesty/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.95,"output":29.7,"cache_read":0.495},"sourceProvider":"requesty"},"requesty/gpt-5.5-pro":{"id":"requesty/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":27,"output":162},"sourceProvider":"requesty"},"requesty/gpt-5.5@eu":{"id":"requesty/gpt-5.5@eu","name":"GPT-5.5 (EU)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.5,"output":27,"cache_read":0.45,"tiers":[{"input":9,"output":40.5,"cache_read":0.9,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":9,"output":40.5,"cache_read":0.9}},"sourceProvider":"requesty"},"requesty/gpt-5.6-luna":{"id":"requesty/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.18,"output":1.08,"cache_read":0.018,"tiers":[{"input":0.36,"output":1.62,"cache_read":0.036,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":0.36,"output":1.62,"cache_read":0.036}},"sourceProvider":"requesty"},"requesty/gpt-5.6-luna@eu":{"id":"requesty/gpt-5.6-luna@eu","name":"GPT-5.6 Luna (EU)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.198,"output":1.188,"cache_read":0.0198},"sourceProvider":"requesty"},"requesty/gpt-5.6-sol":{"id":"requesty/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":3.6,"output":18,"cache_read":0.36,"cache_write":4.5,"tiers":[{"input":7.2,"output":27,"cache_read":0.72,"cache_write":9,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":7.2,"output":27,"cache_read":0.72,"cache_write":9}},"sourceProvider":"requesty"},"requesty/gpt-5.6-sol@eu":{"id":"requesty/gpt-5.6-sol@eu","name":"GPT-5.6 Sol (EU)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4.95,"output":29.7,"cache_read":0.495},"sourceProvider":"requesty"},"requesty/gpt-5.6-terra":{"id":"requesty/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1.8,"output":10.8,"cache_read":0.18,"tiers":[{"input":3.6,"output":16.2,"cache_read":0.36,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":3.6,"output":16.2,"cache_read":0.36}},"sourceProvider":"requesty"},"requesty/gpt-5.6-terra@eu":{"id":"requesty/gpt-5.6-terra@eu","name":"GPT-5.6 Terra (EU)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1.98,"output":11.88,"cache_read":0.198},"sourceProvider":"requesty"},"requesty/gpt-5@eu":{"id":"requesty/gpt-5@eu","name":"GPT-5 (EU)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.2375,"output":9.9,"cache_read":0.12375},"sourceProvider":"requesty"},"requesty/grok-4.2-beta":{"id":"requesty/grok-4.2-beta","name":"grok-4.2-beta","description":"Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-19","last_updated":"2026-03-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.8,"output":5.4,"cache_read":0.18,"cache_write":1.8,"tiers":[{"input":3.6,"output":10.8,"cache_read":0.36,"cache_write":3.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":3.6,"output":10.8,"cache_read":0.36,"cache_write":3.6}},"sourceProvider":"requesty"},"requesty/grok-4.3":{"id":"requesty/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.125,"output":2.25,"cache_read":0.18,"cache_write":1.125,"tiers":[{"input":2.25,"output":4.5,"cache_read":0.36,"cache_write":2.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.25,"output":4.5,"cache_read":0.36,"cache_write":2.25}},"sourceProvider":"requesty"},"requesty/grok-4.5":{"id":"requesty/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":1.8,"output":5.4,"cache_read":0.45,"cache_write":1.8,"tiers":[{"input":3.6,"output":10.8,"cache_read":0.9,"cache_write":3.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":3.6,"output":10.8,"cache_read":0.9,"cache_write":3.6}},"sourceProvider":"requesty"},"requesty/grok-4.6":{"id":"requesty/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":1.8,"output":5.4,"cache_read":0.45,"cache_write":1.8,"tiers":[{"input":3.6,"output":10.8,"cache_read":0.9,"cache_write":3.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":3.6,"output":10.8,"cache_read":0.9,"cache_write":3.6}},"sourceProvider":"requesty"},"requesty/grok-build-0.1":{"id":"requesty/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.9,"output":1.8,"cache_read":0.09},"sourceProvider":"requesty"},"requesty/hy3":{"id":"requesty/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.126,"output":0.522,"cache_read":0.0315},"sourceProvider":"requesty"},"requesty/inkling":{"id":"requesty/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":32768},"cost":{"input":1.683,"output":4.212,"cache_read":0.3366},"sourceProvider":"requesty"},"requesty/inkling-256k":{"id":"requesty/inkling-256k","name":"inkling-256k","description":"Inkling 256K is the extended context variant of Inkling, a large MoE hybrid reasoning model from Thinking Machines with audio and vision input support and a 256K context window.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":1.496,"output":3.744,"cache_read":0.2992},"sourceProvider":"requesty"},"requesty/kat-coder-pro":{"id":"requesty/kat-coder-pro","name":"kat-coder-pro","description":"KAT-Coder-Pro V2 by KwaiKAT is a non-reasoning model optimized for agentic coding. It delivers strong performance on reasoning-style tasks while requiring significantly fewer output tokens than peer models. With the 1210 release, it achieved a score of 64 on the Artificial Analysis Intelligence Index, placing it in the global Top 10 and ranking first among all non-reasoning models.","family":"kat-coder","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.27,"output":1.08},"sourceProvider":"requesty"},"requesty/kimi-k2.6":{"id":"requesty/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.855,"output":3.6,"cache_read":0.144},"sourceProvider":"requesty"},"requesty/kimi-k2.6@eu":{"id":"requesty/kimi-k2.6@eu","name":"Kimi K2.6 (EU)","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":128000},"cost":{"input":0.855,"output":3.6,"cache_read":0.855},"sourceProvider":"requesty"},"requesty/kimi-k2.7-code":{"id":"requesty/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.855,"output":3.6,"cache_read":0.171},"sourceProvider":"requesty"},"requesty/kimi-k2.7-code@eu":{"id":"requesty/kimi-k2.7-code@eu","name":"Kimi K2.7 Code (EU)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.125,"output":4.05,"cache_read":0.279},"sourceProvider":"requesty"},"requesty/kimi-k3":{"id":"requesty/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.025,"output":10.125,"cache_read":0.2025},"sourceProvider":"requesty"},"requesty/kimi-k3@eu":{"id":"requesty/kimi-k3@eu","name":"Kimi K3 (EU)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":262144},"cost":{"input":2.025,"output":10.125,"cache_read":0.2025},"sourceProvider":"requesty"},"requesty/laguna-m.1":{"id":"requesty/laguna-m.1","name":"Laguna M.1","description":"Poolside's open-weight model for agentic coding and long-horizon work","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/laguna-xs.2":{"id":"requesty/laguna-xs.2","name":"Laguna XS.2","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/leanstral-1-5":{"id":"requesty/leanstral-1-5","name":"leanstral-1-5","description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/leanstral-1-5@eu":{"id":"requesty/leanstral-1-5@eu","name":"leanstral-1-5@eu","description":"Leanstral 1.5 is an updated Lean 4 formal proof engineering model from Mistral AI, optimized for automated theorem proving and autoformalization. It has 119B total parameters with 6.5B active and supports a 256K token context window. It supports native function calling and structured output.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/ling-2.6-1t":{"id":"requesty/ling-2.6-1t","name":"ling-2.6-1t","description":"Inclusion AI ling-2.6-1t","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.27,"output":2.25},"sourceProvider":"requesty"},"requesty/ling-2.6-flash":{"id":"requesty/ling-2.6-flash","name":"ling-2.6-flash","description":"Inclusion AI ling-2.6-flash","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.09,"output":0.27},"sourceProvider":"requesty"},"requesty/ling-3.0-tiny":{"id":"requesty/ling-3.0-tiny","name":"ling-3.0-tiny","description":"Ling-3.0-tiny is an efficient 7.9B parameter MoE model from inclusionAI with only 1.3B active parameters per token. Built for responsive agents, reliable instruction following and multi turn conversation, with a 256K context window, native function calling, prompt caching and switchable Thinking and Instant modes.","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/mimo-v2.5":{"id":"requesty/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.126,"output":0.252,"cache_read":0.00252},"sourceProvider":"requesty"},"requesty/mimo-v2.5-pro":{"id":"requesty/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.3915,"output":0.783,"cache_read":0.00324},"sourceProvider":"requesty"},"requesty/minimax-m2.7":{"id":"requesty/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.27,"output":1.08,"cache_read":0.054,"cache_write":1.08},"sourceProvider":"requesty"},"requesty/minimax-m2.7-highspeed":{"id":"requesty/minimax-m2.7-highspeed","name":"MiniMax-M2.7-highspeed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.54,"output":2.16,"cache_read":0.054,"cache_write":1.08},"sourceProvider":"requesty"},"requesty/minimax-m3":{"id":"requesty/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.24,"output":0.96,"cache_read":0.048},"sourceProvider":"requesty"},"requesty/minimax-m3@eu":{"id":"requesty/minimax-m3@eu","name":"MiniMax-M3 (EU)","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.36,"output":1.8,"cache_read":0.09},"sourceProvider":"requesty"},"requesty/mistral-medium-3-5":{"id":"requesty/mistral-medium-3-5","name":"mistral-medium-3-5","description":"Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.485,"output":7.425,"cache_read":1.485},"sourceProvider":"requesty"},"requesty/mistral-medium-3-5@eu":{"id":"requesty/mistral-medium-3-5@eu","name":"mistral-medium-3-5@eu","description":"Mistral Medium 3.5 is a dense 128B instruction following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi step reasoning. It is particularly strong at reliable multi tool calling and long horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self hostable on as few as four GPUs and available under open weights.","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":1.485,"output":7.425,"cache_read":1.485},"sourceProvider":"requesty"},"requesty/mistral-medium-latest":{"id":"requesty/mistral-medium-latest","name":"Mistral Medium (latest)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.396,"output":1.98,"cache_read":0.396},"sourceProvider":"requesty"},"requesty/mistral-medium-latest@eu":{"id":"requesty/mistral-medium-latest@eu","name":"Mistral Medium (latest) (EU)","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.396,"output":1.98,"cache_read":0.396},"sourceProvider":"requesty"},"requesty/mistral-small-2603":{"id":"requesty/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1485,"output":0.594,"cache_read":0.1485},"sourceProvider":"requesty"},"requesty/mistral-small-2603@eu":{"id":"requesty/mistral-small-2603@eu","name":"Mistral Small 4 (EU)","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.1485,"output":0.594,"cache_read":0.1485},"sourceProvider":"requesty"},"requesty/muse-glimmer-30b":{"id":"requesty/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":20480},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-3-nano-omni":{"id":"requesty/nemotron-3-nano-omni","name":"nemotron-3-nano-omni","description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.054,"output":0.216,"cache_read":0.054},"sourceProvider":"requesty"},"requesty/nemotron-3-nano-omni-30b-a3b-reasoning":{"id":"requesty/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":20480},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-3-nano-omni@eu":{"id":"requesty/nemotron-3-nano-omni@eu","name":"nemotron-3-nano-omni@eu","description":"The most open, efficient, and accurate omni modal reasoning model for agentic AI.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":300000},"cost":{"input":0.054,"output":0.216,"cache_read":0.054},"sourceProvider":"requesty"},"requesty/nemotron-3-super-120b-a12b":{"id":"requesty/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-3-ultra-550b-a55b":{"id":"requesty/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-3-ultra-nvfp4":{"id":"requesty/nemotron-3-ultra-nvfp4","name":"nemotron-3-ultra-nvfp4","description":"Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.54,"output":2.16,"cache_read":0.108},"sourceProvider":"requesty"},"requesty/nemotron-3.5-content-safety":{"id":"requesty/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-3.5-lightning-30b-a3b":{"id":"requesty/nemotron-3.5-lightning-30b-a3b","name":"nemotron-3.5-lightning-30b-a3b","description":"NVIDIA Nemotron 3.5 Lightning 30B-A3B is a hybrid Mamba-2 + MoE + Attention model with 30B total and 3B active parameters, pre-trained on over 20T tokens with an NVFP4 recipe and Multi-Token Prediction for fast generation. Up to 1M token context for long-running autonomous agents, sub-agent workhorse deployments, and agentic workflows. Supports reasoning and tool calling. English and coding languages plus Spanish, French, German, Italian, and Japanese. Open weights under the OpenMDW License Agreement v1.1. Part of the NVIDIA Nemotron family.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"requesty"},"requesty/nemotron-lightning-3.5-30b-a3b":{"id":"requesty/nemotron-lightning-3.5-30b-a3b","name":"nemotron-lightning-3.5-30b-a3b","description":"Nemotron-Lightning-3.5-30B-A3B is a 30B-parameter Mixture-of-Experts language model (3B active) from NVIDIA's Nemotron-H family, built on a hybrid Mamba-Transformer architecture for efficient long-context inference. Like other models in the family, it responds to queries by first generating a reasoning trace and then concluding with a final response, with reasoning behavior configurable through a flag in the chat template. It includes a multi-token prediction (MTP) speculative decoding head for low-latency serving.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-08-15","last_updated":"2026-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.045,"output":0.18,"cache_read":0.009},"sourceProvider":"requesty"},"requesty/nvidia-nemotron-3-super-120b-a12b":{"id":"requesty/nvidia-nemotron-3-super-120b-a12b","name":"nvidia-nemotron-3-super-120b-a12b","description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.09,"output":0.45},"sourceProvider":"requesty"},"requesty/nvidia-nemotron-3-ultra":{"id":"requesty/nvidia-nemotron-3-ultra","name":"nvidia-nemotron-3-ultra","description":"NVIDIA Nemotron 3 Ultra is NVIDIA's strongest open-weights reasoning model, positioned near GPT-5.4 Mini (xhigh) and ahead of DeepSeek V4-Flash and Qwen3.5-397B-A17B.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":false,"structured_output":false,"release_date":"2026-06-23","last_updated":"2026-06-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"cost":{"input":0.45,"output":2.25},"sourceProvider":"requesty"},"requesty/o4-mini@eu":{"id":"requesty/o4-mini@eu","name":"o4-mini (EU)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":1.089,"output":4.356,"cache_read":0.27225},"sourceProvider":"requesty"},"requesty/qwen3.5-27b":{"id":"requesty/qwen3.5-27b","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.234,"output":2.34},"sourceProvider":"requesty"},"requesty/qwen3.5-2b":{"id":"requesty/qwen3.5-2b","name":"qwen3.5-2b","description":"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and efficient multilingual deployments.","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.018,"output":0.09},"sourceProvider":"requesty"},"requesty/qwen3.5-35b-a3b":{"id":"requesty/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.126,"output":0.9,"cache_read":0.045},"sourceProvider":"requesty"},"requesty/qwen3.6-plus":{"id":"requesty/qwen3.6-plus","name":"Qwen3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.45,"output":2.7,"cache_read":0.045,"cache_write":0.5625},"sourceProvider":"requesty"},"requesty/qwen3.7-max":{"id":"requesty/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":2.25,"output":6.75,"cache_read":0.225,"cache_write":2.8125},"sourceProvider":"requesty"},"requesty/qwen3.7-plus":{"id":"requesty/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0.28,"output":1.12,"cache_read":0.028,"cache_write":0.35},"sourceProvider":"requesty"},"requesty/qwen3.8-2.4T-A95B":{"id":"requesty/qwen3.8-2.4T-A95B","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.8,"output":5.4,"cache_read":0.18},"sourceProvider":"requesty"},"requesty/qwen3.8-max":{"id":"requesty/qwen3.8-max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":1.8,"output":5.4,"cache_read":0.225,"cache_write":2.25},"sourceProvider":"requesty"},"requesty/ring-2.6-1t":{"id":"requesty/ring-2.6-1t","name":"ring-2.6-1t","description":"Inclusion AI ring-2.6-1t","family":"ring","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-08","last_updated":"2026-05-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.27,"output":2.25},"sourceProvider":"requesty"},"requesty/seed-1.8":{"id":"requesty/seed-1.8","name":"seed-1.8","description":"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-05-27","last_updated":"2026-05-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.225,"output":1.8,"cache_read":0.045},"sourceProvider":"requesty"},"requesty/seed-2.0-code":{"id":"requesty/seed-2.0-code","name":"Seed 2.0 Code","description":"ByteDance Seed coding model for multimodal software engineering and long-running agents","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.45,"output":2.7,"cache_read":0.09},"sourceProvider":"requesty"},"requesty/seed-2.0-mini":{"id":"requesty/seed-2.0-mini","name":"Seed 2.0 Mini","description":"Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.09,"output":0.36,"cache_read":0.018},"sourceProvider":"requesty"},"requesty/seed-2.0-pro":{"id":"requesty/seed-2.0-pro","name":"Seed 2.0 Pro","description":"Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.45,"output":2.7,"cache_read":0.09},"sourceProvider":"requesty"},"requesty/step-3.7-flash":{"id":"requesty/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":256000},"cost":{"input":0.18,"output":1.035,"cache_read":0.036},"sourceProvider":"requesty"},"requesty/thinkingcap-qwen3.6-27b":{"id":"requesty/thinkingcap-qwen3.6-27b","name":"thinkingcap-qwen3.6-27b","description":"ThinkingCap-Qwen3.6-27B is a reasoning tuned model from BottlecapAI built on Qwen3.6 27B. It supports extended thinking with tool calling and a 256K context window. Served via Sference.","family":"qwen3.6","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-07-13","last_updated":"2026-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.36,"output":2.7,"cache_read":0.234},"sourceProvider":"requesty"},"requesty/thinkingcap-qwen3.6-27b@eu":{"id":"requesty/thinkingcap-qwen3.6-27b@eu","name":"thinkingcap-qwen3.6-27b@eu","description":"ThinkingCap-Qwen3.6-27B is a reasoning tuned model from BottlecapAI built on Qwen3.6 27B. It supports extended thinking with tool calling and a 256K context window. Served via Sference.","family":"qwen3.6","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","max"]},{"type":"budget_tokens"}],"tool_call":true,"structured_output":false,"release_date":"2026-07-13","last_updated":"2026-07-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":0.36,"output":2.7,"cache_read":0.234},"sourceProvider":"requesty"},"routing-run/claude-opus-4-8":{"id":"routing-run/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":5,"output":25},"sourceProvider":"routing-run"},"routing-run/claude-sonnet-4-6":{"id":"routing-run/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15},"sourceProvider":"routing-run"},"routing-run/deepseek-v4-flash":{"id":"routing-run/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.112,"output":0.224},"sourceProvider":"routing-run"},"routing-run/deepseek-v4-pro":{"id":"routing-run/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":64000},"cost":{"input":0.348,"output":0.696},"sourceProvider":"routing-run"},"routing-run/glm-5.2":{"id":"routing-run/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.8,"output":2.4},"sourceProvider":"routing-run"},"routing-run/glm-5.2-nitro":{"id":"routing-run/glm-5.2-nitro","name":"GLM 5.2 Nitro","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.8,"output":2.4},"sourceProvider":"routing-run"},"routing-run/gpt-5.6-luna":{"id":"routing-run/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":0.7,"output":4.2},"sourceProvider":"routing-run"},"routing-run/gpt-5.6-sol":{"id":"routing-run/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15},"sourceProvider":"routing-run"},"routing-run/gpt-5.6-terra":{"id":"routing-run/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":1.5,"output":9},"sourceProvider":"routing-run"},"routing-run/kimi-k2.6":{"id":"routing-run/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"sourceProvider":"routing-run"},"routing-run/kimi-k2.6-nitro":{"id":"routing-run/kimi-k2.6-nitro","name":"Kimi K2.6 Nitro","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"sourceProvider":"routing-run"},"routing-run/kimi-k2.7-code":{"id":"routing-run/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"sourceProvider":"routing-run"},"routing-run/kimi-k2.7-code-nitro":{"id":"routing-run/kimi-k2.7-code-nitro","name":"Kimi K2.7 Code Nitro","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32000},"cost":{"input":0.275,"output":1.1},"sourceProvider":"routing-run"},"routing-run/nemotron-3-ultra":{"id":"routing-run/nemotron-3-ultra","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32000},"cost":{"input":0.1,"output":0.1},"sourceProvider":"routing-run"},"routing-run/qwen3.5-9b":{"id":"routing-run/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32000},"cost":{"input":0.16,"output":0.48},"sourceProvider":"routing-run"},"runinfra/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.13,"output":0.27,"cache_read":0.01},"sourceProvider":"runinfra"},"runinfra/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":32768},"cost":{"input":0.6,"output":1.9,"cache_read":0.03},"sourceProvider":"runinfra"},"runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4":{"id":"Inferact/Qwen3.8-2.4T-A95B-NVFP4","name":"Qwen3.8 2.4T A95B (NVFP4)","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"runinfra"},"runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16":{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16","name":"Nemotron 3.5 Lightning 30B A3B","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.05,"output":0.15},"sourceProvider":"runinfra"},"runinfra/Qwen/Qwen3.8-27B":{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"runinfra"},"sakana/fugu":{"id":"sakana/fugu","name":"Fugu","description":"Multi-agent model for routing expert agents across complex analytical tasks","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"sourceProvider":"sakana"},"sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"sakana"},"sakana/fugu-ultra-20260615":{"id":"sakana/fugu-ultra-20260615","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"provider":{"shape":"responses"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"sakana"},"sakana/sakana-namazu":{"id":"sakana/sakana-namazu","name":"Sakana Namazu","description":"Japanese-specialized reasoning model based on Kimi K2.6 and tuned for Japanese language, culture, and business workflows","family":"sakana-namazu","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.15},"sourceProvider":"sakana"},"salad-cloud/qwen3.6-35b-a3b":{"id":"salad-cloud/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Qwen MoE for agentic tasks, complex reasoning, code generation, and instruction following","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"input":262144,"output":262144},"cost":{"input":0.09,"output":0.6},"sourceProvider":"salad-cloud"},"sap-ai-core/amazon--nova-lite":{"id":"sap-ai-core/amazon--nova-lite","name":"amazon--nova-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.3,"output":2.37},"sourceProvider":"sap-ai-core"},"sap-ai-core/amazon--nova-micro":{"id":"sap-ai-core/amazon--nova-micro","name":"amazon--nova-micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.03,"output":0.1},"sourceProvider":"sap-ai-core"},"sap-ai-core/amazon--nova-pro":{"id":"sap-ai-core/amazon--nova-pro","name":"amazon--nova-pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.56,"output":2.13},"sourceProvider":"sap-ai-core"},"sap-ai-core/amazon--titan-embed-text":{"id":"sap-ai-core/amazon--titan-embed-text","name":"amazon--titan-embed-text","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-04-30","last_updated":"2024-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"cost":{"input":0.14,"output":0},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-3-haiku":{"id":"sap-ai-core/anthropic--claude-3-haiku","name":"anthropic--claude-3-haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-3-opus":{"id":"sap-ai-core/anthropic--claude-3-opus","name":"anthropic--claude-3-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-02-29","last_updated":"2024-02-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-3-sonnet":{"id":"sap-ai-core/anthropic--claude-3-sonnet","name":"anthropic--claude-3-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-04","last_updated":"2024-03-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-3.5-sonnet":{"id":"sap-ai-core/anthropic--claude-3.5-sonnet","name":"anthropic--claude-3.5-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04-30","release_date":"2024-10-22","last_updated":"2024-10-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-3.7-sonnet":{"id":"sap-ai-core/anthropic--claude-3.7-sonnet","name":"anthropic--claude-3.7-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2024-10-31","release_date":"2025-02-24","last_updated":"2025-02-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4-opus":{"id":"sap-ai-core/anthropic--claude-4-opus","name":"anthropic--claude-4-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"status":"deprecated","cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4-sonnet":{"id":"sap-ai-core/anthropic--claude-4-sonnet","name":"anthropic--claude-4-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.5-haiku":{"id":"sap-ai-core/anthropic--claude-4.5-haiku","name":"anthropic--claude-4.5-haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.5-opus":{"id":"sap-ai-core/anthropic--claude-4.5-opus","name":"anthropic--claude-4.5-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.5-sonnet":{"id":"sap-ai-core/anthropic--claude-4.5-sonnet","name":"anthropic--claude-4.5-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.6-opus":{"id":"sap-ai-core/anthropic--claude-4.6-opus","name":"anthropic--claude-4.6-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.6-sonnet":{"id":"sap-ai-core/anthropic--claude-4.6-sonnet","name":"anthropic--claude-4.6-sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.7-opus":{"id":"sap-ai-core/anthropic--claude-4.7-opus","name":"anthropic--claude-4.7-opus","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/anthropic--claude-4.8-opus":{"id":"sap-ai-core/anthropic--claude-4.8-opus","name":"anthropic--claude-4.8-opus","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/cohere--command-a-reasoning":{"id":"sap-ai-core/cohere--command-a-reasoning","name":"cohere--command-a-reasoning","description":"Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows","family":"command-a","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high"]},{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2024-06-01","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.63,"output":5.05},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-2.5-flash":{"id":"sap-ai-core/gemini-2.5-flash","name":"gemini-2.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-04-17","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-2.5-flash-lite":{"id":"sap-ai-core/gemini-2.5-flash-lite","name":"gemini-2.5-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01,"input_audio":0.3},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-2.5-pro":{"id":"sap-ai-core/gemini-2.5-pro","name":"gemini-2.5-pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-03-25","last_updated":"2025-06-05","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-3.1-flash-lite":{"id":"sap-ai-core/gemini-3.1-flash-lite","name":"gemini-3.1-flash-lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"input_audio":0.5},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-3.5-flash":{"id":"sap-ai-core/gemini-3.5-flash","name":"gemini-3.5-flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15,"input_audio":1.5},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-embedding":{"id":"sap-ai-core/gemini-embedding","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":2048,"output":1},"sourceProvider":"sap-ai-core"},"sap-ai-core/gemini-embedding-2":{"id":"sap-ai-core/gemini-embedding-2","name":"Gemini Embedding 2","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","family":"gemini","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":3072},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-4.1":{"id":"sap-ai-core/gpt-4.1","name":"gpt-4.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.32},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-4.1-mini":{"id":"sap-ai-core/gpt-4.1-mini","name":"gpt-4.1-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-4.1-nano":{"id":"sap-ai-core/gpt-4.1-nano","name":"gpt-4.1-nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.08,"output":0.26},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5":{"id":"sap-ai-core/gpt-5","name":"gpt-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5-mini":{"id":"sap-ai-core/gpt-5-mini","name":"gpt-5-mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5-nano":{"id":"sap-ai-core/gpt-5-nano","name":"gpt-5-nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.2":{"id":"sap-ai-core/gpt-5.2","name":"gpt-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":9.44,"cache_read":0.12},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.4":{"id":"sap-ai-core/gpt-5.4","name":"gpt-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.5":{"id":"sap-ai-core/gpt-5.5","name":"gpt-5.5","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.6-luna":{"id":"sap-ai-core/gpt-5.6-luna","name":"gpt-5.6-luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"tiers":[{"input":2,"output":9,"cache_read":0.2,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2}},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.6-sol":{"id":"sap-ai-core/gpt-5.6-sol","name":"gpt-5.6-sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"sap-ai-core"},"sap-ai-core/gpt-5.6-terra":{"id":"sap-ai-core/gpt-5.6-terra","name":"gpt-5.6-terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5}},"sourceProvider":"sap-ai-core"},"sap-ai-core/mistralai--mistral-medium":{"id":"sap-ai-core/mistralai--mistral-medium","name":"Mistral Medium 3.5","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"sap-ai-core"},"sap-ai-core/mistralai--mistral-medium-instruct":{"id":"sap-ai-core/mistralai--mistral-medium-instruct","name":"mistralai--mistral-medium-instruct","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.36,"output":1.22},"sourceProvider":"sap-ai-core"},"sap-ai-core/mistralai--mistral-small":{"id":"sap-ai-core/mistralai--mistral-small","name":"mistralai--mistral-small","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"sap-ai-core"},"sap-ai-core/nvidia--llama-3.2-nv-embedqa-1b":{"id":"sap-ai-core/nvidia--llama-3.2-nv-embedqa-1b","name":"nvidia--llama-3.2-nv-embedqa-1b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-09-25","last_updated":"2024-09-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":4096},"cost":{"input":0.07,"output":0},"sourceProvider":"sap-ai-core"},"sap-ai-core/sap-abap-1":{"id":"sap-ai-core/sap-abap-1","name":"sap-abap-1","description":"SAP-hosted model for ABAP code generation and enterprise development tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-11-26","last_updated":"2025-11-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.48,"output":1.7},"sourceProvider":"sap-ai-core"},"sap-ai-core/sonar":{"id":"sap-ai-core/sonar","name":"sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"cost":{"input":1,"output":1},"sourceProvider":"sap-ai-core"},"sap-ai-core/sonar-deep-research":{"id":"sap-ai-core/sonar-deep-research","name":"sonar-deep-research","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar-deep-research","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":false,"knowledge":"2025-01","release_date":"2025-02-01","last_updated":"2025-09-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":2,"output":8,"reasoning":3},"sourceProvider":"sap-ai-core"},"sap-ai-core/sonar-pro":{"id":"sap-ai-core/sonar-pro","name":"sonar-pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-09-01","release_date":"2024-01-01","last_updated":"2025-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":3,"output":15},"sourceProvider":"sap-ai-core"},"sap-ai-core/text-embedding-3-large":{"id":"sap-ai-core/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.09,"output":0},"sourceProvider":"sap-ai-core"},"sap-ai-core/text-embedding-3-small":{"id":"sap-ai-core/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":1536},"cost":{"input":0.02,"output":0},"sourceProvider":"sap-ai-core"},"sarvam/sarvam-105b":{"id":"sarvam/sarvam-105b","name":"Sarvam-105B","description":"Flagship Indian-language reasoning model for enterprise multilingual applications","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":[null,"low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-18","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"sourceProvider":"sarvam"},"sarvam/sarvam-30b":{"id":"sarvam/sarvam-30b","name":"Sarvam-30B","description":"Efficient Indian-language reasoning model for chat, coding, and multilingual work","family":"sarvam","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":[null,"low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-18","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"sourceProvider":"sarvam"},"scaleway/bge-multilingual-gemma2":{"id":"scaleway/bge-multilingual-gemma2","name":"BGE Multilingual Gemma2","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-07-26","last_updated":"2025-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8191,"output":3072},"cost":{"input":0.1,"output":0},"sourceProvider":"scaleway"},"scaleway/deepseek-v4-flash-0731":{"id":"scaleway/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"beta","cost":{"input":0.468,"output":0.936,"reasoning":0.936,"cache_read":0.0936},"sourceProvider":"scaleway"},"scaleway/gemma-4-26b-a4b-it":{"id":"scaleway/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-01","last_updated":"2026-05-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"status":"beta","cost":{"input":0.25,"output":0.5},"sourceProvider":"scaleway"},"scaleway/glm-5.2":{"id":"scaleway/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":1.8,"output":5.5},"sourceProvider":"scaleway"},"scaleway/gpt-oss-120b":{"id":"scaleway/gpt-oss-120b","name":"GPT-OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2024-01-01","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"scaleway"},"scaleway/llama-3.3-70b-instruct":{"id":"scaleway/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":100000,"output":16384},"cost":{"input":0.9,"output":0.9},"sourceProvider":"scaleway"},"scaleway/mistral-medium-3.5-128b":{"id":"scaleway/mistral-medium-3.5-128b","name":"Mistral Medium 3.5 128B","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","family":"mistral-medium","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":1.5,"output":7.5},"sourceProvider":"scaleway"},"scaleway/mistral-small-3.2-24b-instruct-2506":{"id":"scaleway/mistral-small-3.2-24b-instruct-2506","name":"Mistral Small 3.2 24B Instruct (2506)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-06-20","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.15,"output":0.35},"sourceProvider":"scaleway"},"scaleway/pixtral-12b-2409":{"id":"scaleway/pixtral-12b-2409","name":"Pixtral 12B 2409","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-25","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.2,"output":0.2},"sourceProvider":"scaleway"},"scaleway/qwen3-235b-a22b-instruct-2507":{"id":"scaleway/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-01","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":260000,"output":16384},"cost":{"input":0.75,"output":2.25,"reasoning":8.4},"sourceProvider":"scaleway"},"scaleway/qwen3-coder-30b-a3b-instruct":{"id":"scaleway/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.2,"output":0.8},"sourceProvider":"scaleway"},"scaleway/qwen3-embedding-8b":{"id":"scaleway/qwen3-embedding-8b","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2025-06-05","last_updated":"2026-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.1,"output":0},"sourceProvider":"scaleway"},"scaleway/qwen3.5-397b-a17b":{"id":"scaleway/qwen3.5-397b-a17b","name":"Qwen3.5 397B A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.6,"output":3.6},"sourceProvider":"scaleway"},"scaleway/qwen3.6-35b-a3b":{"id":"scaleway/qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-05-01","last_updated":"2026-05-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"status":"beta","cost":{"input":0.25,"output":1.5},"sourceProvider":"scaleway"},"scaleway/whisper-large-v3":{"id":"scaleway/whisper-large-v3","name":"Whisper Large v3","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"knowledge":"2023-09","release_date":"2023-09-01","last_updated":"2026-03-17","modalities":{"input":["audio"],"output":["text"]},"open_weights":true,"limit":{"context":0,"output":8192},"cost":{"input":0.003,"output":0},"sourceProvider":"scaleway"},"scnet-token-plan/DeepSeek-V3.2":{"id":"scnet-token-plan/DeepSeek-V3.2","name":"DeepSeek V3.2","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/DeepSeek-V4-Flash":{"id":"scnet-token-plan/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/DeepSeek-V4-Flash-0731":{"id":"scnet-token-plan/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/DeepSeek-V4-Pro":{"id":"scnet-token-plan/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/GLM-5":{"id":"scnet-token-plan/GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/GLM-5.1":{"id":"scnet-token-plan/GLM-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/GLM-5.2":{"id":"scnet-token-plan/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/Kimi-K2.5":{"id":"scnet-token-plan/Kimi-K2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/Kimi-K2.6":{"id":"scnet-token-plan/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/Kimi-K2.7-Code":{"id":"scnet-token-plan/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/Kimi-K3":{"id":"scnet-token-plan/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/MiMo-V2.5-Pro":{"id":"scnet-token-plan/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/MiniMax-M2.5":{"id":"scnet-token-plan/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/MiniMax-M2.7":{"id":"scnet-token-plan/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/MiniMax-M3":{"id":"scnet-token-plan/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scnet-token-plan/Qwen3.8-Max":{"id":"scnet-token-plan/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"scnet-token-plan"},"scx-ai/GLM-5.2":{"id":"scx-ai/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.55,"output":1.784,"cache_read":0.111},"sourceProvider":"scx-ai"},"scx-ai/gpt-oss-120b":{"id":"scx-ai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.17,"output":0.55},"sourceProvider":"scx-ai"},"scx-ai/MiniMax-M2.7":{"id":"scx-ai/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.48,"output":1.79,"cache_read":0.05},"sourceProvider":"scx-ai"},"scx-ai/Qwen3.8-Max":{"id":"scx-ai/Qwen3.8-Max","name":"Qwen3.8 Max","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":983616,"output":131072},"cost":{"input":1.815,"output":5.4461,"cache_read":0.17,"cache_write":2.5},"sourceProvider":"scx-ai"},"siliconflow-cn/baidu/ERNIE-4.5-300B-A47B":{"id":"baidu/ERNIE-4.5-300B-A47B","name":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ernie","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-02","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.28,"output":1.1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/ByteDance-Seed/Seed-OSS-36B-Instruct":{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.21,"output":0.57},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-OCR":{"id":"deepseek-ai/DeepSeek-OCR","name":"deepseek-ai/DeepSeek-OCR","description":"OCR model for extracting structured text from documents and screenshots","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-R1":{"id":"deepseek-ai/DeepSeek-R1","name":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.5,"output":2.18},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.25,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-V3.1-Terminus":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.42},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.003},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"deepseek-ai/DeepSeek-V4-Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":393000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/inclusionAI/Ling-flash-2.0":{"id":"inclusionAI/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/PaddlePaddle/PaddleOCR-VL-1.5":{"id":"PaddlePaddle/PaddleOCR-VL-1.5","name":"PaddlePaddle/PaddleOCR-VL-1.5","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-29","last_updated":"2026-01-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":16384,"output":16384},"cost":{"input":0,"output":0},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/deepseek-ai/DeepSeek-R1":{"id":"Pro/deepseek-ai/DeepSeek-R1","name":"Pro/deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.5,"output":2.18},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3":{"id":"Pro/deepseek-ai/DeepSeek-V3","name":"Pro/deepseek-ai/DeepSeek-V3","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.25,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.1-Terminus":{"id":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","name":"Pro/deepseek-ai/DeepSeek-V3.1-Terminus","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/deepseek-ai/DeepSeek-V3.2":{"id":"Pro/deepseek-ai/DeepSeek-V3.2","name":"Pro/deepseek-ai/DeepSeek-V3.2","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.42},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/MiniMaxAI/MiniMax-M2.5":{"id":"Pro/MiniMaxAI/MiniMax-M2.5","name":"Pro/MiniMaxAI/MiniMax-M2.5","description":"Frontier MiniMax model for engineering, office tasks, and agentic reasoning","family":"minimax","attachment":false,"reasoning":false,"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":192000,"output":131000},"cost":{"input":0.3,"output":1.22},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/moonshotai/Kimi-K2.5":{"id":"Pro/moonshotai/Kimi-K2.5","name":"Pro/moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/moonshotai/Kimi-K2.6":{"id":"Pro/moonshotai/Kimi-K2.6","name":"Pro/moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/zai-org/GLM-5":{"id":"Pro/zai-org/GLM-5","name":"Pro/zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":205000},"cost":{"input":1,"output":3.2},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Pro/zai-org/GLM-5.1":{"id":"Pro/zai-org/GLM-5.1","name":"Pro/zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":205000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen2.5-72B-Instruct":{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.59,"output":0.59},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen2.5-7B-Instruct":{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.05,"output":0.05},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-14B":{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.13,"output":0.6},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.09,"output":0.3},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-8B":{"id":"Qwen/Qwen3-8B","name":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.06,"output":0.06},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-Coder-30B-A3B-Instruct":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-01","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-Coder-480B-A35B-Instruct":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.25,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Instruct":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.3,"output":1.5},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-235B-A22B-Thinking":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.45,"output":3.5},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Instruct":{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.29,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-30B-A3B-Thinking":{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.29,"output":1},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-32B-Instruct":{"id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.2,"output":0.6},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-32B-Thinking":{"id":"Qwen/Qwen3-VL-32B-Thinking","name":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.2,"output":1.5},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3-VL-8B-Instruct":{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.18,"output":0.68},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-122B-A10B":{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen/Qwen3.5-122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":2.32},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-27B":{"id":"Qwen/Qwen3.5-27B","name":"Qwen/Qwen3.5-27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.26,"output":2.09},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-35B-A3B":{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen/Qwen3.5-35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.23,"output":1.86},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen/Qwen3.5-397B-A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.29,"output":1.74},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-4B":{"id":"Qwen/Qwen3.5-4B","name":"Qwen/Qwen3.5-4B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.22,"output":1.74},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen/Qwen3.6-35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.23,"output":1.86},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/stepfun-ai/Step-3.5-Flash":{"id":"stepfun-ai/Step-3.5-Flash","name":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/tencent/Hunyuan-A13B-Instruct":{"id":"tencent/Hunyuan-A13B-Instruct","name":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/zai-org/GLM-4.5-Air":{"id":"zai-org/GLM-4.5-Air","name":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.86},"sourceProvider":"siliconflow-cn"},"siliconflow-cn/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"siliconflow-cn"},"siliconflow/baidu/ERNIE-4.5-300B-A47B":{"id":"baidu/ERNIE-4.5-300B-A47B","name":"baidu/ERNIE-4.5-300B-A47B","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"ernie","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-02","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.28,"output":1.1},"sourceProvider":"siliconflow"},"siliconflow/ByteDance-Seed/Seed-OSS-36B-Instruct":{"id":"ByteDance-Seed/Seed-OSS-36B-Instruct","name":"ByteDance-Seed/Seed-OSS-36B-Instruct","description":"Tool-capable chat model for instruction following and agentic application workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-04","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.21,"output":0.57},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-R1":{"id":"deepseek-ai/DeepSeek-R1","name":"deepseek-ai/DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.5,"output":2.18},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.25,"output":1},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"deepseek-ai/DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-25","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V3.1-Terminus":{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"deepseek-ai/DeepSeek-V3.1-Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-29","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":1},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V3.2":{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.42},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V3.2-Exp":{"id":"deepseek-ai/DeepSeek-V3.2-Exp","name":"deepseek-ai/DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":164000,"output":164000},"cost":{"input":0.27,"output":0.41},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"siliconflow"},"siliconflow/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.145},"sourceProvider":"siliconflow"},"siliconflow/google/gemma-4-26B-A4B-it":{"id":"google/gemma-4-26B-A4B-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.12,"output":0.4},"sourceProvider":"siliconflow"},"siliconflow/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.13,"output":0.4},"sourceProvider":"siliconflow"},"siliconflow/inclusionAI/Ling-flash-2.0":{"id":"inclusionAI/Ling-flash-2.0","name":"inclusionAI/Ling-flash-2.0","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow"},"siliconflow/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMaxAI/MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":197000,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03},"sourceProvider":"siliconflow"},"siliconflow/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"moonshotai/Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.45,"output":2.25,"cache_read":0.07},"sourceProvider":"siliconflow"},"siliconflow/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"moonshotai/Kimi-K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.77,"output":4,"cache_read":0.2},"sourceProvider":"siliconflow"},"siliconflow/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"openai/gpt-oss-120b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":8000},"cost":{"input":0.05,"output":0.45},"sourceProvider":"siliconflow"},"siliconflow/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"openai/gpt-oss-20b","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-13","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":8000},"cost":{"input":0.04,"output":0.18},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen2.5-72B-Instruct":{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.59,"output":0.59},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen2.5-7B-Instruct":{"id":"Qwen/Qwen2.5-7B-Instruct","name":"Qwen/Qwen2.5-7B-Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-18","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":33000,"output":4000},"cost":{"input":0.05,"output":0.05},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-14B":{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen/Qwen3-235B-A22B-Thinking-2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.13,"output":0.6},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen/Qwen3-30B-A3B-Instruct-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.09,"output":0.3},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-32B":{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-8B":{"id":"Qwen/Qwen3-8B","name":"Qwen/Qwen3-8B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.06,"output":0.06},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-Coder-30B-A3B-Instruct":{"id":"Qwen/Qwen3-Coder-30B-A3B-Instruct","name":"Qwen/Qwen3-Coder-30B-A3B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-01","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.07,"output":0.28},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-Coder-480B-A35B-Instruct":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-31","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.25,"output":1},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-235B-A22B-Instruct":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.3,"output":1.5},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-235B-A22B-Thinking":{"id":"Qwen/Qwen3-VL-235B-A22B-Thinking","name":"Qwen/Qwen3-VL-235B-A22B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-04","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.45,"output":3.5},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-30B-A3B-Instruct":{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-05","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.29,"output":1},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-30B-A3B-Thinking":{"id":"Qwen/Qwen3-VL-30B-A3B-Thinking","name":"Qwen/Qwen3-VL-30B-A3B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-11","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.29,"output":1},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-32B-Instruct":{"id":"Qwen/Qwen3-VL-32B-Instruct","name":"Qwen/Qwen3-VL-32B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.2,"output":0.6},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-32B-Thinking":{"id":"Qwen/Qwen3-VL-32B-Thinking","name":"Qwen/Qwen3-VL-32B-Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-21","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.2,"output":1.5},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3-VL-8B-Instruct":{"id":"Qwen/Qwen3-VL-8B-Instruct","name":"Qwen/Qwen3-VL-8B-Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-15","last_updated":"2025-11-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.18,"output":0.68},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.5-122B-A10B":{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.26,"output":2.08},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.5-27B":{"id":"Qwen/Qwen3.5-27B","name":"Qwen3.5 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":2},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.5-35B-A3B":{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5 35B-A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.24,"output":1.8},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.39,"output":2.34},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.15},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":3.2},"sourceProvider":"siliconflow"},"siliconflow/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":1.6},"sourceProvider":"siliconflow"},"siliconflow/stepfun-ai/Step-3.5-Flash":{"id":"stepfun-ai/Step-3.5-Flash","name":"stepfun-ai/Step-3.5-Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","family":"step","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":262000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"siliconflow"},"siliconflow/tencent/Hunyuan-A13B-Instruct":{"id":"tencent/Hunyuan-A13B-Instruct","name":"tencent/Hunyuan-A13B-Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-06-30","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.57},"sourceProvider":"siliconflow"},"siliconflow/tencent/Hy3-preview":{"id":"tencent/Hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.066,"output":0.26,"cache_read":0.029},"sourceProvider":"siliconflow"},"siliconflow/zai-org/GLM-4.5-Air":{"id":"zai-org/GLM-4.5-Air","name":"zai-org/GLM-4.5-Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131000,"output":131000},"cost":{"input":0.14,"output":0.86},"sourceProvider":"siliconflow"},"siliconflow/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"zai-org/GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":205000},"cost":{"input":0.95,"output":2.55,"cache_read":0.2},"sourceProvider":"siliconflow"},"siliconflow/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"zai-org/GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-04-08","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":205000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"siliconflow"},"siliconflow/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1049000,"output":262000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"siliconflow"},"siliconflow/zai-org/GLM-5V-Turbo":{"id":"zai-org/GLM-5V-Turbo","name":"zai-org/GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"sourceProvider":"siliconflow"},"snowflake-cortex/claude-fable-5":{"id":"snowflake-cortex/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-haiku-4-5":{"id":"snowflake-cortex/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-opus-4-5":{"id":"snowflake-cortex/claude-opus-4-5","name":"Claude Opus 4.5 (latest)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-opus-4-6":{"id":"snowflake-cortex/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-opus-4-7":{"id":"snowflake-cortex/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"status":"beta","experimental":{"modes":{"fast":{"cost":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"provider":{"body":{"speed":"fast"},"headers":{"anthropic-beta":"fast-mode-2026-02-01"}}}}},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-opus-4-8":{"id":"snowflake-cortex/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-opus-5":{"id":"snowflake-cortex/claude-opus-5","name":"Claude Opus 5","description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-sonnet-4-5":{"id":"snowflake-cortex/claude-sonnet-4-5","name":"Claude Sonnet 4.5 (latest)","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":16384},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-sonnet-4-6":{"id":"snowflake-cortex/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens"}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":16384},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/claude-sonnet-5":{"id":"snowflake-cortex/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/deepseek-r1":{"id":"snowflake-cortex/deepseek-r1","name":"DeepSeek-R1","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/gemini-3.1-pro":{"id":"snowflake-cortex/gemini-3.1-pro","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/mistral-large2":{"id":"snowflake-cortex/mistral-large2","name":"Mistral Large (latest)","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2024-11-01","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-4.1":{"id":"snowflake-cortex/openai-gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5":{"id":"snowflake-cortex/openai-gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5-mini":{"id":"snowflake-cortex/openai-gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"input":272000,"output":8192},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5-nano":{"id":"snowflake-cortex/openai-gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.1":{"id":"snowflake-cortex/openai-gpt-5.1","name":"GPT-5.1","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.2":{"id":"snowflake-cortex/openai-gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.4":{"id":"snowflake-cortex/openai-gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","experimental":{"modes":{"fast":{"cost":{"input":5,"output":30,"cache_read":0.5},"provider":{"body":{"service_tier":"priority"}}}}},"sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.5":{"id":"snowflake-cortex/openai-gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.6-luna":{"id":"snowflake-cortex/openai-gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.6-sol":{"id":"snowflake-cortex/openai-gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/openai-gpt-5.6-terra":{"id":"snowflake-cortex/openai-gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"status":"beta","sourceProvider":"snowflake-cortex"},"snowflake-cortex/snowflake-llama3.3-70b":{"id":"snowflake-cortex/snowflake-llama3.3-70b","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"sourceProvider":"snowflake-cortex"},"stackit/cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic":{"id":"cortecs/Llama-3.3-70B-Instruct-FP8-Dynamic","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.53,"output":0.76},"sourceProvider":"stackit"},"stackit/google/gemma-3-27b-it":{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"release_date":"2025-05-17","last_updated":"2025-05-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":37000,"output":4096},"cost":{"input":0.53,"output":0.76},"sourceProvider":"stackit"},"stackit/intfloat/e5-mistral-7b-instruct":{"id":"intfloat/e5-mistral-7b-instruct","name":"E5 Mistral 7B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":4096,"output":4096},"cost":{"input":0.02,"output":0.02},"sourceProvider":"stackit"},"stackit/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":8192},"cost":{"input":0.53,"output":0.76},"sourceProvider":"stackit"},"stackit/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.18,"output":0.29},"sourceProvider":"stackit"},"stackit/Qwen/Qwen3-VL-235B-A22B-Instruct-FP8":{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct-FP8","name":"Qwen3-VL 235B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2024-11-01","last_updated":"2024-11-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":218000,"output":16384},"cost":{"input":1.76,"output":2.05},"sourceProvider":"stackit"},"stackit/Qwen/Qwen3-VL-Embedding-8B":{"id":"Qwen/Qwen3-VL-Embedding-8B","name":"Qwen3-VL Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4096},"cost":{"input":0.09,"output":0.09},"sourceProvider":"stackit"},"stackit/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":16384},"cost":{"input":0.53,"output":0.76},"sourceProvider":"stackit"},"stepfun-ai-step-plan/step-3.5-flash":{"id":"stepfun-ai-step-plan/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-ai-step-plan"},"stepfun-ai-step-plan/step-3.5-flash-2603":{"id":"stepfun-ai-step-plan/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-ai-step-plan"},"stepfun-ai-step-plan/step-3.7-flash":{"id":"stepfun-ai-step-plan/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-ai-step-plan"},"stepfun-ai/step-1-32k":{"id":"stepfun-ai/step-1-32k","name":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":2.05,"output":9.59,"cache_read":0.41},"sourceProvider":"stepfun-ai"},"stepfun-ai/step-2-16k":{"id":"stepfun-ai/step-2-16k","name":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":5.21,"output":16.44,"cache_read":1.04},"sourceProvider":"stepfun-ai"},"stepfun-ai/step-3.5-flash":{"id":"stepfun-ai/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"stepfun-ai"},"stepfun-ai/step-3.5-flash-2603":{"id":"stepfun-ai/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"stepfun-ai"},"stepfun-ai/step-3.7-flash":{"id":"stepfun-ai/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-06-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.185,"output":1.11,"cache_read":0.037},"sourceProvider":"stepfun-ai"},"stepfun-ai/step-tts-2":{"id":"stepfun-ai/step-tts-2","name":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun-ai"},"stepfun-ai/stepaudio-2.5-asr":{"id":"stepfun-ai/stepaudio-2.5-asr","name":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-24","last_updated":"2026-07-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun-ai"},"stepfun-ai/stepaudio-2.5-tts":{"id":"stepfun-ai/stepaudio-2.5-tts","name":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun-ai"},"stepfun-step-plan/step-3.5-flash":{"id":"stepfun-step-plan/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-step-plan"},"stepfun-step-plan/step-3.5-flash-2603":{"id":"stepfun-step-plan/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-step-plan"},"stepfun-step-plan/step-3.7-flash":{"id":"stepfun-step-plan/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-step-plan"},"stepfun-step-plan/step-router-v1":{"id":"stepfun-step-plan/step-router-v1","name":"Step Router v1","description":"StepFun routing model that dispatches requests to the appropriate Step model.","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":256000,"output":256000},"sourceProvider":"stepfun-step-plan"},"stepfun/step-1-32k":{"id":"stepfun/step-1-32k","name":"Step 1 (32K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"input":32768,"output":32768},"cost":{"input":2.05,"output":9.59,"cache_read":0.41},"sourceProvider":"stepfun"},"stepfun/step-2-16k":{"id":"stepfun/step-2-16k","name":"Step 2 (16K)","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-01-01","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16384,"input":16384,"output":8192},"cost":{"input":5.21,"output":16.44,"cache_read":1.04},"sourceProvider":"stepfun"},"stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-06-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"stepfun"},"stepfun/step-3.5-flash-2603":{"id":"stepfun/step-3.5-flash-2603","name":"Step 3.5 Flash 2603","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.1,"output":0.3,"cache_read":0.02},"sourceProvider":"stepfun"},"stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-06-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.185,"output":1.11,"cache_read":0.037},"sourceProvider":"stepfun"},"stepfun/step-tts-2":{"id":"stepfun/step-tts-2","name":"Step TTS 2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-03-01","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun"},"stepfun/stepaudio-2.5-asr":{"id":"stepfun/stepaudio-2.5-asr","name":"StepAudio 2.5 ASR","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-24","last_updated":"2026-07-02","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun"},"stepfun/stepaudio-2.5-tts":{"id":"stepfun/stepaudio-2.5-tts","name":"StepAudio 2.5 TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"step","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-16","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"stepfun"},"subconscious/glm-5.2":{"id":"subconscious/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"subconscious"},"subconscious/tim-qwen3.6-27b":{"id":"subconscious/tim-qwen3.6-27b","name":"TIM-Qwen3.6 27B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-11","last_updated":"2026-05-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":8192,"output":5000},"cost":{"input":0.3,"output":3,"cache_read":0.15},"sourceProvider":"subconscious"},"submodel/deepseek-ai/DeepSeek-R1-0528":{"id":"deepseek-ai/DeepSeek-R1-0528","name":"DeepSeek R1 0528","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.5,"output":2.15},"sourceProvider":"submodel"},"submodel/deepseek-ai/DeepSeek-V3-0324":{"id":"deepseek-ai/DeepSeek-V3-0324","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.2,"output":0.8},"sourceProvider":"submodel"},"submodel/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":75000,"output":163840},"cost":{"input":0.2,"output":0.8},"sourceProvider":"submodel"},"submodel/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.5},"sourceProvider":"submodel"},"submodel/Qwen/Qwen3-235B-A22B-Instruct-2507":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.2,"output":0.3},"sourceProvider":"submodel"},"submodel/Qwen/Qwen3-235B-A22B-Thinking-2507":{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.2,"output":0.6},"sourceProvider":"submodel"},"submodel/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-08-23","last_updated":"2025-08-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.8},"sourceProvider":"submodel"},"submodel/zai-org/GLM-4.5-Air":{"id":"zai-org/GLM-4.5-Air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-air","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.5},"sourceProvider":"submodel"},"submodel/zai-org/GLM-4.5-FP8":{"id":"zai-org/GLM-4.5-FP8","name":"GLM 4.5 FP8","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.2,"output":0.8},"sourceProvider":"submodel"},"synthetic/hf:MiniMaxAI/MiniMax-M3":{"id":"hf:MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.6,"output":1.2,"cache_read":0.6},"sourceProvider":"synthetic"},"synthetic/hf:moonshotai/Kimi-K2.7-Code":{"id":"hf:moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.95,"output":4,"cache_read":0.95},"sourceProvider":"synthetic"},"synthetic/hf:moonshotai/Kimi-K3":{"id":"hf:moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":3,"output":15,"cache_read":0.45},"sourceProvider":"synthetic"},"synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4":{"id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":1,"cache_read":0.3},"sourceProvider":"synthetic"},"synthetic/hf:openai/gpt-oss-120b":{"id":"hf:openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.1,"output":0.1,"cache_read":0.1},"sourceProvider":"synthetic"},"synthetic/hf:Qwen/Qwen3.6-27B":{"id":"hf:Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3.6,"cache_read":0.45},"sourceProvider":"synthetic"},"synthetic/hf:zai-org/GLM-4.7-Flash":{"id":"hf:zai-org/GLM-4.7-Flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":65536},"cost":{"input":0.1,"output":0.5,"cache_read":0.1},"sourceProvider":"synthetic"},"synthetic/hf:zai-org/GLM-5.2":{"id":"hf:zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","xhigh"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":1.4,"output":4.4,"cache_read":1.4},"sourceProvider":"synthetic"},"tencent-coding-plan/glm-5":{"id":"tencent-coding-plan/glm-5","name":"GLM-5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/hunyuan-2.0-instruct":{"id":"tencent-coding-plan/hunyuan-2.0-instruct","name":"Tencent HY 2.0 Instruct","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/hunyuan-2.0-thinking":{"id":"tencent-coding-plan/hunyuan-2.0-thinking","name":"Tencent HY 2.0 Think","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/hunyuan-t1":{"id":"tencent-coding-plan/hunyuan-t1","name":"Hunyuan-T1","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/hunyuan-turbos":{"id":"tencent-coding-plan/hunyuan-turbos","name":"Hunyuan-TurboS","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"hunyuan","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/kimi-k2.5":{"id":"tencent-coding-plan/kimi-k2.5","name":"Kimi-K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/minimax-m2.5":{"id":"tencent-coding-plan/minimax-m2.5","name":"MiniMax-M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":32768},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-coding-plan/tc-code-latest":{"id":"tencent-coding-plan/tc-code-latest","name":"Auto","description":"Automatic model router for matching prompts to suitable backends and budgets","family":"auto","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-08","last_updated":"2026-03-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":16384},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-coding-plan"},"tencent-token-plan/hy3":{"id":"tencent-token-plan/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-token-plan"},"tencent-tokenhub/hy3":{"id":"tencent-tokenhub/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-tokenhub"},"tencent-tokenhub/hy3-preview":{"id":"tencent-tokenhub/hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"tencent-tokenhub"},"tensorx/deepseek/deepseek-chat-v3.1":{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek Chat V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2024-11","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":163840},"cost":{"input":0.2,"output":0.8,"cache_read":0.05,"cache_write":0.25},"sourceProvider":"tensorx"},"tensorx/deepseek/deepseek-r1-0528":{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1-0528","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":164000,"output":8192},"cost":{"input":0.66,"output":2.6,"cache_read":0.165,"cache_write":0.825},"sourceProvider":"tensorx"},"tensorx/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.3,"output":0.5,"cache_read":0.075,"cache_write":0.375},"sourceProvider":"tensorx"},"tensorx/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.15,"output":0.3,"cache_read":0.0375,"cache_write":0.1875},"sourceProvider":"tensorx"},"tensorx/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.25,"output":0.3,"cache_read":0.06},"sourceProvider":"tensorx"},"tensorx/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.75,"output":3.5,"cache_read":0.4375,"cache_write":2.185},"sourceProvider":"tensorx"},"tensorx/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax-M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.075,"cache_write":0.375},"sourceProvider":"tensorx"},"tensorx/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.1},"sourceProvider":"tensorx"},"tensorx/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":2.8,"cache_read":0.125,"cache_write":0.625},"sourceProvider":"tensorx"},"tensorx/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1,"output":4,"cache_read":0.25,"cache_write":1.25},"sourceProvider":"tensorx"},"tensorx/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.25,"output":4.5,"cache_read":0.3125},"sourceProvider":"tensorx"},"tensorx/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"tensorx"},"tensorx/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.3,"output":0.9,"cache_read":0.075,"cache_write":0.375},"sourceProvider":"tensorx"},"tensorx/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.04,"output":0.2,"cache_read":0.01,"cache_write":0.05},"sourceProvider":"tensorx"},"tensorx/qwen/qwen3-235b-a22b-2507":{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen3 235B-A22B-2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06-30","release_date":"2025-07-21","last_updated":"2025-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":262144},"cost":{"input":0.072,"output":0.464,"cache_read":0.018,"cache_write":0.09},"sourceProvider":"tensorx"},"tensorx/qwen/qwen3-coder-30b-a3b-instruct":{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65536},"cost":{"input":0.06,"output":0.25,"cache_read":0.015,"cache_write":0.075},"sourceProvider":"tensorx"},"tensorx/qwen/qwen3-vl-235b-a22b-instruct":{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B-A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131000,"output":131072},"cost":{"input":0.21,"output":1.9,"cache_read":0.0525,"cache_write":0.2625},"sourceProvider":"tensorx"},"tensorx/qwen/qwen3.5-122b-a10b":{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.5,"output":3.5,"cache_read":0.125,"cache_write":0.625},"sourceProvider":"tensorx"},"tensorx/qwen/qwen3.5-9b":{"id":"qwen/qwen3.5-9b","name":"Qwen3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.15,"output":0.2,"cache_read":0.0375,"cache_write":0.1875},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":200000},"cost":{"input":0.6,"output":2.2,"cache_read":0.15,"cache_write":0.75},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1,"output":3.2,"cache_read":0.25,"cache_write":1.25},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.4,"output":4.4,"cache_read":0.35,"cache_write":1.75},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.5,"output":4.5,"cache_read":0.375},"sourceProvider":"tensorx"},"tensorx/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":202752,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.3,"cache_write":1.5},"sourceProvider":"tensorx"},"the-grid-ai/agent-max":{"id":"the-grid-ai/agent-max","name":"Agent Max","description":"Frontier models for autonomous research, deep multi-step tool chains, and complex long-horizon tasks. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-05-04","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/agent-prime":{"id":"the-grid-ai/agent-prime","name":"Agent Prime","description":"Reliable models for dependable agentic applications, multi-step tool use, and reasoning workflows. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":30000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/agent-standard":{"id":"the-grid-ai/agent-standard","name":"Agent Standard","description":"Price-optimized models for fast tool calls, simple agent loops, high-throughput automation, and orchestration. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":16000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/code-max":{"id":"the-grid-ai/code-max","name":"Code Max","description":"Frontier models for complex research, architectural decisions, debugging, and multi-file development. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-05-04","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/code-prime":{"id":"the-grid-ai/code-prime","name":"Code Prime","description":"Reliable models for everyday software tasks, code completion, review, and standard debugging. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":30000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/code-standard":{"id":"the-grid-ai/code-standard","name":"Code Standard","description":"Price-optimized models for rapid autocomplete, linting, high-frequency suggestions, and batch edits. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-05-04","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":16000},"status":"beta","sourceProvider":"the-grid-ai"},"the-grid-ai/text-max":{"id":"the-grid-ai/text-max","name":"Text Max","description":"Frontier models for deep reasoning, long context, and complex workflows. Any model that meets the contract spec can serve your request.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-02-26","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"sourceProvider":"the-grid-ai"},"the-grid-ai/text-prime":{"id":"the-grid-ai/text-prime","name":"Text Prime","description":"Reliable models for everyday text generation, editing, and analysis across diverse workflows. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":196608,"input":120000,"output":30000},"sourceProvider":"the-grid-ai"},"the-grid-ai/text-standard":{"id":"the-grid-ai/text-standard","name":"Text Standard","description":"Price-optimized models with low-latency, high-throughput and shorter maximum outputs. Any model that meets the contract spec can serve your request.","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-26","last_updated":"2026-07-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":120000,"output":16000},"sourceProvider":"the-grid-ai"},"thinkingmachines/Inkling":{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":65536,"output":65536},"cost":{"input":1.87,"output":4.68,"cache_read":0.374},"sourceProvider":"thinkingmachines"},"thinkingmachines/Inkling:peft:262144":{"id":"thinkingmachines/Inkling:peft:262144","name":"Inkling (256K)","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":3.74,"output":9.36,"cache_read":0.748},"sourceProvider":"thinkingmachines"},"tinfoil/deepseek-v4-flash":{"id":"tinfoil/deepseek-v4-flash","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":0.3,"output":0.7,"cache_read":0.06},"sourceProvider":"tinfoil"},"tinfoil/gemma4-31b":{"id":"tinfoil/gemma4-31b","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.4,"output":1},"sourceProvider":"tinfoil"},"tinfoil/glm-5-2":{"id":"tinfoil/glm-5-2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":393216,"output":131072},"cost":{"input":1.5,"output":5.25,"cache_read":0.375},"sourceProvider":"tinfoil"},"tinfoil/gpt-oss-120b":{"id":"tinfoil/gpt-oss-120b","name":"gpt-oss-120b","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"tinfoil"},"tinfoil/gpt-oss-safeguard-120b":{"id":"tinfoil/gpt-oss-safeguard-120b","name":"gpt-oss-safeguard-120b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-10-29","last_updated":"2025-10-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":0.6},"sourceProvider":"tinfoil"},"tinfoil/kimi-k3":{"id":"tinfoil/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":4,"output":20,"cache_read":0.8},"sourceProvider":"tinfoil"},"tinfoil/llama3-3-70b":{"id":"tinfoil/llama3-3-70b","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":1.75,"output":2.75},"sourceProvider":"tinfoil"},"tinfoil/nomic-embed-text":{"id":"tinfoil/nomic-embed-text","name":"Nomic Embed Text v1.5","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":false,"release_date":"2024-02","last_updated":"2024-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":768},"cost":{"input":0.05,"output":0},"sourceProvider":"tinfoil"},"togetherai/deepcogito/cogito-v2-1-671b":{"id":"deepcogito/cogito-v2-1-671b","name":"Cogito v2.1 671B","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"cogito","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"temperature":true,"release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163840,"output":163840},"cost":{"input":1.25,"output":1.25},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-R1":{"id":"deepseek-ai/DeepSeek-R1","name":"DeepSeek-R1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-03-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163839,"output":163839},"status":"deprecated","cost":{"input":3,"output":7},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-V3":{"id":"deepseek-ai/DeepSeek-V3","name":"DeepSeek-V3","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2024-12-26","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":1.25,"output":1.25},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-V3-1":{"id":"deepseek-ai/DeepSeek-V3-1","name":"DeepSeek V3.1","description":"Legacy model retained for compatibility with older integrations","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"status":"deprecated","cost":{"input":0.6,"output":1.7},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.03},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":384000},"cost":{"input":1.74,"output":3.48,"cache_read":0.2},"sourceProvider":"togetherai"},"togetherai/deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.13},"sourceProvider":"togetherai"},"togetherai/essentialai/Rnj-1-Instruct":{"id":"essentialai/Rnj-1-Instruct","name":"Rnj-1 Instruct","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"rnj","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-05","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"status":"deprecated","cost":{"input":0.15,"output":0.15},"sourceProvider":"togetherai"},"togetherai/google/gemma-3n-E4B-it":{"id":"google/gemma-3n-E4B-it","name":"Gemma 3N E4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.06,"output":0.12},"sourceProvider":"togetherai"},"togetherai/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.39,"output":0.97},"sourceProvider":"togetherai"},"togetherai/LiquidAI/LFM2-24B-A2B":{"id":"LiquidAI/LFM2-24B-A2B","name":"LFM2-24B-A2B","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","family":"liquid","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-02-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.03,"output":0.12},"sourceProvider":"togetherai"},"togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo":{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"Llama 3.3 70B","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":1.04,"output":1.04},"sourceProvider":"togetherai"},"togetherai/meta-llama/Meta-Llama-3-8B-Instruct-Lite":{"id":"meta-llama/Meta-Llama-3-8B-Instruct-Lite","name":"Meta Llama 3 8B Instruct Lite","description":"Compact Llama instruction model for fast chat and local deployment","family":"llama","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-18","last_updated":"2024-04-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0.14,"output":0.14},"sourceProvider":"togetherai"},"togetherai/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax-M2.5","description":"Legacy model retained for compatibility with older integrations","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"status":"deprecated","cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"togetherai"},"togetherai/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"togetherai"},"togetherai/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":250000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"togetherai"},"togetherai/moonshotai/Kimi-K2.5":{"id":"moonshotai/Kimi-K2.5","name":"Kimi K2.5","description":"Legacy model retained for compatibility with older integrations","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.5,"output":2.8},"sourceProvider":"togetherai"},"togetherai/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131000},"cost":{"input":1.2,"output":4.5,"cache_read":0.2},"sourceProvider":"togetherai"},"togetherai/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Kimi coding model for software agents, refactors, and repository reasoning","family":"kimi-k2","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-14","last_updated":"2026-06-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"togetherai"},"togetherai/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"togetherai"},"togetherai/nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512300,"output":512300},"cost":{"input":0.6,"output":3.6,"cache_read":0.2},"sourceProvider":"togetherai"},"togetherai/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.15,"output":0.6},"sourceProvider":"togetherai"},"togetherai/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.2},"sourceProvider":"togetherai"},"togetherai/pearl-ai/gemma-4-31b-it":{"id":"pearl-ai/gemma-4-31b-it","name":"Pearl AI Gemma 4 31B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.28,"output":0.86},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen2.5-7B-Instruct-Turbo":{"id":"Qwen/Qwen2.5-7B-Instruct-Turbo","name":"Qwen 2.5 7B Instruct Turbo","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-09-19","last_updated":"2024-09-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.3,"output":0.3},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput":{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507-tput","name":"Qwen3 235B A22B Instruct 2507 FP8","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.2,"output":0.6},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","name":"Qwen3 Coder 480B A35B Instruct","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":2,"output":2},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3-Coder-Next-FP8":{"id":"Qwen/Qwen3-Coder-Next-FP8","name":"Qwen3 Coder Next FP8","description":"Legacy model retained for compatibility with older integrations","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2026-02-03","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"status":"deprecated","cost":{"input":0.5,"output":1.2},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B A17B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":130000},"status":"deprecated","cost":{"input":0.6,"output":3.6,"cache_read":0.35},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3.5-9B":{"id":"Qwen/Qwen3.5-9B","name":"Qwen3.5 9B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.17,"output":0.25},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3.6-Plus":{"id":"Qwen/Qwen3.6-Plus","name":"Qwen3.6 Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":500000},"cost":{"input":0.5,"output":3},"sourceProvider":"togetherai"},"togetherai/Qwen/Qwen3.7-Max":{"id":"Qwen/Qwen3.7-Max","name":"Qwen3.7 Max","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":500000},"cost":{"input":1.25,"output":3.75,"cache_read":0.125},"sourceProvider":"togetherai"},"togetherai/thinkingmachines/Inkling":{"id":"thinkingmachines/Inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["max","xhigh","high","medium","low","none"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":131072},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"togetherai"},"togetherai/zai-org/GLM-5":{"id":"zai-org/GLM-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"status":"deprecated","cost":{"input":1,"output":3.2},"sourceProvider":"togetherai"},"togetherai/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-11","release_date":"2026-04-07","last_updated":"2026-07-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"status":"deprecated","cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"togetherai"},"togetherai/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":164000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"togetherai"},"trustedrouter/auto":{"id":"trustedrouter/auto","name":"Auto","description":"TrustedRouter automatic routing alias that chooses a healthy supported model endpoint for the request.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/cheap":{"id":"trustedrouter/cheap","name":"Cheap","description":"TrustedRouter low-cost routing alias that prefers inexpensive healthy model endpoints.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/e2e":{"id":"trustedrouter/e2e","name":"End-to-End Encrypted","description":"TrustedRouter privacy routing alias for end-to-end encrypted provider routes where available.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/fast":{"id":"trustedrouter/fast","name":"Fast","description":"TrustedRouter speed routing alias that prefers low-latency healthy model endpoints.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/synth":{"id":"trustedrouter/synth","name":"Synth","description":"TrustedRouter synthesis orchestration alias that combines multiple model responses into one answer.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-20","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/synth-code":{"id":"trustedrouter/synth-code","name":"Synth Code","description":"TrustedRouter code synthesis orchestration alias that combines multiple model responses into one answer.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-20","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"trustedrouter/zdr":{"id":"trustedrouter/zdr","name":"Zero Data Retention","description":"TrustedRouter privacy routing alias that prefers zero data retention model endpoints.","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-27","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"sourceProvider":"trustedrouter"},"umans-ai-coding-plan/umans-coder":{"id":"umans-ai-coding-plan/umans-coder","name":"Umans Coder","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-deepseek-v4-flash-0731":{"id":"umans-ai-coding-plan/umans-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-deepseek-v4-pro-0813":{"id":"umans-ai-coding-plan/umans-deepseek-v4-pro-0813","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-flash":{"id":"umans-ai-coding-plan/umans-flash","name":"Umans Flash","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-glm-5.2":{"id":"umans-ai-coding-plan/umans-glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":405504,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-kimi-k2.7":{"id":"umans-ai-coding-plan/umans-kimi-k2.7","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-kimi-k3":{"id":"umans-ai-coding-plan/umans-kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai-coding-plan/umans-qwen3.6-35b-a3b":{"id":"umans-ai-coding-plan/umans-qwen3.6-35b-a3b","name":"Qwen3.6 35B A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"umans-ai-coding-plan"},"umans-ai/umans-coder":{"id":"umans-ai/umans-coder","name":"Umans Coder","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"umans-ai"},"umans-ai/umans-deepseek-v4-flash-0731":{"id":"umans-ai/umans-deepseek-v4-flash-0731","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":0.14,"output":0.28,"cache_read":0.028},"sourceProvider":"umans-ai"},"umans-ai/umans-deepseek-v4-pro-0813":{"id":"umans-ai/umans-deepseek-v4-pro-0813","name":"DeepSeek V4 Pro","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":393215},"cost":{"input":1.32,"output":3.96,"cache_read":0.044},"sourceProvider":"umans-ai"},"umans-ai/umans-flash":{"id":"umans-ai/umans-flash","name":"Umans Flash","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.15,"output":1,"cache_read":0.05},"sourceProvider":"umans-ai"},"umans-ai/umans-glm-5.2":{"id":"umans-ai/umans-glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":405504,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"umans-ai"},"umans-ai/umans-kimi-k2.7":{"id":"umans-ai/umans-kimi-k2.7","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"umans-ai"},"umans-ai/umans-kimi-k3":{"id":"umans-ai/umans-kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"umans-ai"},"unorouter/claude-haiku-4-5-20251001":{"id":"unorouter/claude-haiku-4-5-20251001","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1.2,"output":6},"sourceProvider":"unorouter"},"unorouter/claude-opus-4-8":{"id":"unorouter/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.425,"output":2.125},"sourceProvider":"unorouter"},"unorouter/claude-sonnet-5":{"id":"unorouter/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.44,"output":7.2},"sourceProvider":"unorouter"},"unorouter/deepseek-v4-flash":{"id":"unorouter/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.0625,"output":0.125},"sourceProvider":"unorouter"},"unorouter/deepseek-v4-flash:free":{"id":"unorouter/deepseek-v4-flash:free","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/deepseek-v4-pro":{"id":"unorouter/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.8999,"output":1.7999},"sourceProvider":"unorouter"},"unorouter/deepseek-v4-pro:free":{"id":"unorouter/deepseek-v4-pro:free","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/gemini-3.5-flash":{"id":"unorouter/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1857,"output":1.1142},"sourceProvider":"unorouter"},"unorouter/gemma-4-31b-it:free":{"id":"unorouter/gemma-4-31b-it:free","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/glm-4.5-flash:free":{"id":"unorouter/glm-4.5-flash:free","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/glm-5.2":{"id":"unorouter/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.6001,"output":5.0288},"sourceProvider":"unorouter"},"unorouter/glm-5.2:free":{"id":"unorouter/glm-5.2:free","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/gpt-5.2":{"id":"unorouter/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.05,"output":8.4},"sourceProvider":"unorouter"},"unorouter/gpt-5.4":{"id":"unorouter/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1.8,"output":10.8},"sourceProvider":"unorouter"},"unorouter/gpt-5.4:free":{"id":"unorouter/gpt-5.4:free","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/gpt-5.5":{"id":"unorouter/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.1875,"output":1.125},"sourceProvider":"unorouter"},"unorouter/gpt-5.5:free":{"id":"unorouter/gpt-5.5:free","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/kimi-k2.6":{"id":"unorouter/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1.2675,"output":5.3368},"sourceProvider":"unorouter"},"unorouter/minimax-m2.7":{"id":"unorouter/minimax-m2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.819,"output":3.276},"sourceProvider":"unorouter"},"unorouter/minimax-m2.7:free":{"id":"unorouter/minimax-m2.7:free","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/nemotron-3-ultra-550b-a55b:free":{"id":"unorouter/nemotron-3-ultra-550b-a55b:free","name":"Nemotron 3 Ultra 550B A55B","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/qwen3.5-397b-a17b:free":{"id":"unorouter/qwen3.5-397b-a17b:free","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"unorouter/step-3.7-flash:free":{"id":"unorouter/step-3.7-flash:free","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0,"output":0},"sourceProvider":"unorouter"},"upstage/solar-mini":{"id":"upstage/solar-mini","name":"solar-mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"solar-mini","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-06-12","last_updated":"2025-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":4096},"cost":{"input":0.15,"output":0.15},"sourceProvider":"upstage"},"upstage/solar-pro2":{"id":"upstage/solar-pro2","name":"solar-pro2","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":8192},"cost":{"input":0.25,"output":0.25},"sourceProvider":"upstage"},"upstage/solar-pro3":{"id":"upstage/solar-pro3","name":"solar-pro3","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":8192},"cost":{"input":0.25,"output":0.25},"sourceProvider":"upstage"},"upstage/solar-pro4":{"id":"upstage/solar-pro4","name":"Solar Pro 4","description":"Upstage's flagship model, specialized for agentic use","family":"solar-pro","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02","release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":524288,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"upstage"},"v0/v0-1.0-md":{"id":"v0/v0-1.0-md","name":"v0-1.0-md","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"v0","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":3,"output":15},"sourceProvider":"v0"},"v0/v0-1.5-lg":{"id":"v0/v0-1.5-lg","name":"v0-1.5-lg","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"v0","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-09","last_updated":"2025-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":512000,"output":32000},"cost":{"input":15,"output":75},"sourceProvider":"v0"},"v0/v0-1.5-md":{"id":"v0/v0-1.5-md","name":"v0-1.5-md","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"v0","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2025-06-09","last_updated":"2025-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32000},"cost":{"input":3,"output":15},"sourceProvider":"v0"},"venice/aion-labs-aion-3-0":{"id":"venice/aion-labs-aion-3-0","name":"Aion 3.0","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":3.75,"output":7.5,"cache_read":0.9375},"sourceProvider":"venice"},"venice/aion-labs-aion-3-0-mini":{"id":"venice/aion-labs-aion-3-0-mini","name":"Aion 3.0 Mini","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":0.875,"output":1.75,"cache_read":0.225},"sourceProvider":"venice"},"venice/claude-fable-5":{"id":"venice/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-10","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":12,"output":60,"cache_read":1.2,"cache_write":15},"sourceProvider":"venice"},"venice/claude-opus-4-5":{"id":"venice/claude-opus-4-5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-12-06","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":198000,"output":32768},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"sourceProvider":"venice"},"venice/claude-opus-4-6":{"id":"venice/claude-opus-4-6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"sourceProvider":"venice"},"venice/claude-opus-4-7":{"id":"venice/claude-opus-4-7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"sourceProvider":"venice"},"venice/claude-opus-4-8":{"id":"venice/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"sourceProvider":"venice"},"venice/claude-opus-4-8-fast":{"id":"venice/claude-opus-4-8-fast","name":"Claude Opus 4.8 Fast","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":12,"output":60,"cache_read":1.2,"cache_write":15},"sourceProvider":"venice"},"venice/claude-opus-5":{"id":"venice/claude-opus-5","name":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-23","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6,"output":30,"cache_read":0.6,"cache_write":7.5},"sourceProvider":"venice"},"venice/claude-opus-5-fast":{"id":"venice/claude-opus-5-fast","name":"Claude Opus 5 Fast","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-23","last_updated":"2026-07-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":12,"output":60,"cache_read":1.2,"cache_write":15},"sourceProvider":"venice"},"venice/claude-sonnet-4-5":{"id":"venice/claude-sonnet-4-5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-01-15","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":198000,"output":64000},"cost":{"input":3.75,"output":18.75,"cache_read":0.375,"cache_write":4.69},"sourceProvider":"venice"},"venice/claude-sonnet-4-6":{"id":"venice/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3.6,"output":18,"cache_read":0.36,"cache_write":4.5},"sourceProvider":"venice"},"venice/claude-sonnet-5":{"id":"venice/claude-sonnet-5","name":"Claude Sonnet 5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-29","last_updated":"2026-07-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"venice"},"venice/deepseek-v3.2":{"id":"venice/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":160000,"output":32768},"cost":{"input":0.33,"output":0.48,"cache_read":0.16},"sourceProvider":"venice"},"venice/deepseek-v4-flash":{"id":"venice/deepseek-v4-flash","name":"DeepSeek V4 Flash 0423","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.138,"output":0.275,"cache_read":0.028},"sourceProvider":"venice"},"venice/deepseek-v4-flash-0731":{"id":"venice/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-08-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.175,"output":0.35,"cache_read":0.035},"sourceProvider":"venice"},"venice/deepseek-v4-flash-0731-fast":{"id":"venice/deepseek-v4-flash-0731-fast","name":"DeepSeek V4 Flash 0731 Fast","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-08-09","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0.35,"output":0.7,"cache_read":0.0875},"sourceProvider":"venice"},"venice/deepseek-v4-pro":{"id":"venice/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":1.65,"output":3.301,"cache_read":0.33},"sourceProvider":"venice"},"venice/deepseek-v4-pro-0813":{"id":"venice/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":1.65,"output":4.95,"cache_read":0.165},"sourceProvider":"venice"},"venice/gemini-3-1-pro-preview":{"id":"venice/gemini-3-1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32768},"cost":{"input":2.5,"output":15,"cache_read":0.5,"cache_write":0.5,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":0.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":0.5}},"sourceProvider":"venice"},"venice/gemini-3-5-flash":{"id":"venice/gemini-3-5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-22","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.55,"output":9.45,"cache_read":0.155,"cache_write":0.086},"sourceProvider":"venice"},"venice/gemini-3-5-flash-lite":{"id":"venice/gemini-3-5-flash-lite","name":"Gemini 3.5 Flash-Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-09","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.375,"output":3.125,"cache_read":0.0375},"sourceProvider":"venice"},"venice/gemini-3-6-flash":{"id":"venice/gemini-3-6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-09","last_updated":"2026-07-21","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.875,"output":9.375,"cache_read":0.1875},"sourceProvider":"venice"},"venice/gemini-3-7-flash":{"id":"venice/gemini-3-7-flash","name":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1.875,"output":9.375,"cache_read":0.1875},"sourceProvider":"venice"},"venice/gemini-3-flash-preview":{"id":"venice/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-12-19","last_updated":"2026-06-11","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.7,"output":3.75,"cache_read":0.07},"sourceProvider":"venice"},"venice/gemma-4-uncensored":{"id":"venice/gemma-4-uncensored","name":"Gemma 4 Uncensored","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-13","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.1625,"output":0.5},"sourceProvider":"venice"},"venice/google-gemma-3-27b-it":{"id":"venice/google-gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-11-04","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.12,"output":0.2},"sourceProvider":"venice"},"venice/google-gemma-4-26b-a4b-it":{"id":"venice/google-gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.13,"output":0.4,"cache_read":0.05},"sourceProvider":"venice"},"venice/google-gemma-4-31b-it":{"id":"venice/google-gemma-4-31b-it","name":"Google Gemma 4 31B Instruct","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-03","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":8192},"cost":{"input":0.12,"output":0.36,"cache_read":0.09},"sourceProvider":"venice"},"venice/grok-4-20":{"id":"venice/grok-4-20","name":"Grok 4.20","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"release_date":"2026-03-12","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"sourceProvider":"venice"},"venice/grok-4-20-multi-agent":{"id":"venice/grok-4-20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":true,"release_date":"2026-03-12","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":128000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"sourceProvider":"venice"},"venice/grok-4-3":{"id":"venice/grok-4-3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-18","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.42,"output":2.83,"cache_read":0.23,"tiers":[{"input":2.83,"output":5.67,"cache_read":0.45,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.83,"output":5.67,"cache_read":0.45}},"sourceProvider":"venice"},"venice/grok-4-5":{"id":"venice/grok-4-5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-07","last_updated":"2026-07-08","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":32000},"cost":{"input":2.27,"output":6.8,"cache_read":0.34,"tiers":[{"input":4.53,"output":13.6,"cache_read":0.68,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4.53,"output":13.6,"cache_read":0.68}},"sourceProvider":"venice"},"venice/grok-4-6":{"id":"venice/grok-4-6","name":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-10","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":200000},"cost":{"input":2.27,"output":6.8,"cache_read":0.57,"tiers":[{"input":4.53,"output":13.6,"cache_read":1.13,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4.53,"output":13.6,"cache_read":1.13}},"sourceProvider":"venice"},"venice/grok-build-0-1":{"id":"venice/grok-build-0-1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"venice"},"venice/hermes-3-llama-3.1-405b":{"id":"venice/hermes-3-llama-3.1-405b","name":"Hermes 3 Llama 3.1 405b","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"hermes","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-09-25","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":1.1,"output":3},"sourceProvider":"venice"},"venice/inkling":{"id":"venice/inkling","name":"Inkling","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-17","modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":1.25,"output":5.0625,"cache_read":0.2125},"sourceProvider":"venice"},"venice/kimi-k2-5":{"id":"venice/kimi-k2-5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2024-04","release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.56,"output":3.5,"cache_read":0.22},"sourceProvider":"venice"},"venice/kimi-k2-6":{"id":"venice/kimi-k2-6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.75,"output":3.5,"cache_read":0.16},"sourceProvider":"venice"},"venice/kimi-k2-7-code":{"id":"venice/kimi-k2-7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-13","last_updated":"2026-06-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.75,"output":3.5,"cache_read":0.16},"sourceProvider":"venice"},"venice/kimi-k3":{"id":"venice/kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3.75,"output":18.75,"cache_read":0.375},"sourceProvider":"venice"},"venice/kimi-k3-fast-api":{"id":"venice/kimi-k3-fast-api","name":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"venice"},"venice/llama-3.2-3b":{"id":"venice/llama-3.2-3b","name":"Llama 3.2 3B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-10-03","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.15,"output":0.6},"sourceProvider":"venice"},"venice/llama-3.3-70b":{"id":"venice/llama-3.3-70b","name":"Llama 3.3 70B","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"release_date":"2025-04-06","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.7,"output":2.8},"sourceProvider":"venice"},"venice/mercury-2":{"id":"venice/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-02-20","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":50000},"cost":{"input":0.3125,"output":0.9375,"cache_read":0.03125},"sourceProvider":"venice"},"venice/minimax-m25":{"id":"venice/minimax-m25","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32768},"cost":{"input":0.27,"output":0.95,"cache_read":0.03},"sourceProvider":"venice"},"venice/minimax-m27":{"id":"venice/minimax-m27","name":"MiniMax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32768},"cost":{"input":0.375,"output":1.5,"cache_read":0.06875},"sourceProvider":"venice"},"venice/minimax-m3-preview":{"id":"venice/minimax-m3-preview","name":"MiniMax M3 Preview","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","family":"minimax-m3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-06-12","last_updated":"2026-06-13","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":524288,"output":65536},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"venice"},"venice/mistral-small-2603":{"id":"venice/mistral-small-2603","name":"Mistral Small 4","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","family":"mistral-small","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-06","release_date":"2026-03-16","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.1875,"output":0.75},"sourceProvider":"venice"},"venice/mistral-small-3-2-24b-instruct":{"id":"venice/mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B Instruct","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-01-15","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.09375,"output":0.25},"sourceProvider":"venice"},"venice/nvidia-nemotron-3-nano-30b-a3b":{"id":"venice/nvidia-nemotron-3-nano-30b-a3b","name":"NVIDIA Nemotron 3 Nano 30B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.075,"output":0.3},"sourceProvider":"venice"},"venice/nvidia-nemotron-3-ultra-550b-a55b":{"id":"venice/nvidia-nemotron-3-ultra-550b-a55b","name":"NVIDIA Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.625,"output":3.125,"cache_read":0.1875},"sourceProvider":"venice"},"venice/olafangensan-glm-4.7-flash-heretic":{"id":"venice/olafangensan-glm-4.7-flash-heretic","name":"GLM 4.7 Flash Heretic","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-02-04","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":24000},"cost":{"input":0.07,"output":0.4,"cache_read":0.035},"sourceProvider":"venice"},"venice/openai-gpt-4o-2024-11-20":{"id":"venice/openai-gpt-4o-2024-11-20","name":"GPT-4o","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2026-02-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":3.125,"output":12.5},"sourceProvider":"venice"},"venice/openai-gpt-4o-mini-2024-07-18":{"id":"venice/openai-gpt-4o-mini-2024-07-18","name":"GPT-4o Mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2026-02-28","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.1875,"output":0.75,"cache_read":0.09375},"sourceProvider":"venice"},"venice/openai-gpt-52":{"id":"venice/openai-gpt-52","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-13","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":272000,"output":65536},"cost":{"input":2.19,"output":17.5,"cache_read":0.219},"sourceProvider":"venice"},"venice/openai-gpt-52-codex":{"id":"venice/openai-gpt-52-codex","name":"GPT-5.2 Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08","release_date":"2025-01-15","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"input":272000,"output":65536},"cost":{"input":2.19,"output":17.5,"cache_read":0.219},"sourceProvider":"venice"},"venice/openai-gpt-53-codex":{"id":"venice/openai-gpt-53-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.19,"output":17.5,"cache_read":0.219},"sourceProvider":"venice"},"venice/openai-gpt-54":{"id":"venice/openai-gpt-54","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":131072},"cost":{"input":3.13,"output":18.8,"cache_read":0.313},"sourceProvider":"venice"},"venice/openai-gpt-54-mini":{"id":"venice/openai-gpt-54-mini","name":"GPT-5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-27","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.9375,"output":5.625,"cache_read":0.09375},"sourceProvider":"venice"},"venice/openai-gpt-54-pro":{"id":"venice/openai-gpt-54-pro","name":"GPT-5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":37.5,"output":225,"tiers":[{"input":75,"output":337.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":75,"output":337.5}},"sourceProvider":"venice"},"venice/openai-gpt-55":{"id":"venice/openai-gpt-55","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":131072},"cost":{"input":6.25,"output":37.5,"cache_read":0.625,"tiers":[{"input":12.5,"output":56.25,"cache_read":1.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":12.5,"output":56.25,"cache_read":1.25}},"sourceProvider":"venice"},"venice/openai-gpt-55-pro":{"id":"venice/openai-gpt-55-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":922000,"output":128000},"cost":{"input":37.5,"output":225},"sourceProvider":"venice"},"venice/openai-gpt-56-luna":{"id":"venice/openai-gpt-56-luna","name":"GPT-5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":0.26666667,"output":1.6,"cache_read":0.02666667,"cache_write":0.33333334},"sourceProvider":"venice"},"venice/openai-gpt-56-luna-pro":{"id":"venice/openai-gpt-56-luna-pro","name":"GPT-5.6 Luna Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.25,"output":7.5,"cache_read":0.125,"cache_write":1.5625,"tiers":[{"input":2.5,"output":11.25,"cache_read":0.25,"cache_write":3.125,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2.5,"output":11.25,"cache_read":0.25,"cache_write":3.125}},"sourceProvider":"venice"},"venice/openai-gpt-56-sol":{"id":"venice/openai-gpt-56-sol","name":"GPT-5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.25,"output":37.5,"cache_read":0.625,"cache_write":7.8125},"sourceProvider":"venice"},"venice/openai-gpt-56-sol-pro":{"id":"venice/openai-gpt-56-sol-pro","name":"GPT-5.6 Sol Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":6.25,"output":37.5,"cache_read":0.625,"cache_write":7.8125,"tiers":[{"input":12.5,"output":56.25,"cache_read":1.25,"cache_write":15.625,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":12.5,"output":56.25,"cache_read":1.25,"cache_write":15.625}},"sourceProvider":"venice"},"venice/openai-gpt-56-terra":{"id":"venice/openai-gpt-56-terra","name":"GPT-5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.125,"output":18.75,"cache_read":0.3125,"cache_write":3.90625},"sourceProvider":"venice"},"venice/openai-gpt-56-terra-pro":{"id":"venice/openai-gpt-56-terra-pro","name":"GPT-5.6 Terra Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3.125,"output":18.75,"cache_read":0.3125,"cache_write":3.90625,"tiers":[{"input":6.25,"output":28.125,"cache_read":0.625,"cache_write":7.8125,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":6.25,"output":28.125,"cache_read":0.625,"cache_write":7.8125}},"sourceProvider":"venice"},"venice/openai-gpt-oss-120b":{"id":"venice/openai-gpt-oss-120b","name":"OpenAI GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-11-06","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.07,"output":0.3},"sourceProvider":"venice"},"venice/qwen-3-6-plus":{"id":"venice/qwen-3-6-plus","name":"Qwen 3.6 Plus Uncensored","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-06","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.625,"output":3.75,"cache_read":0.0625,"cache_write":0.78,"tiers":[{"input":2.5,"output":7.5,"cache_read":0.0625,"cache_write":0.78,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2.5,"output":7.5,"cache_read":0.0625,"cache_write":0.78}},"sourceProvider":"venice"},"venice/qwen-3-7-max":{"id":"venice/qwen-3-7-max","name":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-05-22","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.7,"output":8.05,"cache_read":0.27,"cache_write":3.35},"sourceProvider":"venice"},"venice/qwen-3-7-plus":{"id":"venice/qwen-3-7-plus","name":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.5,"output":2,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":1.5,"output":6,"cache_read":0.15,"cache_write":1.875,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.5,"output":6,"cache_read":0.15,"cache_write":1.875}},"sourceProvider":"venice"},"venice/qwen-3-8-2-4t-a95b":{"id":"venice/qwen-3-8-2-4t-a95b","name":"Qwen 3.8 2.4T","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.3125},"sourceProvider":"venice"},"venice/qwen-3-8-27b":{"id":"venice/qwen-3-8-27b","name":"Qwen 3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-17","last_updated":"2026-08-18","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.45,"output":3.2},"sourceProvider":"venice"},"venice/qwen-3-8-max":{"id":"venice/qwen-3-8-max","name":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-22","last_updated":"2026-07-19","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":2.5,"output":7.5,"cache_read":0.3125,"cache_write":3.125},"sourceProvider":"venice"},"venice/qwen3-235b-a22b-instruct-2507":{"id":"venice/qwen3-235b-a22b-instruct-2507","name":"Qwen 3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.75},"sourceProvider":"venice"},"venice/qwen3-235b-a22b-thinking-2507":{"id":"venice/qwen3-235b-a22b-thinking-2507","name":"Qwen 3 235B A22B Thinking 2507","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.45,"output":3.5},"sourceProvider":"venice"},"venice/qwen3-5-35b-a3b":{"id":"venice/qwen3-5-35b-a3b","name":"Qwen 3.5 35B A3B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-25","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.3125,"output":1.25,"cache_read":0.15625},"sourceProvider":"venice"},"venice/qwen3-5-397b-a17b":{"id":"venice/qwen3-5-397b-a17b","name":"Qwen 3.5 397B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-16","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.75,"output":4.5},"sourceProvider":"venice"},"venice/qwen3-5-9b":{"id":"venice/qwen3-5-9b","name":"Qwen 3.5 9B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-05","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.1,"output":0.15},"sourceProvider":"venice"},"venice/qwen3-6-27b":{"id":"venice/qwen3-6-27b","name":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-24","last_updated":"2026-06-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.325,"output":3.25},"sourceProvider":"venice"},"venice/qwen3-6-35b-a3b":{"id":"venice/qwen3-6-35b-a3b","name":"Qwen 3.6 35B A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-20","last_updated":"2026-07-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.1,"output":1},"sourceProvider":"venice"},"venice/qwen3-coder-480b-a35b-instruct-turbo":{"id":"venice/qwen3-coder-480b-a35b-instruct-turbo","name":"Qwen 3 Coder 480B Turbo","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-01-27","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"venice"},"venice/qwen3-next-80b":{"id":"venice/qwen3-next-80b","name":"Qwen 3 Next 80b","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2025-04-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":16384},"cost":{"input":0.35,"output":1.9},"sourceProvider":"venice"},"venice/qwen3-vl-235b-a22b":{"id":"venice/qwen3-vl-235b-a22b","name":"Qwen3 VL 235B","description":"Multimodal model for analyzing text, images, documents, and rich media","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-01-16","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.21,"output":1.9,"cache_read":0.1},"sourceProvider":"venice"},"venice/seed-2-1-turbo":{"id":"venice/seed-2-1-turbo","name":"Seed 2.1 Turbo","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-28","last_updated":"2026-07-24","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":65536},"cost":{"input":0.625,"output":3.125,"cache_read":0.125},"sourceProvider":"venice"},"venice/stealth-ox-alpha":{"id":"venice/stealth-ox-alpha","name":"Ox Alpha","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"alpha","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"venice"},"venice/venice-uncensored-1-2":{"id":"venice/venice-uncensored-1-2","name":"Venice Uncensored 1.2","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-04-01","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8192},"cost":{"input":0.2,"output":0.9},"sourceProvider":"venice"},"venice/venice-uncensored-role-play":{"id":"venice/venice-uncensored-role-play","name":"Venice Role Play Uncensored","description":"Multimodal model for analyzing text, images, documents, and rich media","family":"venice","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"release_date":"2026-02-20","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0.5,"output":2},"sourceProvider":"venice"},"venice/xiaomi-mimo-v2-5":{"id":"venice/xiaomi-mimo-v2-5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-06-11","last_updated":"2026-06-11","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65536},"cost":{"input":0.4,"output":2,"cache_read":0.08},"sourceProvider":"venice"},"venice/z-ai-glm-5-3":{"id":"venice/z-ai-glm-5-3","name":"GLM 5.3","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-18","last_updated":"2026-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.75,"output":5.5,"cache_read":0.325},"sourceProvider":"venice"},"venice/z-ai-glm-5-turbo":{"id":"venice/z-ai-glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-15","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":32768},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"venice"},"venice/z-ai-glm-5v-turbo":{"id":"venice/z-ai-glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-06-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32768},"cost":{"input":1.5,"output":5,"cache_read":0.3},"sourceProvider":"venice"},"venice/zai-org-glm-4.6":{"id":"venice/zai-org-glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2024-04-01","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.43,"output":1.75,"cache_read":0.08},"sourceProvider":"venice"},"venice/zai-org-glm-4.7":{"id":"venice/zai-org-glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-24","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":16384},"cost":{"input":0.55,"output":2.65,"cache_read":0.11},"sourceProvider":"venice"},"venice/zai-org-glm-4.7-flash":{"id":"venice/zai-org-glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-29","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"venice"},"venice/zai-org-glm-5":{"id":"venice/zai-org-glm-5","name":"GLM 5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-02-11","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":198000,"output":32000},"cost":{"input":1,"output":3.2,"cache_read":0.2},"sourceProvider":"venice"},"venice/zai-org-glm-5-1":{"id":"venice/zai-org-glm-5-1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-06-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":80000},"cost":{"input":1.54,"output":4.84,"cache_read":0.286},"sourceProvider":"venice"},"venice/zai-org-glm-5-2":{"id":"venice/zai-org-glm-5-2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"venice"},"vercel/alibaba/qwen-3-14b":{"id":"alibaba/qwen-3-14b","name":"Qwen3-14B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.24},"sourceProvider":"vercel"},"vercel/alibaba/qwen-3-235b":{"id":"alibaba/qwen-3-235b","name":"Qwen3 235B A22B Instruct 2507","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":16384},"cost":{"input":0.22,"output":0.88},"sourceProvider":"vercel"},"vercel/alibaba/qwen-3-30b":{"id":"alibaba/qwen-3-30b","name":"Qwen3-30B-A3B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":40960,"output":16384},"cost":{"input":0.12,"output":0.5},"sourceProvider":"vercel"},"vercel/alibaba/qwen-3-32b":{"id":"alibaba/qwen-3-32b","name":"Qwen 3.32B","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":38912}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-04-28","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.16,"output":0.64},"sourceProvider":"vercel"},"vercel/alibaba/qwen-3.6-max-preview":{"id":"alibaba/qwen-3.6-max-preview","name":"Qwen 3.6 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":240000,"output":64000},"cost":{"input":1.3,"output":7.8,"cache_read":0.26,"cache_write":1.625},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-235b-a22b-thinking":{"id":"alibaba/qwen3-235b-a22b-thinking","name":"Qwen3 235B A22B Thinking 2507","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-04","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":4},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-coder":{"id":"alibaba/qwen3-coder","name":"Qwen3 Coder 480B A35B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-22","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":65536},"cost":{"input":1.5,"output":7.5,"cache_read":0.3},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-coder-30b-a3b":{"id":"alibaba/qwen3-coder-30b-a3b","name":"Qwen 3 Coder 30B A3B Instruct","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-31","last_updated":"2025-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":8192},"cost":{"input":0.15,"output":0.6},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-coder-next":{"id":"alibaba/qwen3-coder-next","name":"Qwen3 Coder Next","description":"Qwen coding model for software agents, repository edits, and code reasoning","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-09","release_date":"2026-02-03","last_updated":"2026-02-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.2},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-coder-plus":{"id":"alibaba/qwen3-coder-plus","name":"Qwen3 Coder Plus","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":1,"output":5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-embedding-0.6b":{"id":"alibaba/qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-11-14","last_updated":"2025-11-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-embedding-4b":{"id":"alibaba/qwen3-embedding-4b","name":"Qwen3 Embedding 4B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-embedding-8b":{"id":"alibaba/qwen3-embedding-8b","name":"Qwen3 Embedding 8B","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"qwen","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-06-05","last_updated":"2025-06-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32768,"output":32768},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-max":{"id":"alibaba/qwen3-max","name":"Qwen3 Max","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":1.2,"output":6,"cache_read":0.24},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-max-preview":{"id":"alibaba/qwen3-max-preview","name":"Qwen3 Max Preview","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-05","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":32768},"cost":{"input":1.2,"output":6,"cache_read":0.24},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-max-thinking":{"id":"alibaba/qwen3-max-thinking","name":"Qwen 3 Max Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-23","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":65536},"cost":{"input":1.2,"output":6,"cache_read":0.24},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-next-80b-a3b-instruct":{"id":"alibaba/qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-next-80b-a3b-thinking":{"id":"alibaba/qwen3-next-80b-a3b-thinking","name":"Qwen3 Next 80B A3B Thinking","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09","last_updated":"2025-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.15,"output":1.2},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-vl-235b-a22b-instruct":{"id":"alibaba/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":129024},"cost":{"input":0.4,"output":1.6},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-vl-instruct":{"id":"alibaba/qwen3-vl-instruct","name":"Qwen3 VL Instruct","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-23","last_updated":"2025-09-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":129024},"cost":{"input":0.4,"output":1.6},"sourceProvider":"vercel"},"vercel/alibaba/qwen3-vl-thinking":{"id":"alibaba/qwen3-vl-thinking","name":"Qwen3 VL Thinking","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-09-23","last_updated":"2025-09-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.4,"output":4},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.5-flash":{"id":"alibaba/qwen3.5-flash","name":"Qwen 3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.1,"output":0.4,"cache_read":0.001,"cache_write":0.125},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.5-plus":{"id":"alibaba/qwen3.5-plus","name":"Qwen 3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":81920}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-02-16","last_updated":"2026-02-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.5},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.6-27b":{"id":"alibaba/qwen3.6-27b","name":"Qwen 3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":0.6,"output":3.6},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.6-plus":{"id":"alibaba/qwen3.6-plus","name":"Qwen 3.6 Plus","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":131072}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.1,"cache_write":0.625},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.7-flash":{"id":"alibaba/qwen3.7-flash","name":"Qwen 3.7 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.7-max":{"id":"alibaba/qwen3.7-max","name":"Qwen 3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":991000,"output":64000},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.7-plus":{"id":"alibaba/qwen3.7-plus","name":"Qwen 3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":262144}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.8-2.4t-a95b":{"id":"alibaba/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":2,"output":6,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.8-27b":{"id":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.55,"output":3.3,"cache_read":0.11},"sourceProvider":"vercel"},"vercel/alibaba/qwen3.8-max":{"id":"alibaba/qwen3.8-max","name":"Qwen 3.8 Max","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","xhigh"]},{"type":"budget_tokens","min":0,"max":262144}],"tool_call":true,"temperature":true,"release_date":"2026-07-19","last_updated":"2026-07-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":6,"cache_read":0.25,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.5-t2v-preview":{"id":"alibaba/wan-v2.5-t2v-preview","name":"Wan v2.5 Text-to-Video Preview","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-24","last_updated":"2025-09-24","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.6-i2v":{"id":"alibaba/wan-v2.6-i2v","name":"Wan v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.6-i2v-flash":{"id":"alibaba/wan-v2.6-i2v-flash","name":"Wan v2.6 Image-to-Video Flash","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.6-r2v":{"id":"alibaba/wan-v2.6-r2v","name":"Wan v2.6 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.6-r2v-flash":{"id":"alibaba/wan-v2.6-r2v-flash","name":"Wan v2.6 Reference-to-Video Flash","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.6-t2v":{"id":"alibaba/wan-v2.6-t2v","name":"Wan v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.7-r2v":{"id":"alibaba/wan-v2.7-r2v","name":"Wan v2.7 Reference-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/alibaba/wan-v2.7-t2v":{"id":"alibaba/wan-v2.7-t2v","name":"Wan v2.7 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/amazon/nova-2-lite":{"id":"amazon/nova-2-lite","name":"Nova 2 Lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"nova","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2024-12-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.3,"output":2.5,"cache_read":0.075},"sourceProvider":"vercel"},"vercel/amazon/nova-lite":{"id":"amazon/nova-lite","name":"Nova Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-lite","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.06,"output":0.24,"cache_read":0.015},"sourceProvider":"vercel"},"vercel/amazon/nova-micro":{"id":"amazon/nova-micro","name":"Nova Micro","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"nova-micro","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.035,"output":0.14,"cache_read":0.00875},"sourceProvider":"vercel"},"vercel/amazon/nova-pro":{"id":"amazon/nova-pro","name":"Nova Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"nova-pro","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-12-03","last_updated":"2024-12-03","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":300000,"output":8192},"cost":{"input":0.8,"output":3.2,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/amazon/titan-embed-text-v2":{"id":"amazon/titan-embed-text-v2","name":"Titan Text Embeddings V2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"titan-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-30","last_updated":"2024-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/anthropic/claude-3-haiku":{"id":"anthropic/claude-3-haiku","name":"Claude Haiku 3","description":"Legacy model retained for compatibility with older integrations","family":"claude-haiku","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-08-31","release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":4096},"cost":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"sourceProvider":"vercel"},"vercel/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"vercel"},"vercel/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8192},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-05","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-05","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-4.8-fast":{"id":"anthropic/claude-opus-4.8-fast","name":"Claude Opus 4.8 (Fast)","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-5":{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vercel"},"vercel/anthropic/claude-opus-5-fast":{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5 (Fast)","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":false,"knowledge":"2026-05","release_date":"2026-07-24","last_updated":"2026-07-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"vercel"},"vercel/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-03-31","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":8192},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"vercel"},"vercel/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":1024}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-07-31","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"vercel"},"vercel/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]},{"type":"budget_tokens","min":1024}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75,"tiers":[{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":6,"output":22.5,"cache_read":0.6,"cache_write":7.5}},"sourceProvider":"vercel"},"vercel/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/arcee-ai/trinity-large-thinking":{"id":"arcee-ai/trinity-large-thinking","name":"Trinity Large Thinking","description":"Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use","family":"trinity","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-03","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262100,"output":80000},"cost":{"input":0.25,"output":0.8999999999999999},"sourceProvider":"vercel"},"vercel/arcee-ai/trinity-mini":{"id":"arcee-ai/trinity-mini","name":"Trinity Mini","description":"Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads","family":"trinity","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-01","last_updated":"2025-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.045,"output":0.15},"sourceProvider":"vercel"},"vercel/bfl/flux-2-flex":{"id":"bfl/flux-2-flex","name":"FLUX.2 [flex]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-2-klein-4b":{"id":"bfl/flux-2-klein-4b","name":"FLUX.2 [klein] 4B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-2-klein-9b":{"id":"bfl/flux-2-klein-9b","name":"FLUX.2 [klein] 9B","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-2-max":{"id":"bfl/flux-2-max","name":"FLUX.2 [max]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":67300,"output":67300},"sourceProvider":"vercel"},"vercel/bfl/flux-2-pro":{"id":"bfl/flux-2-pro","name":"FLUX.2 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":67300,"output":67300},"sourceProvider":"vercel"},"vercel/bfl/flux-3-video":{"id":"bfl/flux-3-video","name":"Flux 3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-08-04","last_updated":"2026-08-04","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-kontext-max":{"id":"bfl/flux-kontext-max","name":"FLUX.1 Kontext Max","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-kontext-pro":{"id":"bfl/flux-kontext-pro","name":"FLUX.1 Kontext Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-29","last_updated":"2025-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-pro-1.0-fill":{"id":"bfl/flux-pro-1.0-fill","name":"FLUX.1 Fill [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-01","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-pro-1.1":{"id":"bfl/flux-pro-1.1","name":"FLUX1.1 [pro]","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-02","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/bfl/flux-pro-1.1-ultra":{"id":"bfl/flux-pro-1.1-ultra","name":"FLUX1.1 [pro] Ultra","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-11-01","last_updated":"2024-11","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seed-1.6":{"id":"bytedance/seed-1.6","name":"Seed 1.6","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-01","last_updated":"2025-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/bytedance/seed-1.8":{"id":"bytedance/seed-1.8","name":"Seed 1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"seed","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-09-01","last_updated":"2025-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.25,"output":2,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/bytedance/seedance-2.0":{"id":"bytedance/seedance-2.0","name":"Seedance 2.0","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedance-2.0-fast":{"id":"bytedance/seedance-2.0-fast","name":"Seedance 2.0 Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-14","last_updated":"2026-04-14","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedance-2.5":{"id":"bytedance/seedance-2.5","name":"Seedance 2.5","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedance-v1.0-pro":{"id":"bytedance/seedance-v1.0-pro","name":"Seedance v1.0 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-06-11","last_updated":"2025-06-11","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedance-v1.0-pro-fast":{"id":"bytedance/seedance-v1.0-pro-fast","name":"Seedance v1.0 Pro Fast","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-24","last_updated":"2025-10-31","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedance-v1.5-pro":{"id":"bytedance/seedance-v1.5-pro","name":"Seedance v1.5 Pro","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-16","last_updated":"2025-12-16","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedream-4.0":{"id":"bytedance/seedream-4.0","name":"Seedream 4.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-09","last_updated":"2025-08-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedream-4.5":{"id":"bytedance/seedream-4.5","name":"Seedream 4.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-11-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedream-5.0-lite":{"id":"bytedance/seedream-5.0-lite","name":"Seedream 5.0 Lite","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/bytedance/seedream-5.0-pro":{"id":"bytedance/seedream-5.0-pro","name":"Seedream 5.0 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"seed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-07-11","last_updated":"2026-07-11","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/cohere/command-a":{"id":"cohere/command-a","name":"Command A","description":"Cohere command model for multilingual enterprise agents, tools, and chat","family":"command","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-03-13","last_updated":"2025-03-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":8000},"cost":{"input":2.5,"output":10},"sourceProvider":"vercel"},"vercel/cohere/embed-v4.0":{"id":"cohere/embed-v4.0","name":"Embed v4.0","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"cohere-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-15","last_updated":"2025-04-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":1536},"sourceProvider":"vercel"},"vercel/cohere/rerank-v3.5":{"id":"cohere/rerank-v3.5","name":"Cohere Rerank 3.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-12-02","last_updated":"2024-12-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":4096,"output":4096},"sourceProvider":"vercel"},"vercel/cohere/rerank-v4-fast":{"id":"cohere/rerank-v4-fast","name":"Cohere Rerank 4 Fast","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"sourceProvider":"vercel"},"vercel/cohere/rerank-v4-pro":{"id":"cohere/rerank-v4-pro","name":"Cohere Rerank 4 Pro","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-r1":{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-01-20","last_updated":"2025-05-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":32768},"cost":{"input":1.35,"output":5.4},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v3":{"id":"deepseek/deepseek-v3","name":"DeepSeek V3 0324","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2024-12-26","last_updated":"2024-12-26","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":163840},"cost":{"input":0.27,"output":1.12,"cache_read":0.135},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v3.1":{"id":"deepseek/deepseek-v3.1","name":"DeepSeek-V3.1","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":163840,"output":128000},"cost":{"input":0.25,"output":0.95,"cache_read":0.13},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v3.1-terminus":{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek V3.1 Terminus","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-09-22","last_updated":"2025-09-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":65536},"cost":{"input":0.27,"output":1,"cache_read":0.135},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":false,"tool_call":false,"structured_output":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":8000},"cost":{"input":0.28,"output":0.42,"cache_read":0.028},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v3.2-thinking":{"id":"deepseek/deepseek-v3.2-thinking","name":"DeepSeek V3.2 Thinking","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8000},"cost":{"input":0.62,"output":1.85},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.13,"output":0.26,"cache_read":0.028},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v4-flash-0731":{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.076,"output":0.153,"cache_read":0.014},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v4-flash-vision-exp":{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","family":"deepseek-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-21","last_updated":"2026-08-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"cost":{"input":0.22,"output":0.66,"cache_read":0.007},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048600,"output":1048600},"cost":{"input":1.74,"output":3.48,"cache_read":0.14},"sourceProvider":"vercel"},"vercel/deepseek/deepseek-v4-pro-0813":{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-12","last_updated":"2026-08-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":1.32,"output":3.96,"cache_read":0.132},"sourceProvider":"vercel"},"vercel/fish-audio/s1":{"id":"fish-audio/s1","name":"S1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/s1-free":{"id":"fish-audio/s1-free","name":"S1 (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2025-10-20","last_updated":"2025-10-20","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/s2-pro":{"id":"fish-audio/s2-pro","name":"S2 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/s2-pro-free":{"id":"fish-audio/s2-pro-free","name":"S2 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/s2.1-pro":{"id":"fish-audio/s2.1-pro","name":"S2.1 Pro","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-07-28","last_updated":"2026-07-28","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/s2.1-pro-free":{"id":"fish-audio/s2.1-pro-free","name":"S2.1 Pro (Free)","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-07-28","last_updated":"2026-07-28","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/transcribe-1":{"id":"fish-audio/transcribe-1","name":"Transcribe-1","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/fish-audio/transcribe-1-free":{"id":"fish-audio/transcribe-1-free","name":"Transcribe-1 (Free)","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-01","last_updated":"2026-03-01","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":0,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03,"input_audio":1},"sourceProvider":"vercel"},"vercel/google/gemini-2.5-flash-image":{"id":"google/gemini-2.5-flash-image","name":"Nano Banana (Gemini 2.5 Flash Image)","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":32768,"output":65536},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":512,"max":24576}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.1,"output":0.4,"cache_read":0.01},"sourceProvider":"vercel"},"vercel/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"budget_tokens","min":128,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.25,"output":10,"cache_read":0.125,"tiers":[{"input":2.5,"output":15,"cache_read":0.25,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":15,"cache_read":0.25}},"sourceProvider":"vercel"},"vercel/google/gemini-3-flash":{"id":"google/gemini-3-flash","name":"Gemini 3 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-03","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/google/gemini-3-pro-image":{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":32768},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/google/gemini-3.1-flash-image":{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/google/gemini-3.1-flash-image-preview":{"id":"google/gemini-3.1-flash-image-preview","name":"Gemini 3.1 Flash Image Preview (Nano Banana 2)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":131072,"output":32768},"cost":{"input":0.5,"output":3,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.25,"output":1.5,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/google/gemini-3.1-flash-lite-image":{"id":"google/gemini-3.1-flash-lite-image","name":"Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image"],"output":["text","image"]},"open_weights":false,"limit":{"context":65536,"output":4096},"cost":{"input":0.25,"output":1.5,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/google/gemini-3.5-flash-lite":{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65000},"cost":{"input":0.3,"output":2.5,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/google/gemini-3.6-flash":{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"vercel"},"vercel/google/gemini-3.7-flash":{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-03","release_date":"2026-08-13","last_updated":"2026-08-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":0.75,"output":3.75,"cache_read":0.075},"sourceProvider":"vercel"},"vercel/google/gemini-embedding-001":{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-05","release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/google/gemini-embedding-2":{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2025-11","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/gemini-omni-flash-preview":{"id":"google/gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","description":"Omni-modal model for text, vision, audio, and multimodal agent tasks","family":"gemini","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":57920},"cost":{"input":1.5,"output":9},"sourceProvider":"vercel"},"vercel/google/gemma-4-26b-a4b-it":{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.6,"cache_read":0.015},"sourceProvider":"vercel"},"vercel/google/gemma-4-31b-it":{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","family":"gemma","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.14,"output":0.4},"sourceProvider":"vercel"},"vercel/google/text-embedding-005":{"id":"google/text-embedding-005","name":"Text Embedding 005","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-08-01","last_updated":"2024-08","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/google/text-multilingual-embedding-002":{"id":"google/text-multilingual-embedding-002","name":"Text Multilingual Embedding 002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-03-01","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/google/veo-3.0-fast-generate-001":{"id":"google/veo-3.0-fast-generate-001","name":"Veo 3.0 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-07-31","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/veo-3.0-generate-001":{"id":"google/veo-3.0-generate-001","name":"Veo 3.0","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/veo-3.1-fast-generate-001":{"id":"google/veo-3.1-fast-generate-001","name":"Veo 3.1 Fast Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/veo-3.1-generate-001":{"id":"google/veo-3.1-generate-001","name":"Veo 3.1","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-15","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/google/veo-3.1-lite-generate-001":{"id":"google/veo-3.1-lite-generate-001","name":"Veo 3.1 Lite Generate","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"veo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/inception/mercury-2":{"id":"inception/mercury-2","name":"Mercury 2","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","family":"mercury","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-02-24","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.25,"output":0.75,"cache_read":0.024999999999999998},"sourceProvider":"vercel"},"vercel/inception/mercury-coder-small":{"id":"inception/mercury-coder-small","name":"Mercury Coder Small Beta","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"mercury","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-02-26","last_updated":"2025-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":16384},"cost":{"input":0.25,"output":1},"sourceProvider":"vercel"},"vercel/inclusionai/ling-3.0-flash":{"id":"inclusionai/ling-3.0-flash","name":"Ling 3.0 Flash","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"ling","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-08-06","last_updated":"2026-08-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.06,"output":0.18,"cache_read":0.012},"sourceProvider":"vercel"},"vercel/interfaze/interfaze-beta":{"id":"interfaze/interfaze-beta","name":"Interfaze Beta","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":false,"temperature":true,"release_date":"2025-10-07","last_updated":"2026-04-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":32000},"cost":{"input":1.5,"output":3.5},"sourceProvider":"vercel"},"vercel/klingai/kling-v2.5-turbo-i2v":{"id":"klingai/kling-v2.5-turbo-i2v","name":"Kling v2.5 Turbo Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v2.5-turbo-t2v":{"id":"klingai/kling-v2.5-turbo-t2v","name":"Kling v2.5 Turbo Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v2.6-i2v":{"id":"klingai/kling-v2.6-i2v","name":"Kling v2.6 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v2.6-motion-control":{"id":"klingai/kling-v2.6-motion-control","name":"Kling v2.6 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-18","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v2.6-t2v":{"id":"klingai/kling-v2.6-t2v","name":"Kling v2.6 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-12-03","last_updated":"2025-12-21","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v3.0-i2v":{"id":"klingai/kling-v3.0-i2v","name":"Kling v3.0 Image-to-Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v3.0-motion-control":{"id":"klingai/kling-v3.0-motion-control","name":"Kling v3.0 Motion Control","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-03-04","last_updated":"2026-03-04","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/klingai/kling-v3.0-t2v":{"id":"klingai/kling-v3.0-t2v","name":"Kling v3.0 Text-to-Video","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"ling","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/kwaipilot/kat-coder-air-v2.5":{"id":"kwaipilot/kat-coder-air-v2.5","name":"Kat Coder Air V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.15,"output":0.6,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/kwaipilot/kat-coder-pro-v1":{"id":"kwaipilot/kat-coder-pro-v1","name":"KAT-Coder-Pro V1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-11-09","last_updated":"2025-10-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"vercel"},"vercel/kwaipilot/kat-coder-pro-v2":{"id":"kwaipilot/kat-coder-pro-v2","name":"Kat Coder Pro V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"vercel"},"vercel/kwaipilot/kat-coder-pro-v2.5":{"id":"kwaipilot/kat-coder-pro-v2.5","name":"Kat Coder Pro V2.5","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"kat-coder","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-07-10","last_updated":"2026-07-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.74,"output":2.96,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/meta/llama-3.1-70b":{"id":"meta/llama-3.1-70b","name":"Llama 3.1 70B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.72,"output":0.72},"sourceProvider":"vercel"},"vercel/meta/llama-3.1-8b":{"id":"meta/llama-3.1-8b","name":"Llama 3.1 8B Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":8192},"cost":{"input":0.22,"output":0.22},"sourceProvider":"vercel"},"vercel/meta/llama-3.3-70b":{"id":"meta/llama-3.3-70b","name":"Llama-3.3-70B-Instruct","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/meta/llama-4-maverick":{"id":"meta/llama-4-maverick","name":"Llama-4-Maverick-17B-128E-Instruct-FP8","description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/meta/llama-4-scout":{"id":"meta/llama-4-scout","name":"Llama-4-Scout-17B-16E-Instruct-FP8","description":"Open multimodal Llama model for long-context analysis and efficient agents","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":4096},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-01-04","release_date":"2026-08-10","last_updated":"2026-08-10","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.35,"output":1.5,"cache_read":0.04},"sourceProvider":"vercel"},"vercel/meta/muse-spark-1.1":{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"muse","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-08","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/meta/muse-spark-1.2":{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.25,"output":4.25,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/meta/muse-spark-1.2-contributor":{"id":"meta/muse-spark-1.2-contributor","name":"Muse Spark 1.2 Contributor","description":"Open Llama multimodal model for image understanding and text reasoning","family":"muse","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-08-05","last_updated":"2026-08-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.1,"output":0.2,"cache_read":0.002},"sourceProvider":"vercel"},"vercel/minimax/minimax-h3":{"id":"minimax/minimax-h3","name":"MiniMax H3","description":"Video model for prompt-guided generation, editing, and motion workflows","family":"minimax","attachment":true,"reasoning":false,"tool_call":false,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"Efficient open MiniMax model built for coding agents and tool-heavy workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":205000,"output":205000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"Earlier MiniMax agent model for practical coding and productivity tasks","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.1-lightning":{"id":"minimax/minimax-m2.1-lightning","name":"MiniMax M2.1 Lightning","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-23","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":2.4,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"Prior MiniMax coding model for agent workflows, office edits, and automation","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.5-highspeed":{"id":"minimax/minimax-m2.5-highspeed","name":"MiniMax M2.5 High Speed","description":"High-speed MiniMax model for low-latency coding and agent workflows","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.6,"output":2.4,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"Minimax M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 High Speed","description":"Low-latency M2.7 variant for interactive coding plans and agent loops","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131100},"cost":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0.375},"sourceProvider":"vercel"},"vercel/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"vercel"},"vercel/mistral/codestral":{"id":"mistral/codestral","name":"Codestral (latest)","description":"Mistral code model for completions, refactors, and developer IDE workflows","family":"codestral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-05-29","last_updated":"2025-01-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":4096},"cost":{"input":0.3,"output":0.9},"sourceProvider":"vercel"},"vercel/mistral/codestral-embed":{"id":"mistral/codestral-embed","name":"Codestral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"codestral-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-28","last_updated":"2025-05-28","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/mistral/devstral-2":{"id":"mistral/devstral-2","name":"Devstral 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-09","last_updated":"2025-12-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.4,"output":2},"sourceProvider":"vercel"},"vercel/mistral/devstral-small-2":{"id":"mistral/devstral-small-2","name":"Devstral Small 2","description":"Mistral coding agent model for repository tasks and software engineering workflows","family":"devstral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-09","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"vercel"},"vercel/mistral/magistral-medium":{"id":"mistral/magistral-medium","name":"Magistral Medium (latest)","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-medium","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":16384},"cost":{"input":2,"output":5},"sourceProvider":"vercel"},"vercel/mistral/magistral-small":{"id":"mistral/magistral-small","name":"Magistral Small","description":"Mistral reasoning model for transparent analysis, math, and complex decisions","family":"magistral-small","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"vercel"},"vercel/mistral/ministral-14b":{"id":"mistral/ministral-14b","name":"Ministral 14B","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2025-12-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.2,"output":0.2},"sourceProvider":"vercel"},"vercel/mistral/ministral-3b":{"id":"mistral/ministral-3b","name":"Ministral 3B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.04,"output":0.04},"sourceProvider":"vercel"},"vercel/mistral/ministral-8b":{"id":"mistral/ministral-8b","name":"Ministral 8B (latest)","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","family":"ministral","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2024-10-01","last_updated":"2024-10-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.1,"output":0.1},"sourceProvider":"vercel"},"vercel/mistral/mistral-embed":{"id":"mistral/mistral-embed","name":"Mistral Embed","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"mistral-embed","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2023-12-11","last_updated":"2023-12-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/mistral/mistral-large-3":{"id":"mistral/mistral-large-3","name":"Mistral Large 3","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","family":"mistral-large","attachment":true,"reasoning":false,"tool_call":false,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-02","last_updated":"2025-12-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.5,"output":1.5},"sourceProvider":"vercel"},"vercel/mistral/mistral-medium":{"id":"mistral/mistral-medium","name":"Mistral Medium 3.1","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-05-07","last_updated":"2025-05-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.4,"output":2},"sourceProvider":"vercel"},"vercel/mistral/mistral-medium-3.5":{"id":"mistral/mistral-medium-3.5","name":"Mistral Medium Latest","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-medium","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-05-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1.5,"output":7.5},"sourceProvider":"vercel"},"vercel/mistral/mistral-nemo":{"id":"mistral/mistral-nemo","name":"Mistral Nemo","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","family":"mistral-nemo","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-04","release_date":"2024-07-18","last_updated":"2024-07-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":128000},"cost":{"input":0.15,"output":0.15},"sourceProvider":"vercel"},"vercel/mistral/mistral-small":{"id":"mistral/mistral-small","name":"Mistral Small (latest)","description":"Efficient Mistral model for fast chat, extraction, and production assistants","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-06","release_date":"2024-09-17","last_updated":"2026-03-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":32000,"output":4000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"vercel"},"vercel/mistral/pixtral-12b":{"id":"mistral/pixtral-12b","name":"Pixtral 12B","description":"Mistral vision-language model for image understanding and multimodal chat","family":"pixtral","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-09","release_date":"2024-09-01","last_updated":"2024-09-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.15,"output":0.15},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2":{"id":"moonshotai/kimi-k2","name":"Kimi K2 Instruct","description":"Kimi model for long-context chat, coding, and agentic reasoning","family":"kimi-k2","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-07-11","last_updated":"2025-09-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"output":131072},"cost":{"input":0.57,"output":2.3},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","family":"kimi-thinking","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":216144,"output":216144},"cost":{"input":0.47,"output":2,"cache_read":0.141},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01","last_updated":"2026-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262114,"output":262114},"cost":{"input":0.6,"output":3,"cache_read":0.1},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":262000},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0.95,"output":4,"cache_read":0.19},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k2.7-code-highspeed":{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code High Speed","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":32768},"cost":{"input":1.9,"output":8,"cache_read":0.38},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"vercel"},"vercel/moonshotai/kimi-k3-fast":{"id":"moonshotai/kimi-k3-fast","name":"Kimi K3 Fast","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":4.5,"output":22.5,"cache_read":0.45},"sourceProvider":"vercel"},"vercel/morph/morph-v3-fast":{"id":"morph/morph-v3-fast","name":"Morph v3 Fast","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16000,"output":16000},"cost":{"input":0.8,"output":1.2},"sourceProvider":"vercel"},"vercel/morph/morph-v3-large":{"id":"morph/morph-v3-large","name":"Morph v3 Large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"morph","attachment":false,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2024-08-15","last_updated":"2024-08-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"cost":{"input":0.9,"output":1.9},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-3-nano-30b-a3b":{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"temperature":true,"release_date":"2025-12-15","last_updated":"2025-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.05,"output":0.24},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA Nemotron 3 Super 120B A12B","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":false,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32000},"cost":{"input":0.15,"output":0.65},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":65000},"cost":{"input":0.6,"output":2.4,"cache_read":0.12},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-3.5-lightning":{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-3.5-lightning-free":{"id":"nvidia/nemotron-3.5-lightning-free","name":"Nemotron 3.5 Lightning 30B (Free)","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"budget_tokens","min":1,"max":32768}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-nano-12b-v2-vl":{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nvidia Nemotron Nano 12B V2 VL","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","family":"nemotron","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-10-28","last_updated":"2025-10-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.2,"output":0.6},"sourceProvider":"vercel"},"vercel/nvidia/nemotron-nano-9b-v2":{"id":"nvidia/nemotron-nano-9b-v2","name":"Nvidia Nemotron Nano 9B V2","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2025-08-18","last_updated":"2025-08-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.06,"output":0.23},"sourceProvider":"vercel"},"vercel/openai/gpt-3.5-turbo":{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2021-09","release_date":"2023-03-01","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":16385,"input":12289,"output":4096},"cost":{"input":0.5,"output":1.5},"sourceProvider":"vercel"},"vercel/openai/gpt-4-turbo":{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2023-12","release_date":"2023-11-06","last_updated":"2024-04-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":4096},"status":"deprecated","cost":{"input":10,"output":30},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1":{"id":"openai/gpt-4.1","name":"GPT-4.1","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1-fast":{"id":"openai/gpt-4.1-fast","name":"GPT-4.1 (Fast)","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":3.5,"output":14,"cache_read":0.875},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1-mini":{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"cost":{"input":0.4,"output":1.6,"cache_read":0.1},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1-mini-fast":{"id":"openai/gpt-4.1-mini-fast","name":"GPT-4.1 mini (Fast)","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":0.7,"output":2.8,"cache_read":0.175},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1-nano":{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"output":32768},"status":"deprecated","cost":{"input":0.1,"output":0.4,"cache_read":0.025},"sourceProvider":"vercel"},"vercel/openai/gpt-4.1-nano-fast":{"id":"openai/gpt-4.1-nano-fast","name":"GPT-4.1 nano (Fast)","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","family":"gpt-nano","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-04","release_date":"2025-04-14","last_updated":"2025-04-14","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1047576,"input":1014808,"output":32768},"cost":{"input":0.2,"output":0.8,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/openai/gpt-4o":{"id":"openai/gpt-4o","name":"GPT-4o","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":2.5,"output":10,"cache_read":1.25},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-fast":{"id":"openai/gpt-4o-fast","name":"GPT-4o (Fast)","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","family":"gpt","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-05-13","last_updated":"2024-08-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":4.25,"output":17,"cache_read":2.125},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-mini":{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16384},"cost":{"input":0.15,"output":0.6,"cache_read":0.075},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-mini-fast":{"id":"openai/gpt-4o-mini-fast","name":"GPT-4o mini (Fast)","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","family":"gpt-mini","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-09","release_date":"2024-07-18","last_updated":"2024-07-18","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":0.25,"output":1,"cache_read":0.125},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-mini-search-preview":{"id":"openai/gpt-4o-mini-search-preview","name":"GPT 4o Mini Search Preview","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":false,"reasoning":false,"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2023-09","release_date":"2025-03-12","last_updated":"2025-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"input":111616,"output":16384},"cost":{"input":0.15,"output":0.6},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-mini-transcribe":{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o mini Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"o-mini","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":1.25,"output":5},"sourceProvider":"vercel"},"vercel/openai/gpt-4o-transcribe":{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03-13","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":2.5,"output":10},"sourceProvider":"vercel"},"vercel/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"vercel"},"vercel/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-09-15","last_updated":"2025-09-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"vercel"},"vercel/openai/gpt-5-fast":{"id":"openai/gpt-5-fast","name":"GPT-5 (Fast)","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5-mini":{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.025},"sourceProvider":"vercel"},"vercel/openai/gpt-5-mini-fast":{"id":"openai/gpt-5-mini-fast","name":"GPT-5 mini (Fast)","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.45,"output":3.6,"cache_read":0.045},"sourceProvider":"vercel"},"vercel/openai/gpt-5-nano":{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.05,"output":0.4,"cache_read":0.005},"sourceProvider":"vercel"},"vercel/openai/gpt-5-pro":{"id":"openai/gpt-5-pro","name":"GPT-5 pro","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":128000,"output":272000},"cost":{"input":15,"output":120},"sourceProvider":"vercel"},"vercel/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1-Codex","description":"Codex GPT for repository edits, code review, and practical software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.13},"sourceProvider":"vercel"},"vercel/openai/gpt-5.1-codex-max":{"id":"openai/gpt-5.1-codex-max","name":"GPT 5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"vercel"},"vercel/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/openai/gpt-5.1-thinking":{"id":"openai/gpt-5.1-thinking","name":"GPT 5.1 Thinking","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-11-12","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text","image"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"vercel"},"vercel/openai/gpt-5.1-thinking-fast":{"id":"openai/gpt-5.1-thinking-fast","name":"GPT 5.1 Thinking (Fast)","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2025-11-12","last_updated":"2025-11-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":2.5,"output":20,"cache_read":0.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"vercel"},"vercel/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2-Codex","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"vercel"},"vercel/openai/gpt-5.2-fast":{"id":"openai/gpt-5.2-fast","name":"GPT 5.2 (Fast)","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":3.5,"output":28,"cache_read":0.35},"sourceProvider":"vercel"},"vercel/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT 5.2 ","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":21,"output":168},"sourceProvider":"vercel"},"vercel/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT 5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"vercel"},"vercel/openai/gpt-5.3-codex-fast":{"id":"openai/gpt-5.3-codex-fast","name":"GPT 5.3 Codex (Fast)","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-05","last_updated":"2026-02-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":3.5,"output":28,"cache_read":0.35},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT 5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4-fast":{"id":"openai/gpt-5.4-fast","name":"GPT 5.4 (Fast)","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT 5.4 Mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4-mini-fast":{"id":"openai/gpt-5.4-mini-fast","name":"GPT 5.4 Mini (Fast)","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT 5.4 Nano","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"vercel"},"vercel/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT 5.4 Pro","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":false,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"vercel"},"vercel/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT 5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/openai/gpt-5.5-fast":{"id":"openai/gpt-5.5-fast","name":"GPT 5.5 (Fast)","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":12.5,"output":75,"cache_read":1.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT 5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"input":872000,"output":128000},"cost":{"input":30,"output":180},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.2,"output":1.2,"cache_read":0.02,"cache_write":0.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-luna-fast":{"id":"openai/gpt-5.6-luna-fast","name":"GPT 5.6 Luna (Fast)","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":0.4,"output":2.4,"cache_read":0.04,"cache_write":0.25},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-sol-fast":{"id":"openai/gpt-5.6-sol-fast","name":"GPT 5.6 Sol (Fast)","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":20,"cache_read":0.4,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/openai/gpt-5.6-terra-fast":{"id":"openai/gpt-5.6-terra-fast","name":"GPT 5.6 Terra (Fast)","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":4,"output":24,"cache_read":0.4,"cache_write":2.5},"sourceProvider":"vercel"},"vercel/openai/gpt-image-1":{"id":"openai/gpt-image-1","name":"GPT Image 1","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","family":"gpt-image","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-04-24","last_updated":"2025-04-24","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":40,"cache_read":1.25},"sourceProvider":"vercel"},"vercel/openai/gpt-image-1-mini":{"id":"openai/gpt-image-1-mini","name":"GPT Image 1 Mini","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-06","last_updated":"2025-10-06","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":2,"output":8,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/openai/gpt-image-1.5":{"id":"openai/gpt-image-1.5","name":"GPT Image 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-11-25","last_updated":"2025-11-25","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":32,"cache_read":1.25},"sourceProvider":"vercel"},"vercel/openai/gpt-image-2":{"id":"openai/gpt-image-2","name":"GPT Image 2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gpt-image","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":5,"output":30,"cache_read":1.25},"sourceProvider":"vercel"},"vercel/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.1,"output":0.5},"sourceProvider":"vercel"},"vercel/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"input":122880,"output":8192},"cost":{"input":0.05,"output":0.2},"sourceProvider":"vercel"},"vercel/openai/gpt-oss-safeguard-20b":{"id":"openai/gpt-oss-safeguard-20b","name":"gpt-oss-safeguard-20b","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-10-29","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":131072,"input":65536,"output":65536},"cost":{"input":0.075,"output":0.3,"cache_read":0.037},"sourceProvider":"vercel"},"vercel/openai/gpt-realtime-1.5":{"id":"openai/gpt-realtime-1.5","name":"GPT-Realtime-1.5","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-23","last_updated":"2026-02-23","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":4,"output":16,"cache_read":0.4},"sourceProvider":"vercel"},"vercel/openai/gpt-realtime-2":{"id":"openai/gpt-realtime-2","name":"gpt-realtime-2","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":4,"output":24,"cache_read":0.4},"sourceProvider":"vercel"},"vercel/openai/gpt-realtime-2.1":{"id":"openai/gpt-realtime-2.1","name":"gpt-realtime-2.1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high","xhigh"]}],"tool_call":false,"structured_output":false,"temperature":true,"knowledge":"2024-09-30","release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":128000,"input":96000,"output":32000},"cost":{"input":4,"output":24,"cache_read":0.4},"sourceProvider":"vercel"},"vercel/openai/gpt-realtime-mini":{"id":"openai/gpt-realtime-mini","name":"GPT-Realtime mini","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gpt","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-10-10","last_updated":"2025-10-10","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":0,"output":0},"cost":{"input":0.6,"output":2.4,"cache_read":0.06},"sourceProvider":"vercel"},"vercel/openai/gpt-realtime-whisper":{"id":"openai/gpt-realtime-whisper","name":"gpt-realtime-whisper","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/openai/o1":{"id":"openai/o1","name":"o1","description":"O-series reasoning model for hard analysis, math, coding, and planning","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2023-09","release_date":"2024-12-05","last_updated":"2024-12-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":15,"output":60,"cache_read":7.5},"sourceProvider":"vercel"},"vercel/openai/o3":{"id":"openai/o3","name":"o3","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/openai/o3-deep-research":{"id":"openai/o3-deep-research","name":"o3-deep-research","description":"Research model for long-horizon investigation, synthesis, and analytical reports","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium"]}],"tool_call":true,"temperature":true,"knowledge":"2024-05","release_date":"2024-06-26","last_updated":"2024-06-26","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":10,"output":40,"cache_read":2.5},"sourceProvider":"vercel"},"vercel/openai/o3-fast":{"id":"openai/o3-fast","name":"o3 (Fast)","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","family":"o","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":3.5,"output":14,"cache_read":0.875},"sourceProvider":"vercel"},"vercel/openai/o3-mini":{"id":"openai/o3-mini","name":"o3-mini","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","family":"o-mini","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2024-12-20","last_updated":"2025-01-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.55},"sourceProvider":"vercel"},"vercel/openai/o3-pro":{"id":"openai/o3-pro","name":"o3 Pro","description":"High-effort o3 tier for difficult technical reasoning and careful answers","family":"o-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-10","release_date":"2025-06-10","last_updated":"2025-06-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":20,"output":80},"sourceProvider":"vercel"},"vercel/openai/o4-mini":{"id":"openai/o4-mini","name":"o4-mini","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":100000},"status":"deprecated","cost":{"input":1.1,"output":4.4,"cache_read":0.275},"sourceProvider":"vercel"},"vercel/openai/o4-mini-fast":{"id":"openai/o4-mini-fast","name":"o4-mini (Fast)","description":"Fast o-series model for compact reasoning, coding, and tool use","family":"o-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-05","release_date":"2025-04-16","last_updated":"2025-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"input":100000,"output":100000},"cost":{"input":2,"output":8,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/openai/text-embedding-3-large":{"id":"openai/text-embedding-3-large","name":"text-embedding-3-large","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"sourceProvider":"vercel"},"vercel/openai/text-embedding-3-small":{"id":"openai/text-embedding-3-small","name":"text-embedding-3-small","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-01-25","last_updated":"2024-01-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"sourceProvider":"vercel"},"vercel/openai/text-embedding-ada-002":{"id":"openai/text-embedding-ada-002","name":"text-embedding-ada-002","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"text-embedding","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2022-12-15","last_updated":"2022-12-15","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"input":6656,"output":1536},"sourceProvider":"vercel"},"vercel/openai/tts-1":{"id":"openai/tts-1","name":"TTS-1","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/openai/tts-1-hd":{"id":"openai/tts-1-hd","name":"TTS-1 HD","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2023-11-06","last_updated":"2023-11-06","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/openai/whisper-1":{"id":"openai/whisper-1","name":"Whisper","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"whisper","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2022-09-21","last_updated":"2022-09-21","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/perplexity/pplx-embed-v1-0.6b":{"id":"perplexity/pplx-embed-v1-0.6b","name":"Embed v1 0.6b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"v0","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":0},"sourceProvider":"vercel"},"vercel/perplexity/pplx-embed-v1-4b":{"id":"perplexity/pplx-embed-v1-4b","name":"Embed v1 4b","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-02-26","last_updated":"2026-02-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":0},"sourceProvider":"vercel"},"vercel/perplexity/sonar":{"id":"perplexity/sonar","name":"Sonar","description":"Sonar search model for current answers, retrieval, and citation-backed chat","family":"sonar","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-02","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":8000},"sourceProvider":"vercel"},"vercel/perplexity/sonar-pro":{"id":"perplexity/sonar-pro","name":"Sonar Pro","description":"Advanced Sonar search model for deeper research and cited synthesis","family":"sonar-pro","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-09","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":8000},"sourceProvider":"vercel"},"vercel/perplexity/sonar-reasoning-pro":{"id":"perplexity/sonar-reasoning-pro","name":"Sonar Reasoning Pro","description":"Web-grounded reasoning model for multi-step research and cited answers","family":"sonar-reasoning","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"tool_call":false,"temperature":true,"knowledge":"2025-09","release_date":"2025-02-19","last_updated":"2025-02-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":127000,"output":8000},"sourceProvider":"vercel"},"vercel/poolside/laguna-s-2.1":{"id":"poolside/laguna-s-2.1","name":"Laguna S 2.1","description":"Agentic coding model from Poolside in the XS size class for local deployment","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0.1,"output":0.2,"cache_read":0.01},"sourceProvider":"vercel"},"vercel/poolside/laguna-s-2.1-free":{"id":"poolside/laguna-s-2.1-free","name":"Laguna S 2.1 Free","description":"Free provider route for experiments, demos, and cost-sensitive chat workloads","family":"laguna","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":false,"temperature":true,"release_date":"2026-07-21","last_updated":"2026-07-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":32768},"cost":{"input":0,"output":0},"sourceProvider":"vercel"},"vercel/prodia/flux-fast-schnell":{"id":"prodia/flux-fast-schnell","name":"Flux Schnell","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"flux","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-08-02","last_updated":"2026-06-08","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/quiverai/arrow-1.1":{"id":"quiverai/arrow-1.1","name":"Arrow 1.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"o","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":131072,"output":131072},"sourceProvider":"vercel"},"vercel/recraft/recraft-v2":{"id":"recraft/recraft-v2","name":"Recraft V2","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-03-13","last_updated":"2024-03","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v3":{"id":"recraft/recraft-v3","name":"Recraft V3","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-10-30","last_updated":"2024-10","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":512,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4":{"id":"recraft/recraft-v4","name":"Recraft V4","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4-pro":{"id":"recraft/recraft-v4-pro","name":"Recraft V4 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-02-17","last_updated":"2026-02-17","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4.1":{"id":"recraft/recraft-v4.1","name":"Recraft V4.1","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4.1-pro":{"id":"recraft/recraft-v4.1-pro","name":"Recraft V4.1 Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4.1-utility":{"id":"recraft/recraft-v4.1-utility","name":"Recraft V4.1 Utility","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/recraft/recraft-v4.1-utility-pro":{"id":"recraft/recraft-v4.1-utility-pro","name":"Recraft V4.1 Utility Pro","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"recraft","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-05-14","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/sakana/fugu-ultra":{"id":"sakana/fugu-ultra","name":"Fugu Ultra","description":"Quality-first multi-agent model for hard research, analysis, and competitions","family":"fugu","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-15","last_updated":"2026-06-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/sakana/namazu":{"id":"sakana/namazu","name":"Sakana Namazu","description":"Multi-agent model for routing expert agents across complex analytical tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-08-03","last_updated":"2026-08-03","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.95,"output":4,"cache_read":0.15},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.1-fast-non-reasoning":{"id":"spacexai/grok-4.1-fast-non-reasoning","name":"Grok 4.1 Fast Non-Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.1-fast-reasoning":{"id":"spacexai/grok-4.1-fast-reasoning","name":"Grok 4.1 Fast Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2025-11-19","last_updated":"2025-11-19","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-multi-agent":{"id":"spacexai/grok-4.20-multi-agent","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-multi-agent-beta":{"id":"spacexai/grok-4.20-multi-agent-beta","name":"Grok 4.20 Multi Agent Beta","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-non-reasoning":{"id":"spacexai/grok-4.20-non-reasoning","name":"Grok 4.20 Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-non-reasoning-beta":{"id":"spacexai/grok-4.20-non-reasoning-beta","name":"Grok 4.20 Beta Non-Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.4},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-reasoning":{"id":"spacexai/grok-4.20-reasoning","name":"Grok 4.20 Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-03-10","last_updated":"2026-03-10","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.20-reasoning-beta":{"id":"spacexai/grok-4.20-reasoning-beta","name":"Grok 4.20 Beta Reasoning","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":2000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.3":{"id":"spacexai/grok-4.3","name":"Grok 4.3","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-04-30","last_updated":"2026-04-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.5":{"id":"spacexai/grok-4.5","name":"Grok 4.5","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3},"sourceProvider":"vercel"},"vercel/spacexai/grok-4.6":{"id":"spacexai/grok-4.6","name":"Grok 4.6","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5},"sourceProvider":"vercel"},"vercel/spacexai/grok-build-0.1":{"id":"spacexai/grok-build-0.1","name":"Grok Build 0.1","description":"Grok coding model for agentic engineering, edits, and codebase workflows","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"release_date":"2026-05-20","last_updated":"2026-05-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"vercel"},"vercel/spacexai/grok-imagine-image":{"id":"spacexai/grok-imagine-image","name":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-imagine-image-2.0":{"id":"spacexai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text"],"output":["image"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-imagine-video":{"id":"spacexai/grok-imagine-video","name":"Grok Imagine","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-imagine-video-1.5":{"id":"spacexai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-06-22","last_updated":"2026-06-22","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-imagine-video-1.5-preview":{"id":"spacexai/grok-imagine-video-1.5-preview","name":"Grok Imagine Video 1.5 Preview","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-05-30","last_updated":"2026-05-30","modalities":{"input":["text"],"output":["video"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-stt":{"id":"spacexai/grok-stt","name":"Grok STT","description":"Speech transcription model for accurate audio-to-text and captioning workflows","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["audio"],"output":["text"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-tts":{"id":"spacexai/grok-tts","name":"Grok TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-voice-think-fast-1.0":{"id":"spacexai/grok-voice-think-fast-1.0","name":"Grok Voice Think Fast 1.0","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/spacexai/grok-voice-think-fast-2.0":{"id":"spacexai/grok-voice-think-fast-2.0","name":"Grok Voice Think Fast 2.0","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"grok","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-07-29","last_updated":"2026-07-29","modalities":{"input":["text","audio"],"output":["text","audio"]},"open_weights":false,"limit":{"context":0,"output":0},"sourceProvider":"vercel"},"vercel/stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"StepFun 3.5 Flash","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-29","last_updated":"2026-02-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262114,"output":262114},"cost":{"input":0.09,"output":0.3,"cache_read":0.02},"sourceProvider":"vercel"},"vercel/stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15,"cache_read":0.04},"sourceProvider":"vercel"},"vercel/tencent/hy-mt2-lite":{"id":"tencent/hy-mt2-lite","name":"Tencent Hy-MT2-Lite","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.044,"output":0.177},"sourceProvider":"vercel"},"vercel/tencent/hy-mt2-plus":{"id":"tencent/hy-mt2-plus","name":"Tencent Hy-MT2-Plus","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.074,"output":0.295},"sourceProvider":"vercel"},"vercel/tencent/hy-mt2-pro":{"id":"tencent/hy-mt2-pro","name":"Tencent Hy-MT2-Pro","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8000,"output":4000},"cost":{"input":0.074,"output":0.295},"sourceProvider":"vercel"},"vercel/tencent/hy3":{"id":"tencent/hy3","name":"Hy3","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-06","last_updated":"2026-07-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":128000},"cost":{"input":0.132,"output":0.528,"cache_read":0.033},"sourceProvider":"vercel"},"vercel/thinkingmachines/inkling":{"id":"thinkingmachines/inkling","name":"Inkling","description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-15","last_updated":"2026-07-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":4.05,"cache_read":0.17},"sourceProvider":"vercel"},"vercel/thinkingmachines/inkling-small":{"id":"thinkingmachines/inkling-small","name":"Inkling Small","description":"Multimodal reasoning model for visual analysis, planning, and tool use","family":"ling","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","minimal","low","medium","high","xhigh","max"]}],"tool_call":true,"temperature":true,"release_date":"2026-07-30","last_updated":"2026-07-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":1000000},"cost":{"input":0.5,"output":1.2,"cache_read":0.1},"sourceProvider":"vercel"},"vercel/voyage/rerank-2.5":{"id":"voyage/rerank-2.5","name":"Voyage Rerank 2.5","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"sourceProvider":"vercel"},"vercel/voyage/rerank-2.5-lite":{"id":"voyage/rerank-2.5-lite","name":"Voyage Rerank 2.5 Lite","description":"Reranking model for improving retrieval quality in search and recommendation systems","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":32000},"sourceProvider":"vercel"},"vercel/voyage/voyage-3-large":{"id":"voyage/voyage-3-large","name":"voyage-3-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-01-07","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-3.5":{"id":"voyage/voyage-3.5","name":"voyage-3.5","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-3.5-lite":{"id":"voyage/voyage-3.5-lite","name":"voyage-3.5-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2025-05-20","last_updated":"2025-05-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-4":{"id":"voyage/voyage-4","name":"voyage-4","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":0},"sourceProvider":"vercel"},"vercel/voyage/voyage-4-large":{"id":"voyage/voyage-4-large","name":"voyage-4-large","description":"Flagship model for demanding analysis, coding, and production agent workflows","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":0},"sourceProvider":"vercel"},"vercel/voyage/voyage-4-lite":{"id":"voyage/voyage-4-lite","name":"voyage-4-lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2026-01-15","last_updated":"2026-03-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":32000,"output":0},"sourceProvider":"vercel"},"vercel/voyage/voyage-code-2":{"id":"voyage/voyage-code-2","name":"voyage-code-2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-01-01","last_updated":"2024-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-code-3":{"id":"voyage/voyage-code-3","name":"voyage-code-3","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-12-04","last_updated":"2024-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-finance-2":{"id":"voyage/voyage-finance-2","name":"voyage-finance-2","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-06-03","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/voyage/voyage-law-2":{"id":"voyage/voyage-law-2","name":"voyage-law-2","description":"General-purpose chat model for instruction following, writing, and analysis","family":"voyage","attachment":false,"reasoning":false,"tool_call":false,"temperature":true,"release_date":"2024-04-15","last_updated":"2024-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":8192,"output":1536},"sourceProvider":"vercel"},"vercel/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo M2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131100},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"vercel"},"vercel/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo V2.5 Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1050000,"output":131000},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"sourceProvider":"vercel"},"vercel/zai/glm-4.5":{"id":"zai/glm-4.5","name":"GLM 4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-07","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"vercel"},"vercel/zai/glm-4.5-air":{"id":"zai/glm-4.5-air","name":"GLM 4.5 Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":96000},"cost":{"input":0.2,"output":1.1,"cache_read":0.03},"sourceProvider":"vercel"},"vercel/zai/glm-4.5v":{"id":"zai/glm-4.5v","name":"GLM 4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-08","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":66000,"output":16000},"cost":{"input":0.6,"output":1.8,"cache_read":0.11},"sourceProvider":"vercel"},"vercel/zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM 4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":96000},"cost":{"input":0.6,"output":2.2,"cache_read":0.11},"sourceProvider":"vercel"},"vercel/zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM 4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":120000},"cost":{"input":0.6,"output":2.2,"cache_read":0.12},"sourceProvider":"vercel"},"vercel/zai/glm-4.7-flash":{"id":"zai/glm-4.7-flash","name":"GLM 4.7 Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131000},"cost":{"input":0.07,"output":0.4},"sourceProvider":"vercel"},"vercel/zai/glm-4.7-flashx":{"id":"zai/glm-4.7-flashx","name":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.06,"output":0.4,"cache_read":0.01},"sourceProvider":"vercel"},"vercel/zai/glm-5":{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":131100},"cost":{"input":1,"output":3.2},"sourceProvider":"vercel"},"vercel/zai/glm-5-turbo":{"id":"zai/glm-5-turbo","name":"GLM 5 Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":202800,"output":131100},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"vercel"},"vercel/zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM 5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202800,"output":64000},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"vercel"},"vercel/zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":0.8,"output":2.55,"cache_read":0.16},"sourceProvider":"vercel"},"vercel/zai/glm-5.2-fast":{"id":"zai/glm-5.2-fast","name":"GLM 5.2 Fast","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":2.1,"output":6.6,"cache_read":0.21},"sourceProvider":"vercel"},"vercel/zai/glm-5.3":{"id":"zai/glm-5.3","name":"GLM 5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":12800},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"vercel"},"vercel/zai/glm-5v-turbo":{"id":"zai/glm-5v-turbo","name":"GLM 5V Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.2,"output":4,"cache_read":0.24},"sourceProvider":"vercel"},"vivgrid/deepseek-v3.2":{"id":"vivgrid/deepseek-v3.2","name":"DeepSeek-V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.28,"output":0.42},"sourceProvider":"vivgrid"},"vivgrid/deepseek-v4-flash":{"id":"vivgrid/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.15,"output":0.3,"reasoning":0.3,"cache_read":0.03},"sourceProvider":"vivgrid"},"vivgrid/deepseek-v4-pro":{"id":"vivgrid/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"vivgrid"},"vivgrid/gemini-3.1-flash-lite-preview":{"id":"vivgrid/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-03-03","last_updated":"2026-03-03","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.25,"output":1.5,"cache_read":0.025,"cache_write":1},"sourceProvider":"vivgrid"},"vivgrid/gemini-3.1-pro-preview":{"id":"vivgrid/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2,"output":12,"cache_read":0.2,"tiers":[{"input":4,"output":18,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":18,"cache_read":0.4}},"sourceProvider":"vivgrid"},"vivgrid/glm-5.2":{"id":"vivgrid/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":128000},"cost":{"input":1.2,"output":4.2,"cache_read":0.3},"sourceProvider":"vivgrid"},"vivgrid/glm-5.3":{"id":"vivgrid/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.2,"output":4.2,"cache_read":0.26},"sourceProvider":"vivgrid"},"vivgrid/gpt-5-mini":{"id":"vivgrid/gpt-5-mini","name":"GPT-5 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2024-05-30","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.1-codex":{"id":"vivgrid/gpt-5.1-codex","name":"GPT-5.1 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.1-codex-max":{"id":"vivgrid/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2024-09-30","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.25,"output":10,"cache_read":0.125},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.2-codex":{"id":"vivgrid/gpt-5.2-codex","name":"GPT-5.2 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-01-14","last_updated":"2026-01-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.3-codex":{"id":"vivgrid/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","family":"gpt-codex","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"cost":{"input":1.75,"output":14,"cache_read":0.175},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.4":{"id":"vivgrid/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":2.5,"output":15,"cache_read":0.25},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.4-mini":{"id":"vivgrid/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.75,"output":4.5,"cache_read":0.075},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.4-nano":{"id":"vivgrid/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","family":"gpt-nano","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":272000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":0.2,"output":1.25,"cache_read":0.02},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.5":{"id":"vivgrid/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"provider":{"npm":"@ai-sdk/openai-compatible"},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.6-luna":{"id":"vivgrid/gpt-5.6-luna","name":"GPT 5.6 Luna","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.6-sol":{"id":"vivgrid/gpt-5.6-sol","name":"GPT 5.6 Sol","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"vivgrid"},"vivgrid/gpt-5.6-terra":{"id":"vivgrid/gpt-5.6-terra","name":"GPT 5.6 Terra","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"sourceProvider":"vivgrid"},"vivgrid/kimi-k3":{"id":"vivgrid/kimi-k3","name":"Kimi K3","description":"Kimi multimodal agent model for visual understanding, coding, and planning","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"vivgrid"},"vultr/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.3,"output":1},"sourceProvider":"vultr"},"vultr/MiniMaxAI/MiniMax-M2.7":{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMax-M2.7","description":"Open MiniMax flagship for coding agents, office automation, and complex environments","family":"minimax","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"vultr"},"vultr/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.3,"output":1.2},"sourceProvider":"vultr"},"vultr/nvidia/DeepSeek-V3.2-NVFP4":{"id":"nvidia/DeepSeek-V3.2-NVFP4","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.55,"output":1.65},"sourceProvider":"vultr"},"vultr/nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16":{"id":"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16","name":"NVIDIA Nemotron 3 Nano Omni","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-28","last_updated":"2026-04-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.13,"output":0.38},"sourceProvider":"vultr"},"vultr/nvidia/Nemotron-Cascade-2-30B-A3B":{"id":"nvidia/Nemotron-Cascade-2-30B-A3B","name":"NVIDIA Nemotron Cascade 2","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-07","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":131072},"cost":{"input":0.15,"output":0.6},"sourceProvider":"vultr"},"vultr/Qwen/Qwen3.5-397B-A17B":{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen3.5 397B-A17B","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-15","last_updated":"2026-02-15","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2},"sourceProvider":"vultr"},"vultr/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.3,"output":2},"sourceProvider":"vultr"},"vultr/XiaomiMiMo/MiMo-V2.5-Pro":{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.55,"output":1.65},"sourceProvider":"vultr"},"vultr/zai-org/GLM-5.2-FP8":{"id":"zai-org/GLM-5.2-FP8","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":393216,"output":131072},"cost":{"input":0.85,"output":3.1},"sourceProvider":"vultr"},"wafer.ai/GLM-5.1":{"id":"wafer.ai/GLM-5.1","name":"GLM-5.1","description":"General Language Model 5.1 — high-quality bilingual (EN/ZH) generation with strong coding and reasoning capabilities.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-04-07","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.1,"cache_write":0},"sourceProvider":"wafer.ai"},"wafer.ai/GLM-5.2":{"id":"wafer.ai/GLM-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1.2,"output":4.1,"cache_read":0.2,"cache_write":0},"sourceProvider":"wafer.ai"},"wafer.ai/glm5.2-fast":{"id":"wafer.ai/glm5.2-fast","name":"GLM5.2-Fast","description":"The same model served for high TPS.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":10.25,"cache_read":0.5,"cache_write":0},"sourceProvider":"wafer.ai"},"wafer.ai/Kimi-K2.6":{"id":"wafer.ai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi K2.6 sparse MoE model with a 262K context window. Available serverless and not included in standard Wafer Pass. Non-ZDR only: requests with `Wafer-ZDR: required` are rejected.","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-04-21","last_updated":"2026-04-21","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":1.14,"output":4.8,"cache_read":0.19,"cache_write":0},"sourceProvider":"wafer.ai"},"wafer.ai/MiniMax-M3":{"id":"wafer.ai/MiniMax-M3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["none","low","medium","high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":128000},"cost":{"input":0.33,"output":1.32,"cache_read":0.07,"cache_write":0,"tiers":[{"input":0.66,"output":2.64,"cache_read":0.13,"cache_write":0,"tier":{"type":"context","size":512000}}],"context_over_200k":{"input":0.66,"output":2.64,"cache_read":0.13,"cache_write":0}},"sourceProvider":"wafer.ai"},"wandb/deepseek-ai/DeepSeek-V3.1":{"id":"deepseek-ai/DeepSeek-V3.1","name":"DeepSeek V3.1","description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","family":"deepseek","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-21","last_updated":"2025-08-21","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":161000,"output":161000},"cost":{"input":0.55,"output":1.65,"cache_read":0.55},"sourceProvider":"wandb"},"wandb/deepseek-ai/DeepSeek-V4-Flash":{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","description":"DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads.","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":0.14,"output":0.28,"cache_read":0.07},"sourceProvider":"wandb"},"wandb/deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","description":"DeepSeek V4-Flash-0731 is an MoE model great for coding, reasoning, and agentic workloads.","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-07-31","last_updated":"2026-07-31","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.13,"output":0.28,"cache_read":0.07},"sourceProvider":"wandb"},"wandb/deepseek-ai/DeepSeek-V4-Pro":{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"DeepSeek V4 Pro","description":"DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning, coding, and complex agentic workloads.","family":"deepseek","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":1.15,"output":2.55,"cache_read":0.2},"sourceProvider":"wandb"},"wandb/google/gemma-4-31B-it":{"id":"google/gemma-4-31B-it","name":"Gemma 4 31B","description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","family":"gemma","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-02","last_updated":"2026-04-02","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.34,"cache_read":0.1},"sourceProvider":"wandb"},"wandb/ibm-granite/granite-4.1-8b":{"id":"ibm-granite/granite-4.1-8b","name":"Granite 4.1 8B","description":"Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-29","last_updated":"2026-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1,"cache_read":0.05},"sourceProvider":"wandb"},"wandb/JetBrains/Mellum2-12B-A2.5B-Instruct":{"id":"JetBrains/Mellum2-12B-A2.5B-Instruct","name":"Mellum2 12B A2.5B","description":"Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflows.","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.05,"output":0.1,"cache_read":0.05},"sourceProvider":"wandb"},"wandb/meta-llama/Llama-3.1-70B-Instruct":{"id":"meta-llama/Llama-3.1-70B-Instruct","name":"Llama 3.1 70B","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.8,"output":0.8,"cache_read":0.8},"sourceProvider":"wandb"},"wandb/meta-llama/Llama-3.1-8B-Instruct":{"id":"meta-llama/Llama-3.1-8B-Instruct","name":"Llama 3.1 8B","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-07-23","last_updated":"2024-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.22,"output":0.22,"cache_read":0.22},"sourceProvider":"wandb"},"wandb/meta-llama/Llama-3.3-70B-Instruct":{"id":"meta-llama/Llama-3.3-70B-Instruct","name":"Llama 3.3 70B","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","family":"llama","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-01","last_updated":"2024-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":128000},"cost":{"input":0.71,"output":0.71,"cache_read":0.71},"sourceProvider":"wandb"},"wandb/MiniMaxAI/MiniMax-M2.5":{"id":"MiniMaxAI/MiniMax-M2.5","name":"MiniMax M2.5","description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","family":"minimax-m2.5","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":196608,"output":196608},"cost":{"input":0.3,"output":1.2,"cache_read":0.3},"sourceProvider":"wandb"},"wandb/MiniMaxAI/MiniMax-M3":{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMax M3","description":"MiniMax M3 is a multimodal MoE model with 23B active parameters optimized for coding and agentic workflows.","family":"minimax-m3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.23,"output":0.96,"cache_read":0.05},"sourceProvider":"wandb"},"wandb/moonshotai/Kimi-K2.6":{"id":"moonshotai/Kimi-K2.6","name":"Kimi K2.6","description":"Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.65,"output":3.41,"cache_read":0.15},"sourceProvider":"wandb"},"wandb/moonshotai/Kimi-K2.7-Code":{"id":"moonshotai/Kimi-K2.7-Code","name":"Kimi K2.7 Code","description":"Kimi K2.7 Code is a 1T-parameter MoE model with 32B active parameters purpose-built for long-horizon agentic coding and software engineering.","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.71,"output":3.5,"cache_read":0.15},"sourceProvider":"wandb"},"wandb/moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","description":"Kimi K3 is a 2.8T-parameter multimodal MoE model with 104B active parameters built for long-horizon coding and agentic workflows.","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":1048576},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"wandb"},"wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8":{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8","name":"Nemotron 3 Super","description":"Nemotron 3 is a LatentMoE model designed to deliver strong agentic, reasoning, and conversational capabilities.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-11","last_updated":"2026-03-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.2,"output":0.8,"cache_read":0.2},"sourceProvider":"wandb"},"wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron 3 Ultra","description":"Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-04","last_updated":"2026-06-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.75,"output":2.75,"cache_read":0.15},"sourceProvider":"wandb"},"wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B":{"id":"nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B","name":"Nemotron 3.5 Lightning","description":"Nemotron 3.5 Lightning is an MoE model built for fast, reliable agentic tasks across use cases such as financial services, cybersecurity, telecom, and retail.","family":"nemotron","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-11","last_updated":"2026-08-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.25,"cache_read":0.05},"sourceProvider":"wandb"},"wandb/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"gpt-oss-120b","description":"Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.17,"cache_read":0.03},"sourceProvider":"wandb"},"wandb/openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"gpt-oss-20b","description":"Lower latency Mixture-of-Experts model trained on OpenAI's Harmony response format with reasoning capabilities.","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.03,"output":0.13,"cache_read":0.03},"sourceProvider":"wandb"},"wandb/OpenPipe/Qwen3-14B-Instruct":{"id":"OpenPipe/Qwen3-14B-Instruct","name":"Qwen3 14B Instruct","description":"An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-04-29","last_updated":"2025-04-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":32768,"output":32768},"cost":{"input":0.05,"output":0.22,"cache_read":0.05},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3-30B-A3B-Instruct-2507":{"id":"Qwen/Qwen3-30B-A3B-Instruct-2507","name":"Qwen3 30B A3B Instruct 2507","description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-07-29","last_updated":"2025-07-29","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.1,"output":0.3,"cache_read":0.1},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct":{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct","name":"Qwen3 Coder 480B A35B","description":"Mixture-of-Experts model optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning.","family":"qwen","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":1,"output":1.5,"cache_read":1},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3.5-35B-A3B":{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen3.5-35B-A3B","description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","family":"qwen3.5","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-02-24","last_updated":"2026-02-24","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.25,"cache_read":0.25},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3.6-27B":{"id":"Qwen/Qwen3.6-27B","name":"Qwen3.6 27B","description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.6,"output":3.6,"cache_read":0.12},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3.6-35B-A3B":{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B A3B","description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","family":"qwen3.6","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.25,"output":1.25,"cache_read":0.25},"sourceProvider":"wandb"},"wandb/Qwen/Qwen3.8-27B":{"id":"Qwen/Qwen3.8-27B","name":"Qwen3.8 27B","description":"Qwen3.8-27B is a dense multimodal model suited for coding, research, vision, and long-running agent tasks.","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.4,"output":3,"cache_read":0.15},"sourceProvider":"wandb"},"wandb/zai-org/GLM-5.1":{"id":"zai-org/GLM-5.1","name":"GLM 5.1","description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":202752,"output":202752},"cost":{"input":1.4,"output":4.4,"cache_read":0.26},"sourceProvider":"wandb"},"wandb/zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","description":"GLM-5.2 is a Mixture-of-Experts language model featuring 40 billion activated parameters and a total of 744 billion parameters.","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-16","last_updated":"2026-06-16","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.76,"output":2.42,"cache_read":0.14},"sourceProvider":"wandb"},"watsonx/ibm/granite-4-h-small":{"id":"ibm/granite-4-h-small","name":"Granite-4.0-H-Small","description":"Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads","family":"granite","attachment":false,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-10-02","last_updated":"2025-10-02","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":131072},"cost":{"input":0.0636,"output":0.265},"sourceProvider":"watsonx"},"watsonx/meta-llama/llama-3-3-70b-instruct":{"id":"meta-llama/llama-3-3-70b-instruct","name":"Llama-3.3-70B-Instruct","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2023-12","release_date":"2024-12-06","last_updated":"2024-12-06","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":4096},"cost":{"input":0.7526,"output":0.7526},"sourceProvider":"watsonx"},"watsonx/meta-llama/llama-4-maverick-17b-128e-instruct-fp8":{"id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","family":"llama","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2024-08","release_date":"2025-04-05","last_updated":"2025-04-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":8192},"cost":{"input":0.371,"output":1.484},"sourceProvider":"watsonx"},"watsonx/mistralai/mistral-small-3-1-24b-instruct-2503":{"id":"mistralai/mistral-small-3-1-24b-instruct-2503","name":"Mistral Small 3.1 24B","description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","family":"mistral-small","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2024-06","release_date":"2025-03-17","last_updated":"2025-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":16384},"cost":{"input":0.106,"output":0.318},"sourceProvider":"watsonx"},"watsonx/openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","family":"gpt-oss","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":32768},"cost":{"input":0.159,"output":0.636},"sourceProvider":"watsonx"},"xai/grok-4.20-0309-non-reasoning":{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":false,"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"xai"},"xai/grok-4.20-0309-reasoning":{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"xai"},"xai/grok-4.20-multi-agent-0309":{"id":"xai/grok-4.20-multi-agent-0309","name":"Grok 4.20 Multi-Agent","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":false,"structured_output":true,"temperature":true,"release_date":"2026-03-09","last_updated":"2026-03-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"xai"},"xai/grok-4.3":{"id":"xai/grok-4.3","name":"Grok 4.3","description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":30000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4}},"sourceProvider":"xai"},"xai/grok-4.5":{"id":"xai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.3,"tiers":[{"input":4,"output":12,"cache_read":0.6,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":0.6}},"sourceProvider":"xai"},"xai/grok-4.6":{"id":"xai/grok-4.6","name":"Grok 4.6","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2026-02-01","release_date":"2026-08-12","last_updated":"2026-08-12","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"xai"},"xai/grok-build-0.1":{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2,"tiers":[{"input":2,"output":4,"cache_read":0.4,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2,"output":4,"cache_read":0.4}},"sourceProvider":"xai"},"xai/grok-imagine-image":{"id":"xai/grok-imagine-image","name":"Grok Imagine Image","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":8000,"output":0},"sourceProvider":"xai"},"xai/grok-imagine-image-2.0":{"id":"xai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-08-07","last_updated":"2026-08-07","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":8000,"output":0},"sourceProvider":"xai"},"xai/grok-imagine-image-quality":{"id":"xai/grok-imagine-image-quality","name":"Grok Imagine Image Quality","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-04-03","last_updated":"2026-04-03","modalities":{"input":["text","image","pdf"],"output":["image","pdf"]},"open_weights":false,"limit":{"context":8000,"output":0},"sourceProvider":"xai"},"xai/grok-imagine-video":{"id":"xai/grok-imagine-video","name":"Grok Imagine Video","description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"grok","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-01-28","last_updated":"2026-01-28","modalities":{"input":["text","image","video","pdf"],"output":["video"]},"open_weights":false,"limit":{"context":1024,"output":0},"sourceProvider":"xai"},"xai/grok-imagine-video-1.5":{"id":"xai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","description":"Video model for image-to-video generation, editing, and extension workflows","family":"grok","attachment":true,"reasoning":false,"tool_call":false,"temperature":false,"release_date":"2026-05-30","last_updated":"2026-05-30","modalities":{"input":["text","image","audio","pdf"],"output":["video"]},"open_weights":false,"limit":{"context":1024,"output":0},"sourceProvider":"xai"},"xiaomi-token-plan-ams/mimo-v2-pro":{"id":"xiaomi-token-plan-ams/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2-tts":{"id":"xiaomi-token-plan-ams/mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2.5":{"id":"xiaomi-token-plan-ams/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2.5-pro":{"id":"xiaomi-token-plan-ams/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2.5-tts":{"id":"xiaomi-token-plan-ams/mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2.5-tts-voiceclone":{"id":"xiaomi-token-plan-ams/mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign":{"id":"xiaomi-token-plan-ams/mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-ams"},"xiaomi-token-plan-cn/mimo-v2-pro":{"id":"xiaomi-token-plan-cn/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2-tts":{"id":"xiaomi-token-plan-cn/mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2.5":{"id":"xiaomi-token-plan-cn/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2.5-pro":{"id":"xiaomi-token-plan-cn/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2.5-tts":{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2.5-tts-voiceclone":{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign":{"id":"xiaomi-token-plan-cn/mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-cn"},"xiaomi-token-plan-sgp/mimo-v2-pro":{"id":"xiaomi-token-plan-sgp/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2-tts":{"id":"xiaomi-token-plan-sgp/mimo-v2-tts","name":"MiMo-V2-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2.5":{"id":"xiaomi-token-plan-sgp/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2.5-pro":{"id":"xiaomi-token-plan-sgp/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2.5-tts":{"id":"xiaomi-token-plan-sgp/mimo-v2.5-tts","name":"MiMo-V2.5-TTS","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2.5-tts-voiceclone":{"id":"xiaomi-token-plan-sgp/mimo-v2.5-tts-voiceclone","name":"MiMo-V2.5-TTS-VoiceClone","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign":{"id":"xiaomi-token-plan-sgp/mimo-v2.5-tts-voicedesign","name":"MiMo-V2.5-TTS-VoiceDesign","description":"Speech generation model for controllable voice, narration, and audio delivery","family":"mimo","attachment":false,"reasoning":false,"tool_call":false,"release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["audio"]},"open_weights":true,"limit":{"context":8192,"output":8192},"cost":{"input":0,"output":0},"sourceProvider":"xiaomi-token-plan-sgp"},"xiaomi/mimo-v2-flash":{"id":"xiaomi/mimo-v2-flash","name":"MiMo-V2-Flash","description":"Legacy model retained for compatibility with older integrations","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"xiaomi"},"xiaomi/mimo-v2-omni":{"id":"xiaomi/mimo-v2-omni","name":"MiMo-V2-Omni","description":"Legacy model retained for compatibility with older integrations","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-06-24","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":262144,"output":131072},"status":"deprecated","cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"xiaomi"},"xiaomi/mimo-v2-pro":{"id":"xiaomi/mimo-v2-pro","name":"MiMo-V2-Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":131072},"status":"deprecated","cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"sourceProvider":"xiaomi"},"xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-06-24","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"xiaomi"},"xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-06-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.435,"output":0.87,"cache_read":0.0036},"sourceProvider":"xiaomi"},"xiaomi/mimo-v2.5-pro-ultraspeed":{"id":"xiaomi/mimo-v2.5-pro-ultraspeed","name":"MiMo-V2.5-Pro-UltraSpeed","description":"MiMo pro model for strong multimodal reasoning and agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-06-08","last_updated":"2026-06-09","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"status":"beta","cost":{"input":1.305,"output":2.61,"cache_read":0.0108},"sourceProvider":"xiaomi"},"xpersona/claude-fable-5":{"id":"xpersona/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":18.5,"reasoning":18.5,"cache_read":0.3},"sourceProvider":"xpersona"},"xpersona/claude-haiku-4-5":{"id":"xpersona/claude-haiku-4-5","name":"Claude Haiku 4.5 (latest)","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","family":"claude-haiku","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-02-28","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.6,"output":3.7,"reasoning":3.7,"cache_read":0.06},"sourceProvider":"xpersona"},"xpersona/claude-opus-4-8":{"id":"xpersona/claude-opus-4-8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":1.5,"output":9.25,"reasoning":9.25,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/claude-sonnet-4-6":{"id":"xpersona/claude-sonnet-4-6","name":"Claude Sonnet 4.6","description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-17","last_updated":"2026-03-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.9,"output":5.55,"reasoning":5.55,"cache_read":0.09},"sourceProvider":"xpersona"},"xpersona/gemini-3.5-flash":{"id":"xpersona/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":1.55,"output":12.2,"reasoning":12.2,"cache_read":0.155},"sourceProvider":"xpersona"},"xpersona/gpt-5.4":{"id":"xpersona/gpt-5.4","name":"GPT-5.4","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-05","last_updated":"2026-03-05","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":0.75,"output":6,"reasoning":6,"cache_read":0.075},"sourceProvider":"xpersona"},"xpersona/gpt-5.4-mini":{"id":"xpersona/gpt-5.4-mini","name":"GPT-5.4 mini","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","family":"gpt-mini","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2026-03-17","last_updated":"2026-03-17","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":272000,"output":128000},"cost":{"input":0.375,"output":4,"reasoning":4,"cache_read":0.0375},"sourceProvider":"xpersona"},"xpersona/gpt-5.5":{"id":"xpersona/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/gpt-5.6":{"id":"xpersona/gpt-5.6","name":"GPT-5.6","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/gpt-5.6-sol":{"id":"xpersona/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":12,"reasoning":12,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/gpt-5.6-terra":{"id":"xpersona/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":372000,"output":128000},"cost":{"input":1.5,"output":2,"reasoning":2,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/xpersona-frieren-coder":{"id":"xpersona/xpersona-frieren-coder","name":"Xpersona Frieren 1","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-30","release_date":"2026-05-01","last_updated":"2026-05-25","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":384000},"cost":{"input":1.5,"output":6,"reasoning":6,"cache_read":0.15},"sourceProvider":"xpersona"},"xpersona/xpersona-gpt-5.5":{"id":"xpersona/xpersona-gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"knowledge":"2025-12-30","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"cost":{"input":3,"output":18,"reasoning":18,"cache_read":0.3},"sourceProvider":"xpersona"},"zai-coding-plan/glm-4.7":{"id":"zai-coding-plan/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai-coding-plan"},"zai-coding-plan/glm-5-turbo":{"id":"zai-coding-plan/glm-5-turbo","name":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai-coding-plan"},"zai-coding-plan/glm-5.2":{"id":"zai-coding-plan/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai-coding-plan"},"zai-coding-plan/glm-5.2-highspeed":{"id":"zai-coding-plan/glm-5.2-highspeed","name":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai-coding-plan"},"zai-coding-plan/glm-5.3":{"id":"zai-coding-plan/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai-coding-plan"},"zai/glm-4.5":{"id":"zai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.5-air":{"id":"zai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.5-flash":{"id":"zai/glm-4.5-flash","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.5v":{"id":"zai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.6,"output":1.8},"sourceProvider":"zai"},"zai/glm-4.6":{"id":"zai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.6v":{"id":"zai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9},"sourceProvider":"zai"},"zai/glm-4.7":{"id":"zai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.7-flash":{"id":"zai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zai"},"zai/glm-4.7-flashx":{"id":"zai/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"sourceProvider":"zai"},"zai/glm-5":{"id":"zai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"sourceProvider":"zai"},"zai/glm-5-turbo":{"id":"zai/glm-5-turbo","name":"GLM-5-Turbo","description":"Faster GLM-5 lane for coding agents that need lower latency","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"sourceProvider":"zai"},"zai/glm-5.1":{"id":"zai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-07","last_updated":"2026-04-07","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"zai"},"zai/glm-5.2":{"id":"zai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"zai"},"zai/glm-5v-turbo":{"id":"zai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"sourceProvider":"zai"},"zeldoc/zdev":{"id":"zeldoc/zdev","name":"ZDev","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-04-15","last_updated":"2026-04-15","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0},"sourceProvider":"zeldoc"},"zenifra/alibaba/qwen3.6-35b-a3b":{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"provider":{"shape":"completions"},"cost":{"input":0.19,"output":0.48},"sourceProvider":"zenifra"},"zenmux/anthropic/claude-3.5-haiku":{"id":"anthropic/claude-3.5-haiku","name":"Claude 3.5 Haiku","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2024-11-04","last_updated":"2024-11-04","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.8,"output":4,"cache_read":0.08,"cache_write":1},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-3.7-sonnet":{"id":"anthropic/claude-3.7-sonnet","name":"Claude 3.7 Sonnet","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-02-24","last_updated":"2025-02-24","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"status":"deprecated","provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-fable-5":{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","description":"Claude model for creative writing, analysis, and controlled agent workflows","family":"claude-fable","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-09","last_updated":"2026-06-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-haiku-4.5":{"id":"anthropic/claude-haiku-4.5","name":"Claude Haiku 4.5","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-10-15","last_updated":"2025-10-15","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4":{"id":"anthropic/claude-opus-4","name":"Claude Opus 4","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":32000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4.1":{"id":"anthropic/claude-opus-4.1","name":"Claude Opus 4.1","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-08-05","last_updated":"2025-08-05","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4.5":{"id":"anthropic/claude-opus-4.5","name":"Claude Opus 4.5","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-24","last_updated":"2025-11-24","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4.6":{"id":"anthropic/claude-opus-4.6","name":"Claude Opus 4.6","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-05-31","release_date":"2026-02-06","last_updated":"2026-02-06","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4.7":{"id":"anthropic/claude-opus-4.7","name":"Claude Opus 4.7","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-opus-4.8":{"id":"anthropic/claude-opus-4.8","name":"Claude Opus 4.8","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01","release_date":"2026-05-28","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-sonnet-4":{"id":"anthropic/claude-sonnet-4","name":"Claude Sonnet 4","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-05-22","last_updated":"2025-05-22","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-sonnet-4.5":{"id":"anthropic/claude-sonnet-4.5","name":"Claude Sonnet 4.5","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-sonnet-4.6":{"id":"anthropic/claude-sonnet-4.6","name":"Claude Sonnet 4.6","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-02-18","last_updated":"2026-02-18","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-sonnet-5":{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":2,"output":10,"cache_read":0.2,"cache_write":4},"sourceProvider":"zenmux"},"zenmux/anthropic/claude-sonnet-5-free":{"id":"anthropic/claude-sonnet-5-free","name":"Claude Sonnet 5 (Free)","description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2026-01-31","release_date":"2026-06-30","last_updated":"2026-06-30","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zenmux"},"zenmux/baidu/ernie-5.0-thinking-preview":{"id":"baidu/ernie-5.0-thinking-preview","name":"ERNIE 5.0","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-01-22","last_updated":"2026-01-22","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.84,"output":3.37},"sourceProvider":"zenmux"},"zenmux/deepseek/deepseek-chat":{"id":"deepseek/deepseek-chat","name":"DeepSeek-V3.2 (Non-thinking Mode)","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-01","last_updated":"2025-12-01","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"status":"deprecated","cost":{"input":0.28,"output":0.42,"cache_read":0.03},"sourceProvider":"zenmux"},"zenmux/deepseek/deepseek-v3.2":{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-05","last_updated":"2025-12-05","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.28,"output":0.43},"sourceProvider":"zenmux"},"zenmux/deepseek/deepseek-v3.2-exp":{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek-V3.2-Exp","description":"DeepSeek chat model for instruction following, coding, and analysis","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-29","last_updated":"2025-09-29","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":163000,"output":64000},"cost":{"input":0.22,"output":0.33},"sourceProvider":"zenmux"},"zenmux/deepseek/deepseek-v4-flash":{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","family":"deepseek-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.14,"output":0.28,"cache_read":0.0028},"sourceProvider":"zenmux"},"zenmux/deepseek/deepseek-v4-pro":{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","description":"Open MoE flagship with million-token context for coding and long agent runs","family":"deepseek-thinking","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"knowledge":"2025-05","release_date":"2026-04-24","last_updated":"2026-04-24","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":384000},"cost":{"input":0.435,"output":0.87,"cache_read":0.003625},"sourceProvider":"zenmux"},"zenmux/google/gemini-2.5-flash":{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"output":64000},"cost":{"input":0.3,"output":2.5,"cache_read":0.07,"cache_write":1},"sourceProvider":"zenmux"},"zenmux/google/gemini-2.5-flash-lite":{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-22","last_updated":"2025-07-22","modalities":{"input":["pdf","image","text","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"output":64000},"cost":{"input":0.1,"output":0.4,"cache_read":0.03,"cache_write":1},"sourceProvider":"zenmux"},"zenmux/google/gemini-2.5-pro":{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-06-17","last_updated":"2025-06-17","modalities":{"input":["pdf","image","text","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"output":64000},"cost":{"input":1.25,"output":10,"cache_read":0.31,"cache_write":4.5},"sourceProvider":"zenmux"},"zenmux/google/gemini-3-flash-preview":{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-17","last_updated":"2025-12-17","modalities":{"input":["text","image","pdf","audio"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":1},"sourceProvider":"zenmux"},"zenmux/google/gemini-3.1-flash-lite":{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-07","last_updated":"2026-05-07","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":0.25,"output":1.5,"cache_read":0.025},"sourceProvider":"zenmux"},"zenmux/google/gemini-3.1-flash-lite-preview":{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2025-03-20","last_updated":"2025-03-20","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":65530},"cost":{"input":0.25,"output":1.5},"sourceProvider":"zenmux"},"zenmux/google/gemini-3.1-pro-preview":{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02-19","release_date":"2026-02-19","last_updated":"2026-02-19","modalities":{"input":["text","image","pdf","audio","video"],"output":["text"]},"open_weights":false,"limit":{"context":1048000,"output":64000},"cost":{"input":2,"output":12,"cache_read":0.2,"cache_write":4.5},"sourceProvider":"zenmux"},"zenmux/google/gemini-3.5-flash":{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-01","release_date":"2026-05-19","last_updated":"2026-05-19","modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1048576,"output":65536},"cost":{"input":1.5,"output":9,"cache_read":0.15},"sourceProvider":"zenmux"},"zenmux/inclusionai/ling-1t":{"id":"inclusionai/ling-1t","name":"Ling-1T","description":"Tool-capable chat model for instruction following and agentic application workflows","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-10-09","last_updated":"2025-10-09","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"status":"deprecated","cost":{"input":0.56,"output":2.24,"cache_read":0.11},"sourceProvider":"zenmux"},"zenmux/inclusionai/ring-1t":{"id":"inclusionai/ring-1t","name":"Ring-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-10-12","last_updated":"2025-10-12","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"status":"deprecated","cost":{"input":0.56,"output":2.24,"cache_read":0.11},"sourceProvider":"zenmux"},"zenmux/inclusionai/ring-2.6-1t":{"id":"inclusionai/ring-2.6-1t","name":"inclusionAI: Ring-2.6-1T","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-12-31","release_date":"2026-05-07","last_updated":"2026-05-14","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262000,"output":65000},"cost":{"input":0.3,"output":2.5,"cache_read":0.06},"sourceProvider":"zenmux"},"zenmux/kuaishou/kat-coder-pro-v2":{"id":"kuaishou/kat-coder-pro-v2","name":"KAT-Coder-Pro-V2","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":80000},"cost":{"input":0.3,"output":1.2,"cache_read":0.06},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2":{"id":"minimax/minimax-m2","name":"MiniMax M2","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-10-27","last_updated":"2025-10-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.38},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2.1":{"id":"minimax/minimax-m2.1","name":"MiniMax M2.1","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204000,"output":64000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.38},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2.5":{"id":"minimax/minimax-m2.5","name":"MiniMax M2.5","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":0.375},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2.5-lightning":{"id":"minimax/minimax-m2.5-lightning","name":"MiniMax M2.5 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-13","last_updated":"2026-02-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131072},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.6,"output":4.8,"cache_read":0.06,"cache_write":0.75},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2.7":{"id":"minimax/minimax-m2.7","name":"MiniMax M2.7","description":"MiniMax model for chat, coding, office work, and agentic tasks","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131070},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.3055,"output":1.2219},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m2.7-highspeed":{"id":"minimax/minimax-m2.7-highspeed","name":"MiniMax M2.7 highspeed","description":"High-speed MiniMax model for low-latency coding and agent workflows","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":204800,"output":131070},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.611,"output":2.4439},"sourceProvider":"zenmux"},"zenmux/minimax/minimax-m3":{"id":"minimax/minimax-m3","name":"MiniMax-M3","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","family":"minimax","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-06-01","last_updated":"2026-06-01","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":512000,"output":128000},"provider":{"npm":"@ai-sdk/anthropic","api":"https://zenmux.ai/api/anthropic/v1"},"cost":{"input":0.6,"output":2.4},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2-0905":{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 0905","description":"Kimi model for long-context chat, coding, and agentic reasoning","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-04","last_updated":"2025-09-04","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":64000},"status":"deprecated","cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2-thinking":{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":64000},"status":"deprecated","cost":{"input":0.6,"output":2.5,"cache_read":0.15},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2-thinking-turbo":{"id":"moonshotai/kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","description":"Kimi reasoning model for long-horizon research, planning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-06","last_updated":"2025-11-06","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":64000},"status":"deprecated","cost":{"input":1.15,"output":8,"cache_read":0.15},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2.5":{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2025-01-01","release_date":"2026-01-27","last_updated":"2026-01-27","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":262000,"output":64000},"cost":{"input":0.58,"output":3.02,"cache_read":0.1},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","description":"Kimi multimodal agent model for visual understanding, coding, and planning","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":false,"knowledge":"2025-01-01","release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262140,"output":262140},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2.7-code":{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0.95,"output":4,"cache_read":0.16},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k2.7-code-free":{"id":"moonshotai/kimi-k2.7-code-free","name":"Kimi K2.7 Code (Free)","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","family":"kimi-k2","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-01","release_date":"2026-06-12","last_updated":"2026-06-12","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":262144},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":3,"output":15,"cache_read":0.3},"sourceProvider":"zenmux"},"zenmux/moonshotai/kimi-k3-free":{"id":"moonshotai/kimi-k3-free","name":"Kimi K3 (Free)","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","family":"kimi-k3","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":false,"release_date":"2026-07-16","last_updated":"2026-07-16","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5":{"id":"openai/gpt-5","name":"GPT-5","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-08-07","last_updated":"2025-08-07","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.12},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5-codex":{"id":"openai/gpt-5-codex","name":"GPT-5 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-23","last_updated":"2025-09-23","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.12},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.1":{"id":"openai/gpt-5.1","name":"GPT-5.1","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.12},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.1-chat":{"id":"openai/gpt-5.1-chat","name":"GPT-5.1 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["pdf","image","text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.12},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.1-codex":{"id":"openai/gpt-5.1-codex","name":"GPT-5.1-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.25,"output":10,"cache_read":0.12},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.1-codex-mini":{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1-Codex-Mini","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-13","last_updated":"2025-11-13","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":0.25,"output":2,"cache_read":0.03},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.2":{"id":"openai/gpt-5.2","name":"GPT-5.2","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-01-01","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["image","text","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.17},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.2-codex":{"id":"openai/gpt-5.2-codex","name":"GPT-5.2-Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":false,"knowledge":"2025-01-01","release_date":"2026-01-15","last_updated":"2026-01-15","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":64000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.75,"output":14,"cache_read":0.17},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.2-pro":{"id":"openai/gpt-5.2-pro","name":"GPT-5.2-Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":false,"knowledge":"2025-08-31","release_date":"2025-12-11","last_updated":"2025-12-11","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":21,"output":168},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.3-chat":{"id":"openai/gpt-5.3-chat","name":"GPT-5.3 Chat","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":16380},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.75,"output":14},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.3-codex":{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":1.75,"output":14},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.4":{"id":"openai/gpt-5.4","name":"GPT-5.4","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":3.75,"output":18.75},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.4-mini":{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 Mini","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":0.75,"output":4.5},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.4-nano":{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 Nano","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":0.2,"output":1.25},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.4-pro":{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","description":"Frontier GPT model for professional reasoning, coding, and multimodal work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"output":128000},"provider":{"npm":"@ai-sdk/openai","api":"https://zenmux.ai/api/v1"},"cost":{"input":45,"output":225},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.5":{"id":"openai/gpt-5.5","name":"GPT-5.5","description":"Default frontier GPT for coding, computer use, research, and knowledge work","family":"gpt","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"experimental":{"modes":{"fast":{"cost":{"input":12.5,"output":75,"cache_read":1.25},"provider":{"body":{"service_tier":"priority"}}}}},"cost":{"input":5,"output":30,"cache_read":0.5,"tiers":[{"input":10,"output":45,"cache_read":1,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1}},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.5-instant":{"id":"openai/gpt-5.5-instant","name":"GPT-5.5 Instant","description":"Compact GPT model for low-latency assistance and high-volume workloads","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"knowledge":"2025-12-01","release_date":"2026-05-05","last_updated":"2026-05-28","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":400000,"input":400000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.5-pro":{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","family":"gpt-pro","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["medium","high","xhigh"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2025-12-01","release_date":"2026-04-23","last_updated":"2026-04-23","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":30,"output":180,"tiers":[{"input":60,"output":270,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":60,"output":270}},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.6-luna":{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","family":"gpt-luna","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":1,"output":6,"cache_read":0.1,"cache_write":1.25,"tiers":[{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":2,"output":9,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.6-sol":{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","family":"gpt-sol","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25,"tiers":[{"input":10,"output":45,"cache_read":1,"cache_write":12.5,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":10,"output":45,"cache_read":1,"cache_write":12.5}},"sourceProvider":"zenmux"},"zenmux/openai/gpt-5.6-terra":{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","family":"gpt-terra","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high","xhigh","max"]}],"tool_call":true,"structured_output":true,"temperature":false,"knowledge":"2026-02-16","release_date":"2026-07-09","last_updated":"2026-07-09","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1050000,"input":922000,"output":128000},"cost":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125,"tiers":[{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25,"tier":{"type":"context","size":272000}}],"context_over_200k":{"input":5,"output":22.5,"cache_read":0.5,"cache_write":6.25}},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3-coder-plus":{"id":"qwen/qwen3-coder-plus","name":"Qwen3-Coder-Plus","description":"Qwen coding model for software agents, repository edits, and code reasoning","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-23","last_updated":"2025-07-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3-max":{"id":"qwen/qwen3-max","name":"Qwen3-Max-Thinking","description":"Qwen reasoning model for deliberate problem solving, math, and coding","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-01-23","last_updated":"2026-01-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":1.2,"output":6},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3.5-flash":{"id":"qwen/qwen3.5-flash","name":"Qwen3.5 Flash","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1020000,"output":1020000},"cost":{"input":0.1,"output":0.4},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3.5-plus":{"id":"qwen/qwen3.5-plus","name":"Qwen3.5 Plus","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.8,"output":4.8},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3.6-plus":{"id":"qwen/qwen3.6-plus","name":"Qwen3.6-Plus","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-03-30","last_updated":"2026-03-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625,"tiers":[{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5}},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3.7-max":{"id":"qwen/qwen3.7-max","name":"Qwen3.7 Max","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","family":"qwen","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"release_date":"2026-05-21","last_updated":"2026-05-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":65536},"cost":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"sourceProvider":"zenmux"},"zenmux/qwen/qwen3.7-plus":{"id":"qwen/qwen3.7-plus","name":"Qwen3.7 Plus","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","family":"qwen","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-06-02","last_updated":"2026-06-02","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":64000},"cost":{"input":0.4,"output":1.6,"cache_read":0.08,"cache_write":0.5,"tiers":[{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":1.5,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":1.5}},"sourceProvider":"zenmux"},"zenmux/sapiens-ai/agnes-1.5-lite":{"id":"sapiens-ai/agnes-1.5-lite","name":"Agnes 1.5 Lite","description":"Efficient model for low-latency assistance, extraction, and routine automation","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"release_date":"2026-03-26","last_updated":"2026-03-26","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.12,"output":0.6},"sourceProvider":"zenmux"},"zenmux/sapiens-ai/agnes-1.5-pro":{"id":"sapiens-ai/agnes-1.5-pro","name":"Agnes 1.5 Pro","description":"Flagship model for demanding analysis, coding, and production agent workflows","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"release_date":"2026-03-21","last_updated":"2026-03-21","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":0.16,"output":0.8},"sourceProvider":"zenmux"},"zenmux/stepfun/step-3":{"id":"stepfun/step-3","name":"Step-3","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-31","last_updated":"2025-07-31","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":65536,"output":64000},"status":"deprecated","cost":{"input":0.21,"output":0.57},"sourceProvider":"zenmux"},"zenmux/stepfun/step-3.5-flash":{"id":"stepfun/step-3.5-flash","name":"Step 3.5 Flash","description":"StepFun flash model for efficient multimodal reasoning, coding, and tool use","attachment":false,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-02","last_updated":"2026-02-02","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.1,"output":0.3},"sourceProvider":"zenmux"},"zenmux/stepfun/step-3.7-flash":{"id":"stepfun/step-3.7-flash","name":"Step 3.7 Flash","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0.2,"output":1.15},"sourceProvider":"zenmux"},"zenmux/stepfun/step-3.7-flash-free":{"id":"stepfun/step-3.7-flash-free","name":"Step 3.7 Flash (Free)","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-03-01","release_date":"2026-05-29","last_updated":"2026-05-29","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"input":256000,"output":256000},"cost":{"input":0,"output":0},"sourceProvider":"zenmux"},"zenmux/tencent/hy3-preview":{"id":"tencent/hy3-preview","name":"Hy3 preview","description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","family":"Hy","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","high"]}],"tool_call":true,"temperature":true,"release_date":"2026-04-20","last_updated":"2026-04-20","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":256000,"output":64000},"cost":{"input":0.172,"output":0.572,"cache_read":0.058,"cache_write":0},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-1.8":{"id":"volcengine/doubao-seed-1.8","name":"Doubao-Seed-1.8","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-18","last_updated":"2025-12-18","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.11,"output":0.28,"cache_read":0.02,"cache_write":0.0024},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-2.0-code":{"id":"volcengine/doubao-seed-2.0-code","name":"Doubao Seed 2.0 Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":32000},"cost":{"input":0.9,"output":4.48},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-2.0-lite":{"id":"volcengine/doubao-seed-2.0-lite","name":"Doubao-Seed-2.0-lite","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02-14","release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.09,"output":0.51,"cache_read":0.02,"cache_write":0.0024},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-2.0-mini":{"id":"volcengine/doubao-seed-2.0-mini","name":"Doubao-Seed-2.0-mini","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02-14","release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.03,"output":0.28,"cache_read":0.01,"cache_write":0.0024},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-2.0-pro":{"id":"volcengine/doubao-seed-2.0-pro","name":"Doubao-Seed-2.0-pro","description":"Multimodal reasoning model for visual analysis, planning, and tool use","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2026-02-14","release_date":"2026-02-14","last_updated":"2026-02-14","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"cost":{"input":0.45,"output":2.24,"cache_read":0.09,"cache_write":0.0024},"sourceProvider":"zenmux"},"zenmux/volcengine/doubao-seed-code":{"id":"volcengine/doubao-seed-code","name":"Doubao-Seed-Code","description":"Coding model for repository understanding, refactors, and agentic engineering tasks","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-11","last_updated":"2025-11-11","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"status":"deprecated","cost":{"input":0.17,"output":1.12,"cache_read":0.03},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4":{"id":"x-ai/grok-4","name":"Grok 4","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-09","last_updated":"2025-07-09","modalities":{"input":["image","text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"status":"deprecated","cost":{"input":3,"output":15,"cache_read":0.75},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4-fast":{"id":"x-ai/grok-4-fast","name":"Grok 4 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-19","last_updated":"2025-09-19","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":64000},"status":"deprecated","cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.1-fast":{"id":"x-ai/grok-4.1-fast","name":"Grok 4.1 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":64000},"status":"deprecated","cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.1-fast-non-reasoning":{"id":"x-ai/grok-4.1-fast-non-reasoning","name":"Grok 4.1 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-11-20","last_updated":"2025-11-20","modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":64000},"status":"deprecated","cost":{"input":0.2,"output":0.5,"cache_read":0.05},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.2-fast":{"id":"x-ai/grok-4.2-fast","name":"Grok 4.2 Fast","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":3,"output":9},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.2-fast-non-reasoning":{"id":"x-ai/grok-4.2-fast-non-reasoning","name":"Grok 4.2 Fast Non Reasoning","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":true,"reasoning":false,"tool_call":true,"temperature":true,"knowledge":"2025-08-31","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":2000000,"output":30000},"cost":{"input":3,"output":9},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.3":{"id":"x-ai/grok-4.3","name":"Grok 4.3","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["none","low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-17","last_updated":"2026-04-17","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":1000000},"cost":{"input":1.25,"output":2.5,"cache_read":0.2,"cache_write":0,"tiers":[{"input":2.5,"output":5,"cache_read":0.4,"cache_write":0,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":2.5,"output":5,"cache_read":0.4,"cache_write":0}},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-4.5":{"id":"x-ai/grok-4.5","name":"Grok 4.5","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","family":"grok","attachment":true,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-07-08","last_updated":"2026-07-08","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":500000,"output":500000},"cost":{"input":2,"output":6,"cache_read":0.5,"tiers":[{"input":4,"output":12,"cache_read":1,"tier":{"type":"context","size":200000}}],"context_over_200k":{"input":4,"output":12,"cache_read":1}},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-build-0.1":{"id":"x-ai/grok-build-0.1","name":"Grok Build 0.1","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","family":"grok-build","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-04-16","last_updated":"2026-04-16","modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":256000},"cost":{"input":1,"output":2,"cache_read":0.2},"sourceProvider":"zenmux"},"zenmux/x-ai/grok-code-fast-1":{"id":"x-ai/grok-code-fast-1","name":"Grok Code Fast 1","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-08-26","last_updated":"2025-08-26","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":256000,"output":64000},"status":"deprecated","cost":{"input":0.2,"output":1.5,"cache_read":0.02},"sourceProvider":"zenmux"},"zenmux/xiaomi/mimo-v2-flash":{"id":"xiaomi/mimo-v2-flash","name":"MiMo-V2-Flash","description":"MiMo flash model for fast multimodal assistance and agent workflows","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12-01","release_date":"2025-12-16","last_updated":"2026-02-04","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":262144,"output":65536},"cost":{"input":0.1,"output":0.3,"cache_read":0.01},"sourceProvider":"zenmux"},"zenmux/xiaomi/mimo-v2-omni":{"id":"xiaomi/mimo-v2-omni","name":"MiMo V2 Omni","description":"MiMo omni model for text, image, video, audio, and agents","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":265000,"output":265000},"cost":{"input":0.4,"output":2,"cache_read":0.08},"sourceProvider":"zenmux"},"zenmux/xiaomi/mimo-v2-pro":{"id":"xiaomi/mimo-v2-pro","name":"MiMo V2 Pro","description":"Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2024-12","release_date":"2026-03-18","last_updated":"2026-03-18","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":256000},"cost":{"input":1,"output":3,"cache_read":0.2,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"zenmux"},"zenmux/xiaomi/mimo-v2.5":{"id":"xiaomi/mimo-v2.5","name":"MiMo-V2.5","description":"Open MiMo model for multimodal coding agents and long-context automation","family":"mimo","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":0.4,"output":2,"cache_read":0.08,"tiers":[{"input":0.8,"output":4,"cache_read":0.16,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":0.8,"output":4,"cache_read":0.16}},"sourceProvider":"zenmux"},"zenmux/xiaomi/mimo-v2.5-pro":{"id":"xiaomi/mimo-v2.5-pro","name":"MiMo-V2.5-Pro","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","family":"mimo","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2024-12","release_date":"2026-04-22","last_updated":"2026-04-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1048576,"output":131072},"cost":{"input":1,"output":3,"cache_read":0.2,"tiers":[{"input":2,"output":6,"cache_read":0.4,"tier":{"type":"context","size":256000}}],"context_over_200k":{"input":2,"output":6,"cache_read":0.4}},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.5":{"id":"z-ai/glm-4.5","name":"GLM 4.5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.35,"output":1.54,"cache_read":0.07},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.5-air":{"id":"z-ai/glm-4.5-air","name":"GLM 4.5 Air","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-07-25","last_updated":"2025-07-25","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":128000,"output":64000},"cost":{"input":0.11,"output":0.56,"cache_read":0.02},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.6":{"id":"z-ai/glm-4.6","name":"GLM 4.6","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.35,"output":1.54,"cache_read":0.07},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.6v":{"id":"z-ai/glm-4.6v","name":"GLM 4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.14,"output":0.42,"cache_read":0.03},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.6v-flash":{"id":"z-ai/glm-4.6v-flash","name":"GLM 4.6V FlashX","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.02,"output":0.21,"cache_read":0.0043},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.6v-flash-free":{"id":"z-ai/glm-4.6v-flash-free","name":"GLM 4.6V Flash (Free)","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.7":{"id":"z-ai/glm-4.7","name":"GLM 4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01-01","release_date":"2025-12-23","last_updated":"2025-12-23","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.28,"output":1.14,"cache_read":0.06},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.7-flash-free":{"id":"z-ai/glm-4.7-flash-free","name":"GLM 4.7 Flash (Free)","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01-01","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0,"output":0},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-4.7-flashx":{"id":"z-ai/glm-4.7-flashx","name":"GLM 4.7 FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01-01","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":64000},"cost":{"input":0.07,"output":0.42,"cache_read":0.01},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5":{"id":"z-ai/glm-5","name":"GLM 5","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-01-01","release_date":"2026-02-12","last_updated":"2026-02-12","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":128000},"cost":{"input":0.58,"output":2.6,"cache_read":0.14},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5-turbo":{"id":"z-ai/glm-5-turbo","name":"GLM 5 Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"temperature":true,"knowledge":"2025-01-01","release_date":"2026-03-20","last_updated":"2026-03-20","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.88,"output":3.48},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5.1":{"id":"z-ai/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-04-03","last_updated":"2026-04-03","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0.8781,"output":3.5126,"cache_read":0.1903},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5.2":{"id":"z-ai/glm-5.2","name":"GLM 5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.5,"cache_read":0.26},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5.2-free":{"id":"z-ai/glm-5.2-free","name":"GLM 5.2 (Free)","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0},"sourceProvider":"zenmux"},"zenmux/z-ai/glm-5v-turbo":{"id":"z-ai/glm-5v-turbo","name":"GLM 5V Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","attachment":true,"reasoning":true,"reasoning_options":[],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":128000},"cost":{"input":0.726,"output":3.1946,"cache_read":0.1743},"sourceProvider":"zenmux"},"zhipuai-coding-plan/glm-4.6v":{"id":"zhipuai-coding-plan/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-4.7":{"id":"zhipuai-coding-plan/glm-4.7","name":"GLM-4.7","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5-turbo":{"id":"zhipuai-coding-plan/glm-5-turbo","name":"GLM-5-Turbo","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-16","last_updated":"2026-03-16","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5.1":{"id":"zhipuai-coding-plan/glm-5.1","name":"GLM-5.1","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5.2":{"id":"zhipuai-coding-plan/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5.2-highspeed":{"id":"zhipuai-coding-plan/glm-5.2-highspeed","name":"GLM-5.2 Highspeed","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5.3":{"id":"zhipuai-coding-plan/glm-5.3","name":"GLM-5.3","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["low","high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-08-14","last_updated":"2026-08-14","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai-coding-plan/glm-5v-turbo":{"id":"zhipuai-coding-plan/glm-5v-turbo","name":"GLM-5V-Turbo","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai-coding-plan"},"zhipuai/glm-4.5":{"id":"zhipuai/glm-4.5","name":"GLM-4.5","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.5-air":{"id":"zhipuai/glm-4.5-air","name":"GLM-4.5-Air","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","family":"glm-air","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0.2,"output":1.1,"cache_read":0.03,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.5-flash":{"id":"zhipuai/glm-4.5-flash","name":"GLM-4.5-Flash","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-07-28","last_updated":"2025-07-28","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":131072,"output":98304},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.5v":{"id":"zhipuai/glm-4.5v","name":"GLM-4.5V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-08-11","last_updated":"2025-08-11","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":64000,"output":16384},"cost":{"input":0.6,"output":1.8},"sourceProvider":"zhipuai"},"zhipuai/glm-4.6":{"id":"zhipuai/glm-4.6","name":"GLM-4.6","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-09-30","last_updated":"2025-09-30","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.6v":{"id":"zhipuai/glm-4.6v","name":"GLM-4.6V","description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2025-12-08","last_updated":"2025-12-08","modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"limit":{"context":128000,"output":32768},"cost":{"input":0.3,"output":0.9},"sourceProvider":"zhipuai"},"zhipuai/glm-4.7":{"id":"zhipuai/glm-4.7","name":"GLM-4.7","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"knowledge":"2025-04","release_date":"2025-12-22","last_updated":"2025-12-22","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.7-flash":{"id":"zhipuai/glm-4.7-flash","name":"GLM-4.7-Flash","description":"Budget GLM lane for fast coding help, routing, and everyday automation","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0,"output":0,"cache_read":0,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-4.7-flashx":{"id":"zhipuai/glm-4.7-flashx","name":"GLM-4.7-FlashX","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","family":"glm-flash","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"temperature":true,"knowledge":"2025-04","release_date":"2026-01-19","last_updated":"2026-01-19","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":200000,"output":131072},"cost":{"input":0.07,"output":0.4,"cache_read":0.01,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-5":{"id":"zhipuai/glm-5","name":"GLM-5","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-02-11","last_updated":"2026-02-11","modalities":{"input":["text"],"output":["text"]},"open_weights":true,"limit":{"context":204800,"output":131072},"cost":{"input":1,"output":3.2,"cache_read":0.2,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-5.1":{"id":"zhipuai/glm-5.1","name":"GLM-5.1","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-03-27","last_updated":"2026-03-27","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-5.2":{"id":"zhipuai/glm-5.2","name":"GLM-5.2","description":"Open flagship GLM for long-horizon coding agents and million-token context work","family":"glm","attachment":false,"reasoning":true,"reasoning_options":[{"type":"effort","values":["high","max"]}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"structured_output":true,"temperature":true,"release_date":"2026-06-13","last_updated":"2026-06-13","modalities":{"input":["text"],"output":["text"]},"open_weights":false,"limit":{"context":1000000,"output":131072},"cost":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"sourceProvider":"zhipuai"},"zhipuai/glm-5v-turbo":{"id":"zhipuai/glm-5v-turbo","name":"GLM-5V-Turbo","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","family":"glm","attachment":true,"reasoning":true,"reasoning_options":[{"type":"toggle"}],"tool_call":true,"interleaved":{"field":"reasoning_content"},"temperature":true,"release_date":"2026-04-01","last_updated":"2026-04-01","modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false,"limit":{"context":200000,"output":131072},"cost":{"input":5,"output":22,"cache_read":1.2,"cache_write":0},"sourceProvider":"zhipuai"}}