{
"source": "https://models.dev/api.json",
"fetched_at": "2026-10-22T06:14:35.608Z",
"provider_count": 232,
"model_count": 9142,
"providers": [
{
"id": "bee",
"name": "Bee by HEOSSI",
"env": [
"BEE_API_KEY"
],
"doc": "https://bee.heossi.com/docs/sdks",
"api": "https://api.bee.heossi.com/bee",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "bee-hive",
"name": "Bee Hive 1.0",
"description": "Scalable Bee serving with quantum-reasoning routing and multi-base domain-adapter routing for shared knowledge workflows, document intelligence, and lower-cost cloud inference. Domain adapters activate per customer domain after evaluation.",
"released": "2026-07-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 5,
"output": 20,
"cache_read": 0.5,
"cache_write": 6
}
},
{
"id": "bee-buzz",
"name": "Bee Buzz 1.0",
"description": "Mid-tier production model for tool-using agents, multi-step workflows, and builder/integration work. Bigger context than Comb, deeper planning, faster than Hive on routine tasks.",
"released": "2026-07-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 24576
},
"cost": {
"input": 2.5,
"output": 10,
"cache_read": 0.25,
"cache_write": 3
}
},
{
"id": "bee-comb",
"name": "Bee Comb 2.0",
"description": "Stronger local/workstation AI for coding, architecture, security reasoning, larger RAG, and domain-specific workflows. The default workhorse for engineers and dev teams.",
"released": "2026-07-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 16384
},
"cost": {
"input": 1.25,
"output": 5,
"cache_read": 0.125,
"cache_write": 1.5
}
},
{
"id": "bee-brood",
"name": "Bee Brood 1.0",
"description": "Production multimodal reasoning for image and video analysis, tool-enabled workflows, and multi-step planning at controlled cost.",
"released": "2026-07-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 16384
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.72
}
},
{
"id": "bee-cell",
"name": "Bee Cell 1.0",
"description": "Fast hosted AI for chat, coding help, document question answering, image understanding, and lightweight technical reasoning.",
"released": "2026-07-10",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.03,
"cache_write": 0.36
}
},
{
"id": "bee-swarm",
"name": "Bee Swarm 1.0",
"description": "Premium reasoning, multi-model cloud execution, large-document analysis, and high-value technical work. Includes the evolution engine and stronger eval gates by default.",
"released": "2026-07-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-09-28",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 25,
"output": 150,
"cache_read": 2.5,
"cache_write": 30
}
}
]
},
{
"id": "aki-io",
"name": "AKI.IO",
"env": [
"AKI_IO_API_KEY"
],
"doc": "https://aki.io/docs/",
"api": "https://aki.io/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-v4.1-flash-552b",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 81920
},
"cost": {
"input": 0.280375,
"output": 1.1215,
"cache_read": 0.11215
}
},
{
"id": "qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.33645,
"output": 2.4673,
"cache_read": 0.11215
}
},
{
"id": "glm5.3-754b",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 81920
},
"cost": {
"input": 1.1215,
"output": 3.92525,
"cache_read": 0.280375
}
},
{
"id": "qwen3.6-35b",
"name": "Qwen3.6 35B-A3B",
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
"released": "2026-04-17",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-17",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 32768
},
"cost": {
"input": 0.168225,
"output": 0.56075
}
},
{
"id": "gemma4-26b",
"name": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"released": "2026-04-02",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 32768
},
"cost": {
"input": 0.11215,
"output": 0.56075
}
},
{
"id": "mistral4-119b",
"name": "Mistral Small 4",
"description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
"released": "2026-03-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-16",
"family": "mistral-small",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 81920
},
"cost": {
"input": 0.2243,
"output": 0.6729
}
},
{
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0.168225,
"output": 0.616825
}
}
]
},
{
"id": "gitlab",
"name": "GitLab Duo",
"env": [
"GITLAB_TOKEN"
],
"doc": "https://docs.gitlab.com/user/duo_agent_platform/",
"npm": "gitlab-ai-provider",
"models": [
{
"id": "duo-chat-gpt-6-1-sol",
"name": "Agentic Chat (GPT-6.1 Sol)",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-sonnet-5-5",
"name": "Agentic Chat (Claude Sonnet 5.5)",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-opus-5-5",
"name": "Agentic Chat (Claude Opus 5.5)",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-6-sol",
"name": "Agentic Chat (GPT-6 Sol)",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-6-luna",
"name": "Agentic Chat (GPT-6 Luna)",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-6-astra",
"name": "Agentic Chat (GPT-6 Astra)",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-fable-5-1",
"name": "Agentic Chat (Claude Fable 5.1)",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-opus-5",
"name": "Agentic Chat (Claude Opus 5)",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-sonnet-5",
"name": "Agentic Chat (Claude Sonnet 5)",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-fable-5",
"name": "Agentic Chat (Claude Fable 5)",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-opus-4-8",
"name": "Agentic Chat (Claude Opus 4.8)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-5-5",
"name": "Agentic Chat (GPT-5.5)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-opus-4-7",
"name": "Agentic Chat (Claude Opus 4.7)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-gpt-5-4",
"name": "Agentic Chat (GPT-5.4)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-sonnet-4-6",
"name": "Agentic Chat (Claude Sonnet 4.6)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-opus-4-6",
"name": "Agentic Chat (Claude Opus 4.6)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-5-2",
"name": "Agentic Chat (GPT-5.2)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-opus-4-5",
"name": "Agentic Chat (Claude Opus 4.5)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-5-1",
"name": "Agentic Chat (GPT-5.1)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-haiku-4-5",
"name": "Agentic Chat (Claude Haiku 4.5)",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-sonnet-4-5",
"name": "Agentic Chat (Claude Sonnet 4.5)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "duo-chat-gpt-5-codex",
"name": "Agentic Chat (GPT-5 Codex)",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-09-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "duo-chat-gpt-5-mini",
"name": "Agentic Chat (GPT-5 Mini)",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "routing-run",
"name": "routing.run",
"env": [
"ROUTING_RUN_API_KEY"
],
"doc": "https://docs.routing.run/api-reference/models",
"api": "https://api.routing.run/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.5,
"output": 15
}
},
{
"id": "gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.7,
"output": 4.2
}
},
{
"id": "gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 1.5,
"output": 9
}
},
{
"id": "glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.8,
"output": 2.4
}
},
{
"id": "glm-5.2-nitro",
"name": "GLM 5.2 Nitro",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.8,
"output": 2.4
}
},
{
"id": "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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.275,
"output": 1.1
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.275,
"output": 1.1
}
},
{
"id": "nemotron-3-ultra",
"name": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"released": "2026-06-04",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-06-04",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32000
},
"cost": {
"input": 0.1,
"output": 0.1
}
},
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 32000
},
"cost": {
"input": 5,
"output": 25
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0.112,
"output": 0.224
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0.348,
"output": 0.696
}
},
{
"id": "kimi-k2.6-nitro",
"name": "Kimi K2.6 Nitro",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.275,
"output": 1.1
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.275,
"output": 1.1
}
},
{
"id": "qwen3.5-9b",
"name": "Qwen3.5 9B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32000
},
"cost": {
"input": 0.16,
"output": 0.48
}
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15
}
}
]
},
{
"id": "kimi-code-plan-cn",
"name": "Kimi For Coding (kimi.com)",
"env": [
"KIMI_API_KEY"
],
"doc": "https://www.kimi.com/code/docs/en/kimi-code/models.html",
"api": "https://api.kimi.com/coding/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "kimi-for-coding",
"name": "Kimi K2.8 Preview",
"description": "Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "k3-256k",
"name": "Kimi K3-256K",
"description": "256K-context version of Kimi K3, reducing token consumption for shorter coding sessions",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "kimi-for-coding-highspeed",
"name": "Kimi For Coding HighSpeed",
"description": "Lower-latency Kimi Code variant for interactive edits and coding-agent loops",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
}
]
},
{
"id": "ovhcloud",
"name": "OVHcloud AI Endpoints",
"env": [
"OVHCLOUD_API_KEY"
],
"doc": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog//",
"api": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "qwen3.8-27b",
"name": "Qwen3.8-27B",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.47,
"output": 3.19
}
},
{
"id": "qwen3.6-27b",
"name": "Qwen3.6-27B",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-22",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.47,
"output": 3.19
}
},
{
"id": "qwen3.5-9b",
"name": "Qwen3.5-9B",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.12,
"output": 0.18
}
},
{
"id": "qwen3.5-397b-a17b",
"name": "Qwen3.5-397B-A17B",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-02-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-15",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.71,
"output": 4.25
}
},
{
"id": "qwen3guard-gen-0.6b",
"name": "Qwen3Guard-Gen-0.6B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"released": "2026-01-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-01-22",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 16384
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen3guard-gen-8b",
"name": "Qwen3Guard-Gen-8B",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"released": "2026-01-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-01-22",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 16384
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "gpt-oss-20b",
"name": "gpt-oss-20b",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.05,
"output": 0.18
}
},
{
"id": "gpt-oss-120b",
"name": "gpt-oss-120b",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.09,
"output": 0.47
}
},
{
"id": "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",
"released": "2025-06-20",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10-31",
"last_updated": "2025-06-20",
"family": "mistral-small",
"modalities": {
"input": [
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.1,
"output": 0.31
}
},
{
"id": "qwen2.5-vl-72b-instruct",
"name": "Qwen2.5-VL-72B-Instruct",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"released": "2025-01-26",
"attachment": true,
"reasoning": false,
"tool_call": false,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-01-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 32768
},
"cost": {
"input": 1.01,
"output": 1.01
}
},
{
"id": "meta-llama-3_3-70b-instruct",
"name": "Meta-Llama-3_3-70B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.74,
"output": 0.74
}
},
{
"id": "mistral-nemo-instruct-2407",
"name": "Mistral-Nemo-Instruct-2407",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"released": "2024-07-18",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2024-07-18",
"family": "mistral-nemo",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 65536,
"output": 65536
},
"cost": {
"input": 0.14,
"output": 0.14
}
}
]
},
{
"id": "xiaomi-token-plan-cn",
"name": "Xiaomi Token Plan (China)",
"env": [
"XIAOMI_API_KEY"
],
"doc": "https://platform.xiaomimimo.com/#/docs",
"api": "https://token-plan-cn.xiaomimimo.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.5-tts-voicedesign",
"name": "MiMo-V2.5-TTS-VoiceDesign",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2.5-tts-voiceclone",
"name": "MiMo-V2.5-TTS-VoiceClone",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2.5-tts",
"name": "MiMo-V2.5-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-04-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2-tts",
"name": "MiMo-V2-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-03-18",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-03-18",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-03-18",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
}
]
},
{
"id": "fireworks-ai",
"name": "Fireworks AI",
"env": [
"FIREWORKS_API_KEY"
],
"doc": "https://fireworks.ai/docs/",
"api": "https://api.fireworks.ai/inference/v1/",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "accounts/fireworks/routers/deepseek-flash-latest",
"name": "DeepSeek Flash Latest",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "accounts/fireworks/models/deepseek-v4p1-flash-1017",
"name": "DeepSeek V4.1 Flash 1017",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "accounts/fireworks/models/muse-spark-open",
"name": "Muse Spark Open",
"description": "Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01-04",
"last_updated": "2026-10-15",
"family": "muse",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"id": "accounts/fireworks/models/ember-1",
"name": "Ember-1",
"description": "Specialized model from Fireworks built on Kimi K3, producing shorter reasoning traces with approximately 40% fewer tokens while maintaining comparable quality",
"released": "2026-09-22",
"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,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-22",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "accounts/fireworks/models/deepseek-v4p1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "accounts/fireworks/routers/glm-flash-latest",
"name": "GLM Flash Latest (GLM 5.3 Flash)",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048573,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03
}
},
{
"id": "accounts/fireworks/models/glm-5p3-flash",
"name": "GLM 5.3 Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048573,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03
}
},
{
"id": "accounts/fireworks/routers/glm-fast-latest",
"name": "GLM 5.3 Fast (Latest)",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048572,
"output": 262144
},
"cost": {
"input": 2.1,
"output": 6.6,
"cache_read": 0.39
}
},
{
"id": "accounts/fireworks/routers/glm-latest",
"name": "GLM Latest",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048573,
"output": 262144
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "accounts/fireworks/routers/glm-5p3-fast",
"name": "GLM 5.3 Fast",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048572,
"output": 262144
},
"cost": {
"input": 2.1,
"output": 6.6,
"cache_read": 0.39
}
},
{
"id": "accounts/fireworks/models/glm-5p3",
"name": "GLM 5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048573,
"output": 262144
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "accounts/fireworks/models/qwen3p8-2p4t-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",
"released": "2026-08-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-12",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25
}
},
{
"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",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-08-11",
"family": "nemotron",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.05,
"output": 0.2,
"cache_read": 0.01
}
},
{
"id": "accounts/fireworks/routers/qwen-max-latest",
"name": "Qwen Max Latest (Qwen3.8 Max)",
"description": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-03",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25
}
},
{
"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",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-03",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25
}
},
{
"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",
"released": "2026-07-16",
"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,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 4.5,
"output": 22.5,
"cache_read": 0.45
}
},
{
"id": "accounts/fireworks/routers/kimi-latest",
"name": "Kimi Latest",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"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,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "accounts/fireworks/routers/kimi-fast-latest",
"name": "Kimi Fast Latest",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"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,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 4.5,
"output": 22.5,
"cache_read": 0.45
}
},
{
"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",
"released": "2026-07-16",
"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,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "accounts/fireworks/models/inkling",
"name": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-15",
"family": "ling",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 1,
"output": 4.05,
"cache_read": 0.17
}
},
{
"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",
"released": "2026-06-04",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-06-04",
"family": "nemotron",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 128000
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.12
}
},
{
"id": "accounts/fireworks/routers/minimax-latest",
"name": "MiniMax Latest",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512000,
"output": 512000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"id": "accounts/fireworks/models/minimax-m3",
"name": "MiniMax-M3",
"description": "Fireworks text-only MiniMax coding model for long-context reasoning and agent tasks",
"released": "2026-06-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512000,
"output": 512000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"id": "accounts/fireworks/models/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.015
}
}
]
},
{
"id": "zeldoc",
"name": "Zeldoc",
"env": [
"ZELDOC_API_KEY"
],
"doc": "https://docs.zeldoc.ai",
"api": "https://api.zeldoc.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "zdev",
"name": "ZDev",
"description": "Coding model for repository understanding, refactors, and agentic engineering tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "perplexity-agent",
"name": "Perplexity Agent",
"env": [
"PERPLEXITY_API_KEY"
],
"doc": "https://docs.perplexity.ai/docs/agent-api/models",
"api": "https://api.perplexity.ai/v1",
"npm": "@ai-sdk/openai",
"models": [
{
"id": "perplexity/nemotron-3.5-super-120b-a12b",
"name": "Nemotron 3.5 Super 120B A12B",
"description": "NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input",
"released": "2026-10-15",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-10-15",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.04
}
},
{
"id": "google/gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1
}
},
{
"id": "anthropic/claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "openai/gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2
}
}
},
{
"id": "anthropic/claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "openai/gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.4
}
}
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02
}
}
},
{
"id": "xai/grok-4.7",
"name": "Grok 4.7",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 4,
"output": 12,
"cache_read": 1
}
}
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2
}
}
},
{
"id": "google/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "anthropic/claude-fable-5-1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "perplexity/glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03
}
},
{
"id": "perplexity/glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "google/gemini-3.7-flash",
"name": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "perplexity/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",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.32,
"output": 3.96,
"cache_read": 0.044
}
},
{
"id": "xai/grok-4.6",
"name": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.13,
"output": 0.26,
"cache_read": 0.028
}
},
{
"id": "anthropic/claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "google/gemini-3.6-flash",
"name": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5,
"output": 7.5,
"cache_read": 0.15
}
},
{
"id": "perplexity/kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"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",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 8,
"output": 30,
"cache_read": 0.8
}
}
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.4,
"output": 1.8,
"cache_read": 0.04
}
}
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 18,
"cache_read": 0.4
}
}
},
{
"id": "xai/grok-4.5",
"name": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-07-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-08",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 0.5
}
},
{
"id": "anthropic/claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "nvidia/nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super 120B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"released": "2026-03-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-02",
"last_updated": "2026-03-11",
"family": "nemotron",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 32000
},
"cost": {
"input": 0.25,
"output": 2.5
}
},
{
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.5,
"output": 15,
"cache_read": 0.25
}
},
{
"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",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "anthropic/claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "google/gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"released": "2025-12-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-12-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "anthropic/claude-opus-4-5",
"name": "Claude Opus 4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "xai/grok-4-1-fast-non-reasoning",
"name": "Grok 4.1 Fast (Non-Reasoning)",
"description": "xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses",
"released": "2025-11-19",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07",
"last_updated": "2025-11-19",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 30000
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "anthropic/claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "anthropic/claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"id": "perplexity/sonar",
"name": "Sonar",
"description": "Fast web-grounded Sonar for current answers, citations, and lightweight retrieval",
"released": "2024-01-01",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-09-01",
"last_updated": "2025-09-01",
"family": "sonar",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.25,
"output": 2.5,
"cache_read": 0.0625
}
}
]
},
{
"id": "crusoe",
"name": "Crusoe",
"env": [
"CRUSOE_API_KEY"
],
"doc": "https://docs.crusoecloud.com/managed-inference/overview",
"api": "https://api.inference.crusoecloud.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "zai/GLM-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"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",
"released": "2026-04-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-28",
"family": "nemotron",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 1.83,
"cache_read": 0.3
}
},
{
"id": "moonshotai/Kimi-K2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.7,
"output": 3.5,
"cache_read": 0.35
}
},
{
"id": "zai/GLM-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.2,
"output": 4.4,
"cache_read": 0.25
}
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.14,
"output": 0.4,
"cache_read": 0.14
}
},
{
"id": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B",
"name": "Nemotron 3 Super 120B A12B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"released": "2026-03-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.3,
"output": 2.4,
"cache_read": 0.15
}
},
{
"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",
"released": "2025-12-15",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06-25",
"last_updated": "2025-12-15",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.05,
"output": 0.2,
"cache_read": 0.03
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.05,
"output": 0.25,
"cache_read": 0.05
}
},
{
"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",
"released": "2025-07-21",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-07-21",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 16384
},
"cost": {
"input": 0.22,
"output": 0.8,
"cache_read": 0.11
}
},
{
"id": "deepseek-ai/DeepSeek-V3-0324",
"name": "DeepSeek V3 0324",
"description": "March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding",
"released": "2025-03-24",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-03-24",
"family": "deepseek",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 163840,
"output": 163840
},
"cost": {
"input": 0.5,
"output": 1.5,
"cache_read": 0.25
}
},
{
"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",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.25,
"output": 0.75,
"cache_read": 0.13
}
}
]
},
{
"id": "coralbricks",
"name": "CoralBricks",
"env": [
"CORAL_API_KEY"
],
"doc": "https://www.coralbricks.ai/docs",
"api": "https://inference.coralbricks.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-v4.1-flash-fast",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.25,
"output": 1.2,
"cache_read": 0.005,
"cache_write": 0
}
}
]
},
{
"id": "groq",
"name": "Groq",
"env": [
"GROQ_API_KEY"
],
"doc": "https://console.groq.com/docs/models",
"npm": "@ai-sdk/groq",
"models": [
{
"id": "qwen/qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"default",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"status": "beta",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 16384
},
"cost": {
"input": 0.8,
"output": 4
}
},
{
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"default"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-22",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 16384
},
"cost": {
"input": 0.6,
"output": 3,
"cache_read": 0.3
}
},
{
"id": "canopylabs/orpheus-v1-english",
"name": "Canopy Labs Orpheus V1 English",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2025-12-19",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-19",
"family": "canopylabs",
"status": "beta",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.groq.com/openai/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 4000,
"output": 50000
}
},
{
"id": "canopylabs/orpheus-arabic-saudi",
"name": "Canopy Labs Orpheus Arabic Saudi",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2025-12-16",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-16",
"family": "canopylabs",
"status": "beta",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.groq.com/openai/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 4000,
"output": 50000
}
},
{
"id": "openai/gpt-oss-safeguard-20b",
"name": "Safety GPT OSS 20B",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"released": "2025-10-29",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-10-29",
"family": "gpt-oss",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 0.075,
"output": 0.3,
"cache_read": 0.0375
}
},
{
"id": "groq/compound-mini",
"name": "Compound Mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2025-09-04",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2025-09-04",
"family": "groq",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
}
},
{
"id": "groq/compound",
"name": "Compound",
"description": "General-purpose chat model for instruction following, writing, and analysis",
"released": "2025-09-04",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2025-09-04",
"family": "groq",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
}
},
{
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 0.075,
"output": 0.3,
"cache_read": 0.0375
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075
}
},
{
"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",
"released": "2025-04-29",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2025-04-29",
"family": "llama",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 512
},
"cost": {
"input": 0.03,
"output": 0.03
}
},
{
"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",
"released": "2025-04-29",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2025-04-29",
"family": "llama",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 512
},
"cost": {
"input": 0.04,
"output": 0.04
}
},
{
"id": "allam-2-7b",
"name": "ALLaM-2-7b",
"description": "ALLaM-2-7b instruction tuned model by SDAIA",
"released": "2025-01-23",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2025-01-23",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 4096,
"output": 4096
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "llama-3.3-70b-versatile",
"name": "Llama 3.3 70B",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.59,
"output": 0.79
}
},
{
"id": "whisper-large-v3-turbo",
"name": "Whisper Large V3 Turbo",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"released": "2024-10-01",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2024-10-01",
"family": "whisper",
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 448,
"output": 448
}
},
{
"id": "llama-3.1-8b-instant",
"name": "Llama 3.1 8B",
"description": "Compact Llama instruction model for fast chat and local deployment",
"released": "2024-07-23",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-07-23",
"family": "llama",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.05,
"output": 0.08
}
},
{
"id": "whisper-large-v3",
"name": "Whisper",
"description": "Speech transcription model for accurate audio-to-text and captioning workflows",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2023-11-06",
"family": "whisper",
"modalities": {
"input": [
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 448,
"output": 448
}
}
]
},
{
"id": "llmtech",
"name": "LLM Tech",
"env": [
"LLMTECH_API_KEY"
],
"doc": "https://llmtech.eu/models/qwen3.8-27b",
"api": "https://api.llmtech.eu/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "nvidia/Qwen3.8-27B-NVFP4",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.25,
"output": 2.09,
"cache_read": 0.04
}
}
]
},
{
"id": "impossibl",
"name": "Impossibl",
"env": [
"IMPOSSIBL_API_KEY"
],
"doc": "https://impossibl.com/docs/models",
"api": "https://api.impossibl.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "google/gemini-3.6-flash",
"name": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "google/gemini-3.5-flash-lite",
"name": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"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",
"released": "2026-07-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-19",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 2.5,
"output": 7.5
}
},
{
"id": "moonshotai/kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "thinkingmachines/inkling",
"name": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-15",
"family": "ling",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 65536,
"output": 65536
},
"cost": {
"input": 1.87,
"output": 4.68,
"cache_read": 0.374
}
},
{
"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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "xai/grok-4.5",
"name": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-07-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-08",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "fireworks/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.14
}
},
{
"id": "zai/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-06-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"released": "2026-05-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-21",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 2.5,
"output": 7.5,
"cache_read": 0.5
}
},
{
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5,
"output": 9,
"cache_read": 0.15
}
},
{
"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",
"released": "2026-05-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-07",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.25,
"output": 1.5,
"cache_read": 0.025
}
},
{
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-27",
"family": "qwen3.6",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.19,
"output": 0.51,
"cache_read": 0.028
}
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.74,
"output": 3.48,
"cache_read": 0.145
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.003
}
},
{
"id": "xai/grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "xai/grok-build-0.1",
"name": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-16",
"family": "grok-build",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "zai/glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "zai/glm-5-turbo",
"name": "GLM-5-Turbo",
"description": "Faster GLM-5 lane for coding agents that need lower latency",
"released": "2026-03-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-16",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.2,
"output": 4,
"cache_read": 0.24
}
},
{
"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",
"released": "2026-03-09",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-09",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "xai/grok-4.20-0309-reasoning",
"name": "Grok 4.20 (Reasoning)",
"description": "Reasoning Grok for document-heavy analysis and long-horizon tool use",
"released": "2026-03-09",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-09",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "zai/glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 1,
"output": 3.2,
"cache_read": 0.2
}
},
{
"id": "anthropic/claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "zai/glm-4.7",
"name": "GLM-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.6,
"output": 2.2,
"cache_read": 0.11
}
},
{
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"description": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "anthropic/claude-opus-4-5",
"name": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"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",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"description": "Codex GPT for repository edits, code review, and practical software agents",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "anthropic/claude-haiku-4-5",
"name": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "openai/gpt-5-pro",
"name": "GPT-5 Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"released": "2025-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-10-06",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 272000
},
"cost": {
"input": 15,
"output": 120
}
},
{
"id": "zai/glm-4.6",
"name": "GLM-4.6",
"description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
"released": "2025-09-30",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-09-30",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.6,
"output": 2.2,
"cache_read": 0.11
}
},
{
"id": "anthropic/claude-sonnet-4-5",
"name": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "openai/gpt-5-codex",
"name": "GPT-5-Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-09-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.05,
"output": 0.4,
"cache_read": 0.005
}
},
{
"id": "openai/gpt-5",
"name": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "groq/gpt-oss-20b",
"name": "GPT OSS 20B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.075,
"output": 0.3,
"cache_read": 0.0375
}
},
{
"id": "groq/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075
}
},
{
"id": "fireworks/gpt-oss-20b",
"name": "GPT OSS 20B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.07,
"output": 0.3,
"cache_read": 0.035
}
},
{
"id": "fireworks/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.015
}
},
{
"id": "cerebras/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.35,
"output": 0.75
}
},
{
"id": "zai/glm-4.5",
"name": "GLM-4.5",
"description": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful",
"released": "2025-07-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-07-28",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 98304
},
"cost": {
"input": 0.6,
"output": 2.2,
"cache_read": 0.11
}
},
{
"id": "zai/glm-4.5-air",
"name": "GLM-4.5-Air",
"description": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents",
"released": "2025-07-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-07-28",
"family": "glm-air",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 98304
},
"cost": {
"input": 0.2,
"output": 1.1,
"cache_read": 0.03
}
},
{
"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",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 512,
"max": 24576
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01
}
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 128,
"max": 32768
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"id": "openai/o3",
"name": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"id": "openai/o4-mini",
"name": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.275
}
},
{
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1 mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.4,
"output": 1.6,
"cache_read": 0.1
}
},
{
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"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",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.025
}
},
{
"id": "openai/o3-mini",
"name": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"released": "2024-12-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-01-29",
"family": "o-mini",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.55
}
},
{
"id": "openai/o1",
"name": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"released": "2024-12-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-12-05",
"family": "o",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 15,
"output": 60,
"cache_read": 7.5
}
},
{
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075
}
},
{
"id": "openai/gpt-4o",
"name": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"released": "2024-05-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-08-06",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 2.5,
"output": 10,
"cache_read": 1.25
}
},
{
"id": "openai/gpt-4-turbo",
"name": "GPT-4 Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-04-09",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 10,
"output": 30
}
},
{
"id": "openai/gpt-3.5-turbo",
"name": "GPT-3.5-turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-03-01",
"attachment": false,
"reasoning": false,
"tool_call": false,
"structured_output": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-09-01",
"last_updated": "2023-11-06",
"family": "gpt",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 16385,
"output": 4096
},
"cost": {
"input": 0.5,
"output": 1.5
}
}
]
},
{
"id": "hpc-ai",
"name": "HPC-AI",
"env": [
"HPC_AI_API_KEY"
],
"doc": "https://www.hpc-ai.com/doc/docs/quickstart/",
"api": "https://api.hpc-ai.com/inference/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "zai-org/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 128000
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.028
}
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1002000,
"output": 128000
},
"cost": {
"input": 1.74,
"output": 3.48,
"cache_read": 0.145
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-opus-4.7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5
}
},
{
"id": "zai-org/glm-5.1",
"name": "GLM 5.1",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202000,
"output": 202000
},
"cost": {
"input": 0.615,
"output": 2.46,
"cache_read": 0.133
}
},
{
"id": "minimax/minimax-m2.5",
"name": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 196000,
"output": 195000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.03
}
},
{
"id": "moonshotai/kimi-k2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.6,
"output": 3,
"cache_read": 0.1
}
}
]
},
{
"id": "claudinio",
"name": "Claudinio",
"env": [
"CLAUDINIO_API_KEY"
],
"doc": "https://claudin.io",
"api": "https://api.claudin.io/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "claudinio",
"name": "Claudinio",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-05-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"knowledge": "2026-05",
"last_updated": "2026-06-02",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 64000
},
"cost": {
"input": 0.5,
"output": 2,
"cache_read": 0.15
}
},
{
"id": "claudius",
"name": "Claudius",
"description": "Multimodal reasoning model for visual analysis, planning, and tool use",
"released": "2026-05-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"knowledge": "2026-05",
"last_updated": "2026-05-12",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 64000
},
"cost": {
"input": 3,
"output": 8,
"cache_read": 0.9
}
}
]
},
{
"id": "nan",
"name": "NaN",
"env": [
"NAN_API_KEY"
],
"doc": "https://nan.builders/docs/models",
"api": "https://api.nan.builders/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen-image-2.1",
"name": "Qwen-Image-2.1",
"description": "Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing",
"released": "2026-09-14",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2026-09-21",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 8192,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "glm5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "glm5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen3.6",
"name": "Qwen3.6 35B-A3B",
"description": "Open multimodal Qwen MoE for local agents that need vision, audio, and code",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-17",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "gemma4",
"name": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "moonshotai-cn",
"name": "Moonshot AI (China)",
"env": [
"MOONSHOT_API_KEY"
],
"doc": "https://platform.moonshot.cn/docs/api/chat",
"api": "https://api.moonshot.cn/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 2.9879,
"output": 14.9395,
"cache_read": 0.2988,
"cache_write": 2.9879
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.9711,
"output": 4.0337,
"cache_read": 0.1942
}
},
{
"id": "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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 1.9421,
"output": 8.0673,
"cache_read": 0.3884
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.9711,
"output": 4.0337,
"cache_read": 0.1643
}
}
]
},
{
"id": "aixy",
"name": "Aixy",
"env": [
"AIXY_API_KEY"
],
"doc": "https://docs.aixy-gateway.com/integrations/overview",
"api": "https://api.aixy-gateway.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "gemini/gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1
}
},
{
"id": "anthropic/claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://api.aixy-gateway.com/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.625,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "openai/gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5
}
}
},
{
"id": "anthropic/claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://api.aixy-gateway.com/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://api.aixy-gateway.com/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "openai/gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "gemini/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "anthropic/claude-fable-5-1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://api.aixy-gateway.com/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"provider": {
"npm": "@ai-sdk/openai",
"api": "https://api.aixy-gateway.com/v1",
"shape": "responses"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
}
]
},
{
"id": "standardcompute",
"name": "Standard Compute",
"env": [
"STANDARDCOMPUTE_API_KEY"
],
"doc": "https://docs.standardcompute.com/models",
"api": "https://api.stdcmpt.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "anthropic/claude-haiku-5.5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.625,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "mistralai/mistral-large-4-0",
"name": "Mistral Large 4",
"description": "Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work",
"released": "2026-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-06",
"family": "mistral-large",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.68,
"output": 2.09,
"cache_read": 0.07
}
},
{
"id": "anthropic/claude-sonnet-5.5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-opus-5.5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "xiaomi/mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.43,
"output": 0.87,
"cache_read": 0.0036
}
},
{
"id": "xiaomi/mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.0028
}
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.14,
"output": 0.42,
"cache_read": 0.0042
}
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "google/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.041667
}
},
{
"id": "qwen/qwen3.8-max-0902",
"name": "Qwen3.8 Max 0902",
"description": "2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-fable-5.1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "z-ai/glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.08,
"output": 0.5,
"cache_read": 0.012
}
},
{
"id": "qwen/qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens",
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.15,
"output": 0.47,
"cache_read": 0.016,
"cache_write": 0.2
}
},
{
"id": "z-ai/glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "qwen/qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.425,
"output": 2.55,
"cache_read": 0.085,
"cache_write": 0.53125
}
},
{
"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",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 1.122,
"output": 3.366,
"cache_read": 0.1122
}
},
{
"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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.44,
"output": 1.32,
"cache_read": 0.014
}
},
{
"id": "anthropic/claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "google/gemini-3.5-flash-lite",
"name": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03,
"cache_write": 0.083333
}
},
{
"id": "moonshotai/kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "qwen/qwen3.7-flash",
"name": "Qwen3.7 Flash",
"description": "Lightweight multimodal Qwen model for high-throughput text, image, and video tasks",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-15",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"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
}
}
]
}
},
{
"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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 850000,
"output": 50000
},
"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
}
}
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 850000,
"output": 50000
},
"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
}
}
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 850000,
"output": 50000
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "z-ai/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.5625,
"output": 1.8,
"cache_read": 0.105
}
},
{
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-06-02",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"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
}
}
},
{
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"released": "2026-05-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-21",
"family": "qwen",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 1.475,
"output": 4.425,
"cache_read": 0.295,
"cache_write": 1.84375
}
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.0826,
"output": 0.1652,
"cache_read": 0.01652
}
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
},
"cost": {
"input": 1.044,
"output": 2.088,
"cache_read": 0.2088
}
},
{
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.0028
}
},
{
"id": "xiaomi/mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-04-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.435,
"output": 0.87,
"cache_read": 0.0036
}
},
{
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"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
}
}
},
{
"id": "standardcompute",
"name": "Standard Compute",
"description": "Flat-rate smart-routing gateway: one model id, each request routed across the customer's enabled models from a curated ~1M-context catalog (Claude, GPT, Gemini, DeepSeek, GLM, Qwen, Kimi, MiniMax, Grok, MiMo) or pinned to a user-selected model",
"released": "2026-03-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-13",
"family": "auto",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 850000,
"output": 50000
}
},
{
"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",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 2,
"output": 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
}
}
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 128,
"max": 32768
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 1.25,
"output": 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
}
}
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"provider": {
"npm": "@openrouter/ai-sdk-provider"
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"input": 850000,
"output": 50000
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03,
"cache_write": 0.083333
}
}
]
},
{
"id": "liquid",
"name": "Liquid Inference",
"env": [
"LIQUID_API_KEY"
],
"doc": "https://inference.ai.exchange/docs",
"api": "https://router.inference.ai.exchange/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "liquid.auto",
"name": "Liquid Auto",
"description": "Routes each request to the lowest-priced eligible offer on the Liquid Inference exchange",
"released": "2026-10-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-20",
"family": "auto",
"modalities": {
"input": [
"text",
"image",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 10000000,
"output": 1048576
}
}
]
},
{
"id": "zhipuai-coding-plan",
"name": "Zhipu AI Coding Plan",
"env": [
"ZHIPU_API_KEY"
],
"doc": "https://docs.bigmodel.cn/cn/coding-plan/overview",
"api": "https://open.bigmodel.cn/api/coding/paas/v4",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.3-highspeed",
"name": "GLM-5.3 Highspeed",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-4.6v",
"name": "GLM-4.6V",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"released": "2025-12-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-08",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
}
]
},
{
"id": "auriko",
"name": "Auriko",
"env": [
"AURIKO_API_KEY"
],
"doc": "https://docs.auriko.ai",
"api": "https://api.auriko.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.0028
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.32,
"output": 3.96,
"cache_read": 0.044
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.16
}
},
{
"id": "grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "qwen-3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-04-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "minimax-m2-7",
"name": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06,
"cache_write": 0.375
}
},
{
"id": "minimax-m2-7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"description": "Low-latency M2.7 variant for interactive coding plans and agent loops",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.375
}
},
{
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.45,
"output": 2.25,
"cache_read": 0.07
}
},
{
"id": "gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
}
]
},
{
"id": "requesty",
"name": "Requesty",
"env": [
"REQUESTY_API_KEY"
],
"doc": "https://requesty.ai/solution/llm-routing/models",
"api": "https://router.requesty.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "minimax-m3.1-flash",
"name": "MiniMax-M3.1-Flash",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"released": "2026-10-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-19",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.015
}
},
{
"id": "deepseek-v4.1-flash-1017",
"name": "DeepSeek V4.1 Flash 1017",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.5,
"output": 1.5,
"cache_read": 0.05
}
},
{
"id": "deepseek-v4.1-flash-1017@eu",
"name": "DeepSeek V4.1 Flash 1017 (EU)",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.5,
"output": 1.5,
"cache_read": 0.05
}
},
{
"id": "muse-spark-open",
"name": "Muse Spark Open",
"description": "Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01-04",
"last_updated": "2026-10-15",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"id": "gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1
}
},
{
"id": "gemini-4-argon@eu",
"name": "Gemini 4 Argon (EU)",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 2.2,
"output": 11,
"cache_read": 0.11
}
},
{
"id": "muse-wonder-1.0",
"name": "Muse Wonder",
"description": "Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.",
"released": "2026-10-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-12",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2
}
},
{
"id": "claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.13,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.63,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "claude-haiku-5-5@eu",
"name": "Claude Haiku 5.5 (EU)",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.11,
"output": 0.55,
"cache_read": 0.02,
"cache_write": 0.14,
"tiers": [
{
"input": 0.55,
"output": 2.75,
"cache_read": 0.06,
"cache_write": 0.69,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "mistral-large-4@eu",
"name": "Mistral Large 4 (EU)",
"description": "Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work",
"released": "2026-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-06",
"family": "mistral-large",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 262144
},
"cost": {
"input": 0.68,
"output": 2.09,
"cache_read": 0.07
}
},
{
"id": "mistral-large-4",
"name": "Mistral Large 4",
"description": "Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work",
"released": "2026-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-06",
"family": "mistral-large",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 262144
},
"cost": {
"input": 0.68,
"output": 2.09,
"cache_read": 0.07
}
},
{
"id": "gpt-6.1-sol@eu",
"name": "GPT-6.1 Sol (EU)",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.4,
"output": 12,
"cache_read": 0.12,
"cache_write": 3,
"tiers": [
{
"input": 4.8,
"output": 18,
"cache_read": 0.24,
"cache_write": 6,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4.8,
"output": 18,
"cache_read": 0.24,
"cache_write": 6
}
}
},
{
"id": "gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5
}
}
},
{
"id": "claude-sonnet-5-5@eu",
"name": "Claude Sonnet 5.5 (EU)",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2.2,
"output": 11,
"cache_read": 0.22,
"cache_write": 2.75
}
},
{
"id": "claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.43,
"output": 0.87,
"cache_read": 0.0036
}
},
{
"id": "mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.0027
}
},
{
"id": "gpt-6-sol@eu",
"name": "GPT-6 Sol (EU)",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.4,
"output": 12,
"cache_read": 0.24,
"cache_write": 3,
"tiers": [
{
"input": 4.8,
"output": 18,
"cache_read": 0.48,
"cache_write": 6,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4.8,
"output": 18,
"cache_read": 0.48,
"cache_write": 6
}
}
},
{
"id": "gpt-6-luna@eu",
"name": "GPT-6 Luna (EU)",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.12,
"output": 0.6,
"cache_read": 0.012,
"cache_write": 0.15,
"tiers": [
{
"input": 0.24,
"output": 0.9,
"cache_read": 0.024,
"cache_write": 0.3,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.24,
"output": 0.9,
"cache_read": 0.024,
"cache_write": 0.3
}
}
},
{
"id": "gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "claude-opus-5-5@eu",
"name": "Claude Opus 5.5 (EU)",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4.4,
"output": 22,
"cache_read": 0.22,
"cache_write": 5.5
}
},
{
"id": "gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "grok-4.7",
"name": "Grok 4.7",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 500000,
"output": 500000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5,
"cache_write": 2
}
},
{
"id": "step-5-preview",
"name": "Step 5 Preview",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"released": "2026-09-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-20",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1,
"output": 2.7,
"cache_read": 0.05
}
},
{
"id": "deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.5,
"output": 1.5,
"cache_read": 0.05
}
},
{
"id": "deepseek-v4.1-flash@eu",
"name": "DeepSeek V4.1 Flash (EU)",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.5,
"output": 1.5,
"cache_read": 0.05
}
},
{
"id": "gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "muse-spark-1.3",
"name": "Muse Spark 1.3",
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"id": "gemini-3.8-flash@eu",
"name": "Gemini 3.8 Flash (EU)",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.825,
"output": 4.125,
"cache_read": 0.0825
}
},
{
"id": "gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "claude-fable-5.1@eu",
"name": "Claude Fable 5.1 (EU)",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 11,
"output": 55,
"cache_read": 0.275,
"cache_write": 13.75
}
},
{
"id": "claude-fable-5.1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "qwen3.8-flash-next",
"name": "Qwen3.8 Flash Next",
"description": "Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding",
"released": "2026-08-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-27",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "qwen3.8-flash-next@eu",
"name": "Qwen3.8 Flash Next (EU)",
"description": "Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding",
"released": "2026-08-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-27",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.16,
"output": 0.47,
"cache_read": 0.016,
"cache_write": 0.2
}
},
{
"id": "glm-5.3-flash@eu",
"name": "GLM-5.3-Flash (EU)",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 262144
},
"cost": {
"input": 0.2,
"output": 0.6,
"cache_read": 0.07
}
},
{
"id": "glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 262144
},
"cost": {
"input": 0.2,
"output": 0.6,
"cache_read": 0.07
}
},
{
"id": "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.",
"released": "2026-08-15",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-08-15",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.05,
"output": 0.2,
"cache_read": 0.01
}
},
{
"id": "glm-5.3@eu",
"name": "GLM-5.3 (EU)",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 1.2,
"output": 4.2,
"cache_read": 0.26
}
},
{
"id": "glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 1.2,
"output": 4.2,
"cache_read": 0.26
}
},
{
"id": "deepseek-v4-pro-0813@eu",
"name": "DeepSeek V4 Pro 0813 (EU)",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.75,
"output": 3.5,
"cache_read": 0.44
}
},
{
"id": "gemini-3.7-flash",
"name": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075
}
},
{
"id": "gemini-3.7-flash@eu",
"name": "Gemini 3.7 Flash (EU)",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.825,
"output": 4.125,
"cache_read": 0.0825
}
},
{
"id": "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",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.32,
"output": 3.96,
"cache_read": 0.044
}
},
{
"id": "grok-4.6",
"name": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "qwen3.8-2.4T-A95B@eu",
"name": "Qwen3.8 2.4T A95B (EU)",
"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",
"released": "2026-08-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-12",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 262144
},
"cost": {
"input": 2.5,
"output": 6,
"cache_read": 0.63
}
},
{
"id": "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",
"released": "2026-08-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-12",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.2
}
},
{
"id": "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",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-08-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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.",
"released": "2026-08-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01-04",
"last_updated": "2026-08-10",
"family": "muse",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 20480
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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.",
"released": "2026-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-08-05",
"family": "ling",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-03",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25,
"cache_write": 2.5
}
},
{
"id": "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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.28,
"output": 0.56,
"cache_read": 0.07
}
},
{
"id": "deepseek-v4-flash-0731",
"name": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.28,
"output": 0.56,
"cache_read": 0.07
}
},
{
"id": "claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "claude-opus-5@eu",
"name": "Claude Opus 5 (EU)",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 27.5,
"cache_read": 0.55,
"cache_write": 6.875
}
},
{
"id": "gemini-3.6-flash",
"name": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.5,
"output": 7,
"cache_read": 0.15
}
},
{
"id": "gemini-3.5-flash-lite",
"name": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"id": "gemini-3.5-flash-lite@eu",
"name": "Gemini 3.5 Flash Lite (EU)",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.33,
"output": 2.75,
"cache_read": 0.033
}
},
{
"id": "kimi-k3@eu",
"name": "Kimi K3 (EU)",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 262144
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.45
}
},
{
"id": "kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 262144
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.45
}
},
{
"id": "inkling",
"name": "Inkling",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-15",
"family": "ling",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 65536,
"output": 32768
},
"cost": {
"input": 1.87,
"output": 4.68,
"cache_read": 0.374
}
},
{
"id": "inkling-256k",
"name": "Inkling 256K",
"description": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-15",
"family": "ling",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 1.87,
"output": 4.68,
"cache_read": 0.374
}
},
{
"id": "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.",
"released": "2026-07-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-07-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 2.1,
"output": 6.6,
"cache_read": 0.21
}
},
{
"id": "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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 4.4,
"output": 22,
"cache_read": 0.44,
"cache_write": 5.5,
"tiers": [
{
"input": 8.8,
"output": 33,
"cache_read": 0.88,
"cache_write": 11,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 8.8,
"output": 33,
"cache_read": 0.88,
"cache_write": 11
}
}
},
{
"id": "gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-terra@eu",
"name": "GPT-5.6 Terra (EU)",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-luna@eu",
"name": "GPT-5.6 Luna (EU)",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "grok-4.5",
"name": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-07-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-08",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "hy3",
"name": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"released": "2026-07-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-06",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.14,
"output": 0.58,
"cache_read": 0.035
}
},
{
"id": "claude-sonnet-5@eu",
"name": "Claude Sonnet 5 (EU)",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2.2,
"output": 11,
"cache_read": 0.22,
"cache_write": 2.75
}
},
{
"id": "claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "fugu-ultra",
"name": "Fugu Ultra",
"description": "Quality-first multi-agent model for hard research, analysis, and competitions",
"released": "2026-06-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-06-15",
"family": "fugu",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"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
}
}
},
{
"id": "glm-5.2@eu",
"name": "GLM-5.2 (EU)",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1.2,
"output": 4.2,
"cache_read": 0.26
}
},
{
"id": "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.",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-06-13",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.12
}
},
{
"id": "glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.8,
"output": 2.55,
"cache_read": 0.16
}
},
{
"id": "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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 1.25,
"output": 4.5,
"cache_read": 0.31
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "claude-fable-5@eu",
"name": "Claude Fable 5 (EU)",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 11,
"output": 55,
"cache_read": 1.1,
"cache_write": 13.75
}
},
{
"id": "claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 11,
"output": 55,
"cache_read": 1.1,
"cache_write": 13.75
}
},
{
"id": "nvidia-nemotron-3-ultra",
"name": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"released": "2026-06-04",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-06-04",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 0.5,
"output": 2.5
}
},
{
"id": "nemotron-3-ultra-550b-a55b",
"name": "Nemotron 3 Ultra 550B A55B",
"description": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy",
"released": "2026-06-04",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-06-04",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "nemotron-3.5-content-safety",
"name": "Nemotron 3.5 Content Safety",
"description": "Safety model for policy screening, moderation, and risk-aware routing workflows",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-02",
"family": "nemotron",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-06-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.32,
"output": 1.28,
"cache_read": 0.032,
"cache_write": 0.4
}
},
{
"id": "minimax-m3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"id": "minimax-m3@eu",
"name": "MiniMax-M3 (EU)",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 0.4,
"output": 2,
"cache_read": 0.1
}
},
{
"id": "step-3.7-flash",
"name": "Step 3.7 Flash",
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"released": "2026-05-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-03-01",
"last_updated": "2026-05-29",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 256000
},
"cost": {
"input": 0.2,
"output": 1.15,
"cache_read": 0.04
}
},
{
"id": "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",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 27.5,
"cache_read": 0.55,
"cache_write": 6.875
}
},
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "gemini-3-pro-image",
"name": "Nano Banana Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-28",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 2,
"output": 12,
"cache_read": 0.2,
"cache_write": 4.5
}
},
{
"id": "gemini-3.1-flash-image",
"name": "Nano Banana 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-05-28",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-28",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.5,
"output": 2
}
},
{
"id": "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.",
"released": "2026-05-27",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-27",
"family": "leanstral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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.",
"released": "2026-05-27",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-27",
"family": "devstral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.44,
"output": 2.2,
"cache_read": 0.44
}
},
{
"id": "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.",
"released": "2026-05-27",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-27",
"family": "leanstral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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.",
"released": "2026-05-27",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-27",
"family": "devstral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.44,
"output": 2.2,
"cache_read": 0.44
}
},
{
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"released": "2026-05-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-21",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 2.5,
"output": 7.5,
"cache_read": 0.25,
"cache_write": 3.125
}
},
{
"id": "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.",
"released": "2026-05-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-20",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 300000,
"output": 300000
},
"cost": {
"input": 0.06,
"output": 0.24,
"cache_read": 0.06
}
},
{
"id": "nemotron-3-nano-omni",
"name": "nemotron-3-nano-omni",
"description": "The most open, efficient, and accurate omni modal reasoning model for agentic AI.",
"released": "2026-05-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"last_updated": "2026-05-20",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 300000,
"output": 300000
},
"cost": {
"input": 0.06,
"output": 0.24,
"cache_read": 0.06
}
},
{
"id": "gemini-3.5-flash@eu",
"name": "Gemini 3.5 Flash (EU)",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.65,
"output": 9.9,
"cache_read": 0.165,
"cache_write": 1.7413
}
},
{
"id": "gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.5,
"output": 9,
"cache_read": 0.15,
"cache_write": 1.583
}
},
{
"id": "ring-2.6-1t",
"name": "ring-2.6-1t",
"description": "Inclusion AI ring-2.6-1t",
"released": "2026-05-08",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-05-08",
"family": "ring",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.3,
"output": 2.5
}
},
{
"id": "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",
"released": "2026-05-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-07",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.275,
"output": 1.65,
"cache_read": 0.0275,
"cache_write": 0.091663
}
},
{
"id": "gemini-3.1-flash-lite",
"name": "Gemini 3.1 Flash Lite",
"description": "Low-latency Gemini model for high-volume multimodal and agent workloads",
"released": "2026-05-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-07",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.25,
"output": 1.5,
"cache_read": 0.025,
"cache_write": 0.08333
}
},
{
"id": "mistral-medium-3-5",
"name": "Mistral Medium 3.5",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"released": "2026-04-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-30",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 209715
},
"cost": {
"input": 1.65,
"output": 8.25,
"cache_read": 1.65
}
},
{
"id": "mistral-medium-3-5@eu",
"name": "Mistral Medium 3.5 (EU)",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"released": "2026-04-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-30",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 209715
},
"cost": {
"input": 1.65,
"output": 8.25,
"cache_read": 1.65
}
},
{
"id": "mistral-medium-latest@eu",
"name": "Mistral Medium (latest) (EU)",
"description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
"released": "2026-04-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-29",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.44,
"output": 2.2,
"cache_read": 0.44
}
},
{
"id": "mistral-medium-latest",
"name": "Mistral Medium (latest)",
"description": "Balanced Mistral model for enterprise assistants, multilingual work, and tools",
"released": "2026-04-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-29",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.44,
"output": 2.2,
"cache_read": 0.44
}
},
{
"id": "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",
"released": "2026-04-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-28",
"family": "nemotron",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 20480
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "laguna-m.1",
"name": "Laguna M.1",
"description": "Poolside's open-weight model for agentic coding and long-horizon work",
"released": "2026-04-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "laguna",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "laguna-xs.2",
"name": "Laguna XS.2",
"description": "Agentic coding model from Poolside in the XS size class for local deployment",
"released": "2026-04-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "laguna",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 32768
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.28,
"output": 0.56,
"cache_read": 0.07
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.32,
"output": 3.96,
"cache_read": 0.044
}
},
{
"id": "deepseek-v4-pro@eu",
"name": "DeepSeek V4 Pro (EU)",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 1.75,
"output": 3.5,
"cache_read": 0.44
}
},
{
"id": "gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 33,
"cache_read": 0.55
}
},
{
"id": "gpt-5.5-pro",
"name": "GPT-5.5 Pro",
"description": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 30,
"output": 180
}
},
{
"id": "gpt-5.5@eu",
"name": "GPT-5.5 (EU)",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 33,
"cache_read": 0.55,
"tiers": [
{
"input": 11,
"output": 49.5,
"cache_read": 1.1,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 11,
"output": 49.5,
"cache_read": 1.1
}
}
},
{
"id": "ling-2.6-1t",
"name": "ling-2.6-1t",
"description": "Inclusion AI ling-2.6-1t",
"released": "2026-04-23",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-04-23",
"family": "ling",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.3,
"output": 2.5
}
},
{
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"released": "2026-04-22",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.0028
}
},
{
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.435,
"output": 0.87,
"cache_read": 0.0036
}
},
{
"id": "ling-2.6-flash",
"name": "ling-2.6-flash",
"description": "Inclusion AI ling-2.6-flash",
"released": "2026-04-21",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-04-21",
"family": "ling",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.1,
"output": 0.3
}
},
{
"id": "kimi-k2.6@eu",
"name": "Kimi K2.6 (EU)",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 128000
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.95
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.16
}
},
{
"id": "grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 30000
},
"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
}
}
},
{
"id": "grok-build-0.1",
"name": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"released": "2026-04-16",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-16",
"family": "grok-build",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 1,
"output": 2,
"cache_read": 0.1
}
},
{
"id": "claude-opus-4-7@eu",
"name": "Claude Opus 4.7 (EU)",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 27.5,
"cache_read": 0.55,
"cache_write": 6.875
}
},
{
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "glm-5.1@eu",
"name": "GLM-5.1 (EU)",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 1.4
}
},
{
"id": "glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-04-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 0.5,
"output": 3,
"cache_read": 0.05,
"cache_write": 0.625
}
},
{
"id": "gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "gemma-4-26b-a4b-it",
"name": "Gemma 4 26B A4B IT",
"description": "Open Gemma instruction model for efficient chat and self-hosted deployments",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.07,
"output": 0.34,
"cache_read": 0.07
}
},
{
"id": "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.",
"released": "2026-03-27",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"last_updated": "2026-03-27",
"family": "kat-coder",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.3,
"output": 1.2
}
},
{
"id": "minimax-m2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"description": "Low-latency M2.7 variant for interactive coding plans and agent loops",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.06,
"cache_write": 1.2
}
},
{
"id": "minimax-m2.7",
"name": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06,
"cache_write": 1.2
}
},
{
"id": "gpt-5.4-mini",
"name": "GPT-5.4 mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "gpt-5.4-nano",
"name": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "mistral-small-2603",
"name": "Mistral Small 4",
"description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
"released": "2026-03-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-16",
"family": "mistral-small",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.165,
"output": 0.66,
"cache_read": 0.165
}
},
{
"id": "mistral-small-2603@eu",
"name": "Mistral Small 4 (EU)",
"description": "Fast Mistral production model for chat, extraction, and cost-sensitive agents",
"released": "2026-03-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-16",
"family": "mistral-small",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.165,
"output": 0.66,
"cache_read": 0.165
}
},
{
"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",
"released": "2026-03-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.1,
"output": 0.5
}
},
{
"id": "nemotron-3-super-120b-a12b",
"name": "Nemotron 3 Super 120B A12B",
"description": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads",
"released": "2026-03-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-06",
"last_updated": "2026-03-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "grok-4.2-beta",
"name": "Grok 4.20 (Reasoning)",
"description": "Reasoning Grok for document-heavy analysis and long-horizon tool use",
"released": "2026-03-09",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-09",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 30000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.2,
"cache_write": 2,
"tiers": [
{
"input": 4,
"output": 12,
"cache_read": 0.4,
"cache_write": 4,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 4,
"output": 12,
"cache_read": 0.4,
"cache_write": 4
}
}
},
{
"id": "gpt-5.4@eu",
"name": "GPT-5.4 (EU)",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.75,
"output": 16.5,
"cache_read": 0.275,
"tiers": [
{
"input": 5.5,
"output": 24.75,
"cache_read": 0.55,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 5.5,
"output": 24.75,
"cache_read": 0.55
}
}
},
{
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 30,
"output": 180,
"cache_read": 30
}
},
{
"id": "gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.75,
"output": 16.5,
"cache_read": 0.275
}
},
{
"id": "qwen3.5-2b",
"name": "Qwen3.5 2B",
"description": "Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use",
"released": "2026-03-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 81920
},
"cost": {
"input": 0.02,
"output": 0.1
}
},
{
"id": "qwen3.5-35b-a3b",
"name": "Qwen3.5 35B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.14,
"output": 1,
"cache_read": 0.05
}
},
{
"id": "qwen3.5-27b",
"name": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.26,
"output": 2.6
}
},
{
"id": "gemini-3.1-pro-preview",
"name": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 2,
"output": 12,
"cache_read": 0.2,
"cache_write": 4.5,
"tiers": [
{
"input": 4,
"output": 18,
"cache_read": 0.4,
"cache_write": 9,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 4,
"output": 18,
"cache_read": 0.4,
"cache_write": 9
}
}
},
{
"id": "claude-sonnet-4-6@eu",
"name": "Claude Sonnet 4.6 (EU)",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3.3,
"output": 16.5,
"cache_read": 0.3,
"cache_write": 4.125
}
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "seed-2.0-code",
"name": "Seed 2.0 Code",
"description": "ByteDance Seed coding model for multimodal software engineering and long-running agents",
"released": "2026-02-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-02-14",
"family": "seed",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 131072
},
"cost": {
"input": 0.5,
"output": 3,
"cache_read": 0.1
}
},
{
"id": "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",
"released": "2026-02-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-02-14",
"family": "seed",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 128000
},
"cost": {
"input": 0.5,
"output": 3,
"cache_read": 0.1
}
},
{
"id": "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",
"released": "2026-02-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-02-14",
"family": "seed",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 32000
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.02
}
},
{
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "claude-opus-4-6@eu",
"name": "Claude Opus 4.6 (EU)",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5.5,
"output": 27.5,
"cache_read": 0.55,
"cache_write": 6.875
}
},
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "kimi-k2.5@eu",
"name": "Kimi K2.5 (EU)",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16000
},
"cost": {
"input": 0.72,
"output": 3.6,
"cache_read": 0.72,
"cache_write": 0.72
}
},
{
"id": "seed-1.8",
"name": "Seed 1.8",
"description": "ByteDance Seed model for multimodal reasoning, long-context analysis, and agent workflows",
"released": "2025-12-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2025-12-28",
"family": "seed",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 64000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.05
}
},
{
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "claude-opus-4-5@eu",
"name": "Claude Opus 4.5 (latest) (EU)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5.5,
"output": 27.5,
"cache_read": 0.55,
"cache_write": 6.875
}
},
{
"id": "gpt-5.1@eu",
"name": "GPT-5.1 (EU)",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.375,
"output": 11,
"cache_read": 0.1375
}
},
{
"id": "claude-haiku-4-5",
"name": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "claude-haiku-4-5@eu",
"name": "Claude Haiku 4.5 (latest) (EU)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1.1,
"output": 5.5,
"cache_read": 0.11,
"cache_write": 1.375
}
},
{
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-sonnet-4-5@eu",
"name": "Claude Sonnet 4.5 (latest) (EU)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3.3,
"output": 16.5,
"cache_read": 0.3,
"cache_write": 4.125,
"tiers": [
{
"input": 6.6,
"output": 24.75,
"cache_read": 0.6,
"cache_write": 8.25,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 6.6,
"output": 24.75,
"cache_read": 0.6,
"cache_write": 8.25
}
}
},
{
"id": "gpt-5@eu",
"name": "GPT-5 (EU)",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.375,
"output": 11,
"cache_read": 0.1375
}
},
{
"id": "gpt-5-mini@eu",
"name": "GPT-5 Mini (EU)",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 0.275,
"output": 2.2,
"cache_read": 0.0275
}
},
{
"id": "gpt-5-nano@eu",
"name": "GPT-5 Nano (EU)",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 0.055,
"output": 0.44,
"cache_read": 0.0055
}
},
{
"id": "claude-opus-4-1",
"name": "Claude Opus 4.1 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-08-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-08-05",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 15,
"output": 75,
"cache_read": 1.5,
"cache_write": 18.75
}
},
{
"id": "gemini-2.5-flash-lite@eu",
"name": "Gemini 2.5 Flash-Lite (EU)",
"description": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01,
"cache_write": 0.18333
}
},
{
"id": "gemini-2.5-flash@eu",
"name": "Gemini 2.5 Flash (EU)",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.075,
"cache_write": 0.55
}
},
{
"id": "gemini-2.5-pro@eu",
"name": "Gemini 2.5 Pro (EU)",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.31,
"cache_write": 2.375,
"tiers": [
{
"input": 2.5,
"output": 15,
"cache_read": 0.62,
"cache_write": 4.75,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 2.5,
"output": 15,
"cache_read": 0.62,
"cache_write": 4.75
}
}
},
{
"id": "claude-sonnet-4@eu",
"name": "Claude Sonnet 4 (latest) (EU)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-05-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-05-22",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "o4-mini@eu",
"name": "o4-mini (EU)",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.21,
"output": 4.84,
"cache_read": 0.3025
}
},
{
"id": "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",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.11,
"output": 0.44,
"cache_read": 0.0275
}
},
{
"id": "gpt-4.1@eu",
"name": "GPT-4.1 (EU)",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2.2,
"output": 8.8,
"cache_read": 0.55
}
},
{
"id": "gpt-4.1-mini@eu",
"name": "GPT-4.1 mini (EU)",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.44,
"output": 1.76,
"cache_read": 0.11
}
},
{
"id": "gpt-4o-mini@eu",
"name": "GPT-4o mini (EU)",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16000
},
"cost": {
"input": 0.165,
"output": 0.66,
"cache_read": 0.0825
}
}
]
},
{
"id": "drun",
"name": "D.Run (China)",
"env": [
"DRUN_API_KEY"
],
"doc": "https://www.d.run",
"api": "https://chat.d.run/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "public/minimax-m25",
"name": "MiniMax M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_details"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.29,
"output": 1.16
}
},
{
"id": "public/deepseek-r1",
"name": "DeepSeek R1",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"released": "2025-01-20",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2025-05-29",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32000
},
"cost": {
"input": 0.55,
"output": 2.2
}
},
{
"id": "public/deepseek-v3",
"name": "DeepSeek V3",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2024-12-26",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2024-12-26",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0.28,
"output": 1.1
}
}
]
},
{
"id": "jalapeno",
"name": "Jalapeno Cloud",
"env": [
"JALAPENO_API_KEY"
],
"doc": "https://www.jalapeno-cloud.ai/docs/",
"api": "https://api.jalapeno-cloud.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "Kimi-K3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "Hy3",
"name": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"released": "2026-07-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-06",
"family": "Hy",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"input": 192000,
"output": 128000
},
"cost": {
"input": 0.14,
"output": 0.58
}
},
{
"id": "GLM-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "Kimi-K2.7-Code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 271360,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 512000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"id": "DeepSeek-V4-Pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 384000
},
"cost": {
"input": 1.6,
"output": 3.38,
"cache_read": 0.14
}
},
{
"id": "DeepSeek-V4-Flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 384000
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.028
}
},
{
"id": "GLM-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 131072
},
"cost": {
"input": 1.38,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "Qwen3.5-122B-A10B",
"name": "Qwen3.5 122B-A10B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.4,
"output": 3.2
}
},
{
"id": "Qwen3.5-35B-A3B",
"name": "Qwen3.5 35B-A3B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.25,
"output": 2
}
},
{
"id": "Qwen3.5-27B",
"name": "Qwen3.5 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-02-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.4
}
},
{
"id": "Qwen3.5-397B-A17B",
"name": "Qwen3.5 397B-A17B",
"description": "Large open Qwen multimodal MoE for visual agents and long technical tasks",
"released": "2026-02-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-15",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.6,
"output": 3.6
}
},
{
"id": "Kimi-K2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 180224
},
"cost": {
"input": 0.6,
"output": 3,
"cache_read": 0.1
}
},
{
"id": "Qwen3-VL-235B-A22B-Thinking",
"name": "Qwen3 VL 235B A22B Thinking",
"description": "Qwen vision-language thinking model for visual reasoning, documents, and agent tasks",
"released": "2025-09-23",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-09-23",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.98,
"output": 3.95
}
},
{
"id": "Qwen3-VL-235B-A22B-Instruct",
"name": "Qwen3 VL 235B A22B Instruct",
"description": "Qwen vision-language instruct model for visual reasoning, documents, and agent tasks",
"released": "2025-09-23",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-09-23",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 129024,
"output": 32768
},
"cost": {
"input": 0.3,
"output": 1.5
}
},
{
"id": "Qwen3-Next-80B-A3B-Instruct",
"name": "Qwen3-Next 80B-A3B Instruct",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2025-09",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-09",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 129024,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 1.5
}
},
{
"id": "Qwen3-Next-80B-A3B-Thinking",
"name": "Qwen3-Next 80B-A3B (Thinking)",
"description": "Efficient Qwen thinking model for local reasoning, math, and coding agents",
"released": "2025-09",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-09",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 1.5
}
}
]
},
{
"id": "dinference",
"name": "DInference",
"env": [
"DINFERENCE_API_KEY"
],
"doc": "https://dinference.com",
"api": "https://api.dinference.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 3.89
}
},
{
"id": "glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 3.89
}
},
{
"id": "glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 2.4
}
},
{
"id": "minimax-m2.5",
"name": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 0.22,
"output": 0.88
}
},
{
"id": "glm-4.7",
"name": "GLM-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 0.45,
"output": 1.65
}
},
{
"id": "gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open-weight GPT model for self-hosted reasoning and instruction-following workloads",
"released": "2025-08-05",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.0675,
"output": 0.27
}
}
]
},
{
"id": "chutes",
"name": "Chutes",
"env": [
"CHUTES_API_KEY"
],
"doc": "https://llm.chutes.ai/v1/models",
"api": "https://llm.chutes.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "Qwen/Qwen3.8-27B-TEE",
"name": "Qwen3.8 27B TEE",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.039,
"output": 1.25,
"cache_read": 0.003899999999999999
}
},
{
"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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.44,
"output": 1.32,
"cache_read": 0.04399999999999999
}
},
{
"id": "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",
"released": "2026-07-23",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-23",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 0
},
"cost": {
"input": 0.0245,
"output": 0.0978,
"cache_read": 0.0024499999999999995
}
},
{
"id": "moonshotai/Kimi-K3-TEE",
"name": "Kimi K3 TEE",
"description": "Kimi multimodal agent model for visual understanding, coding, and planning",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.85,
"output": 9.5,
"cache_read": 0.18499999999999997
}
},
{
"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",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65535
},
"cost": {
"input": 1.25,
"output": 3.95,
"cache_read": 0.12499999999999997
}
},
{
"id": "Qwen/Qwen3.6-27B-TEE",
"name": "Qwen3.6 27B TEE",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-22",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.024999999999999994
}
},
{
"id": "moonshotai/Kimi-K2.6-TEE",
"name": "Kimi K2.6 TEE",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65535
},
"cost": {
"input": 0.45,
"output": 1.95,
"cache_read": 0.04499999999999999
}
},
{
"id": "zai-org/GLM-5.1-TEE",
"name": "GLM 5.1 TEE",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 65535
},
"cost": {
"input": 0.98,
"output": 3.08,
"cache_read": 0.09799999999999998
}
},
{
"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",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 0.12,
"output": 0.37,
"cache_read": 0.011999999999999997
}
},
{
"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",
"released": "2026-02-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-15",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.45,
"output": 3,
"cache_read": 0.04499999999999999
}
},
{
"id": "deepseek-ai/DeepSeek-V3.2-TEE",
"name": "DeepSeek V3.2 TEE",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 1,
"output": 1,
"cache_read": 0.09999999999999998
}
},
{
"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",
"released": "2025-07-25",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2025-07-25",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.2989,
"output": 1.1957,
"cache_read": 0.029889999999999993
}
},
{
"id": "Qwen/Qwen3-32B-TEE",
"name": "Qwen3 32B TEE",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"released": "2025-04-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-04-28",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 40960,
"output": 40960
},
"cost": {
"input": 0.104,
"output": 0.416,
"cache_read": 0.010399999999999998
}
},
{
"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",
"released": "2024-07-18",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2024-07-18",
"family": "mistral-nemo",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.0245,
"output": 0.0978,
"cache_read": 0.0024499999999999995
}
}
]
},
{
"id": "minimax-coding-plan",
"name": "MiniMax Token Plan (minimax.io)",
"env": [
"MINIMAX_API_KEY"
],
"doc": "https://platform.minimax.io/docs/token-plan/intro",
"api": "https://api.minimax.io/anthropic/v1",
"npm": "@ai-sdk/anthropic",
"models": [
{
"id": "MiniMax-M3.1-Flash",
"name": "MiniMax-M3.1-Flash",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"released": "2026-10-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-19",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 524288
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M3.1-Flash-Preview",
"name": "MiniMax-M3.1-Flash-Preview",
"description": "Frontier multimodal coding model with 1M context window and tunable thinking depth",
"released": "2026-09-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-27",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 512000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-25",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 524288
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2.7",
"name": "MiniMax-M2.7",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2.5-highspeed",
"name": "MiniMax-M2.5-highspeed",
"description": "High-speed MiniMax model for low-latency coding and agent workflows",
"released": "2026-02-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-13",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2.1",
"name": "MiniMax-M2.1",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2025-12-23",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-12-23",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "MiniMax-M2",
"name": "MiniMax-M2",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2025-10-27",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-10-27",
"family": "minimax",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "openreason",
"name": "OpenReason",
"env": [
"OPENREASON_API_KEY"
],
"doc": "https://openreason.app/docs",
"api": "https://api.openreason.app/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.1371,
"output": 0.2743
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 1.0022,
"output": 4.22
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.1055,
"output": 0.422
}
}
]
},
{
"id": "ainetcafe",
"name": "ainetcafe",
"env": [
"AINETCAFE_API_KEY"
],
"doc": "https://ainetcafe.com/k3/guides/",
"api": "https://microquickjs.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "Kimi-K3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 2.1,
"output": 10.5,
"cache_read": 0.3
}
}
]
},
{
"id": "mixlayer",
"name": "Mixlayer",
"env": [
"MIXLAYER_API_KEY"
],
"doc": "https://docs.mixlayer.com",
"api": "https://models.mixlayer.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "qwen/qwen3.5-9b",
"name": "Qwen3.5 9B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.1,
"output": 0.4
}
},
{
"id": "qwen/qwen3.5-35b-a3b",
"name": "Qwen3.5 35B A3B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.25,
"output": 1.3
}
},
{
"id": "qwen/qwen3.5-122b-a10b",
"name": "Qwen3.5 122B A10B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.4,
"output": 3.2
}
},
{
"id": "qwen/qwen3.5-27b",
"name": "Qwen3.5 27B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.3,
"output": 2.4
}
},
{
"id": "qwen/qwen3.5-397b-a17b",
"name": "Qwen3.5 397B A17B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-02-15",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-15",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.6,
"output": 3.6
}
}
]
},
{
"id": "azure",
"name": "Azure",
"env": [
"AZURE_RESOURCE_NAME",
"AZURE_API_KEY"
],
"doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models",
"npm": "@ai-sdk/azure",
"models": [
{
"id": "claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.625,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5
}
}
},
{
"id": "claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "grok-4.7",
"name": "Grok 4.7",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 500000,
"output": 500000
}
},
{
"id": "deepseek-v4.1-flash",
"name": "DeepSeek-V4.1-Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"status": "beta",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "gpt-image-2.5-sunburst",
"name": "GPT Image 2.5 Sunburst",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-09-08",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-08",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "gpt-image-2.5-flare",
"name": "GPT Image 2.5 Flare",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-09-08",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-08",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "claude-fable-5-1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "grok-4.6",
"name": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5
}
},
{
"id": "claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"status": "beta",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "claude-mythos-5",
"name": "Claude Mythos 5",
"description": "Restricted Claude model for advanced cybersecurity and biology research workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-mythos",
"status": "beta",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-31",
"last_updated": "2026-05-28",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25,
"tiers": [
{
"input": 10,
"output": 37.5,
"cache_read": 1,
"cache_write": 12.5,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 10,
"output": 37.5,
"cache_read": 1,
"cache_write": 12.5
}
}
},
{
"id": "gpt-chat-latest",
"name": "GPT Chat Latest",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2026-05-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-05-28",
"status": "beta",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 0.5
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek-V4-Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": false,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.19,
"output": 0.51
}
},
{
"id": "gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-24",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek-V4-Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": false,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.74,
"output": 3.48
}
},
{
"id": "gpt-image-2",
"name": "GPT-Image-2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-04-21",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-21",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4
}
},
{
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "grok-4-20-non-reasoning",
"name": "Grok 4.20 (Non-Reasoning)",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2026-04-08",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-04-08",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 8192
},
"cost": {
"input": 2,
"output": 6
}
},
{
"id": "grok-4-20-reasoning",
"name": "Grok 4.20 (Reasoning)",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2026-04-08",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-04-08",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 8192
},
"cost": {
"input": 2,
"output": 6
}
},
{
"id": "gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-02-24",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-07-17",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25,
"tiers": [
{
"input": 10,
"output": 37.5,
"cache_read": 1,
"cache_write": 12.5,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 10,
"output": 37.5,
"cache_read": 1,
"cache_write": 12.5
}
}
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.6,
"output": 3
}
},
{
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-01-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-01-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "gpt-5.2",
"name": "GPT-5.2",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "deepseek-v3.2",
"name": "DeepSeek-V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.58,
"output": 1.68
}
},
{
"id": "deepseek-v3.2-speciale",
"name": "DeepSeek-V3.2-Speciale",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.58,
"output": 1.68
}
},
{
"id": "gpt-image-1.5",
"name": "GPT-Image-1.5",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-11-25",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-25",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 32,
"cache_read": 1.25
}
},
{
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-08-01",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-11-18",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-11-18",
"family": "claude-haiku",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "claude-opus-4-1",
"name": "Claude Opus 4.1",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-11-18",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 15,
"output": 75,
"cache_read": 1.5,
"cache_write": 18.75
}
},
{
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex Mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5.1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-pro",
"name": "GPT-5 Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"released": "2025-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-10-06",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 15,
"output": 120
}
},
{
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-09-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.05,
"output": 0.4,
"cache_read": 0.005
}
},
{
"id": "gpt-5",
"name": "GPT-5",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "grok-4-1-fast-reasoning",
"name": "Grok 4.1 Fast (Reasoning)",
"description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
"released": "2025-06-27",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2025-06-27",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "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",
"released": "2025-06-27",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2025-06-27",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "model-router",
"name": "Model Router",
"description": "Automatic model router for matching prompts to suitable backends and budgets",
"released": "2025-05-19",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"last_updated": "2025-11-18",
"family": "model-router",
"provider": {
"npm": "@ai-sdk/azure",
"shape": "completions"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 16384
},
"cost": {
"input": 0.14,
"output": 0
}
},
{
"id": "codex-mini",
"name": "Codex Mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-05-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04",
"last_updated": "2025-05-16",
"family": "gpt-codex-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.5,
"output": 6,
"cache_read": 0.375
}
},
{
"id": "mistral-medium-2505",
"name": "Mistral Medium 3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"released": "2025-05-07",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-05-07",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.4,
"output": 2
}
},
{
"id": "gpt-image-1",
"name": "GPT-Image-1",
"description": "OpenAI image model for production generation, edits, and brand-safe visual workflows",
"released": "2025-04-24",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-04-24",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 40,
"cache_read": 1.25
}
},
{
"id": "o3",
"name": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"id": "o4-mini",
"name": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.275
}
},
{
"id": "cohere-embed-v-4-0",
"name": "Embed v4",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2025-04-15",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2025-04-15",
"family": "cohere-embed",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 1536
},
"cost": {
"input": 0.12,
"output": 0
}
},
{
"id": "gpt-4.1-mini",
"name": "GPT-4.1 mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.4,
"output": 1.6,
"cache_read": 0.1
}
},
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"id": "gpt-4.1-nano",
"name": "GPT-4.1 nano",
"description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-nano",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.025
}
},
{
"id": "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",
"released": "2025-04-05",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-08",
"last_updated": "2025-04-05",
"family": "llama",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.78
}
},
{
"id": "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",
"released": "2025-04-05",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-08",
"last_updated": "2025-04-05",
"family": "llama",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 16384
},
"cost": {
"input": 0.25,
"output": 1
}
},
{
"id": "cohere-command-a",
"name": "Command A",
"description": "Cohere command model for multilingual enterprise agents, tools, and chat",
"released": "2025-03-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06-01",
"last_updated": "2025-03-13",
"family": "command-a",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 2.5,
"output": 10
}
},
{
"id": "mistral-small-2503",
"name": "Mistral Small 3.1",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"released": "2025-03-01",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09",
"last_updated": "2025-03-01",
"family": "mistral-small",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.3
}
},
{
"id": "deepseek-r1",
"name": "DeepSeek-R1",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"released": "2025-01-20",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-01-20",
"family": "deepseek-thinking",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 163840,
"output": 163840
},
"cost": {
"input": 1.35,
"output": 5.4
}
},
{
"id": "codestral-2501",
"name": "Codestral 25.01",
"description": "Mistral coding model for code completion, generation, and developer workflows",
"released": "2025-01-01",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-03",
"last_updated": "2025-01-01",
"family": "codestral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.3,
"output": 0.9
}
},
{
"id": "o3-mini",
"name": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"released": "2024-12-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-01-29",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.55
}
},
{
"id": "phi-4-mini-reasoning",
"name": "Phi-4-mini-reasoning",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.075,
"output": 0.3
}
},
{
"id": "phi-4-reasoning-plus",
"name": "Phi-4-reasoning-plus",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-reasoning",
"name": "Phi-4-reasoning",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-multimodal",
"name": "Phi-4-multimodal",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"released": "2024-12-11",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.08,
"output": 0.32
}
},
{
"id": "phi-4",
"name": "Phi-4",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"released": "2024-12-11",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-mini",
"name": "Phi-4-mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2024-12-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.075,
"output": 0.3
}
},
{
"id": "llama-3.3-70b-instruct",
"name": "Llama-3.3-70B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0.71,
"output": 0.71
}
},
{
"id": "o1",
"name": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"released": "2024-12-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-12-05",
"family": "o",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 15,
"output": 60,
"cache_read": 7.5
}
},
{
"id": "ministral-3b",
"name": "Ministral 3B",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"released": "2024-10-22",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-03",
"last_updated": "2024-10-22",
"family": "ministral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.04,
"output": 0.04
}
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075
}
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"released": "2024-05-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-08-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 2.5,
"output": 10,
"cache_read": 1.25
}
},
{
"id": "text-embedding-3-small",
"name": "text-embedding-3-small",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2024-01-25",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 1536
},
"cost": {
"input": 0.02,
"output": 0
}
},
{
"id": "text-embedding-3-large",
"name": "text-embedding-3-large",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2024-01-25",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 3072
},
"cost": {
"input": 0.13,
"output": 0
}
},
{
"id": "gpt-3.5-turbo-0125",
"name": "GPT-3.5 Turbo 0125",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2024-01-25",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 16384,
"output": 4096
},
"cost": {
"input": 0.5,
"output": 1.5
}
},
{
"id": "cohere-embed-v3-english",
"name": "Embed v3 English",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2023-11-07",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2023-11-07",
"family": "cohere-embed",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 1024
},
"cost": {
"input": 0.1,
"output": 0
}
},
{
"id": "cohere-embed-v3-multilingual",
"name": "Embed v3 Multilingual",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2023-11-07",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2023-11-07",
"family": "cohere-embed",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 1024
},
"cost": {
"input": 0.1,
"output": 0
}
},
{
"id": "gpt-3.5-turbo-1106",
"name": "GPT-3.5 Turbo 1106",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2023-11-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 16384,
"output": 4096
},
"cost": {
"input": 1,
"output": 2
}
},
{
"id": "gpt-4-turbo-vision",
"name": "GPT-4 Turbo Vision",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-11",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 10,
"output": 30
}
},
{
"id": "gpt-4-turbo",
"name": "GPT-4 Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 10,
"output": 30
}
},
{
"id": "gpt-3.5-turbo-instruct",
"name": "GPT-3.5 Turbo Instruct",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-09-21",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2023-09-21",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 4096,
"output": 4096
},
"cost": {
"input": 1.5,
"output": 2
}
},
{
"id": "text-embedding-ada-002",
"name": "text-embedding-ada-002",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2022-12-15",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2022-12-15",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 1536
},
"cost": {
"input": 0.1,
"output": 0
}
}
]
},
{
"id": "stepfun-ai-step-plan",
"name": "StepFun Step Plan (Global)",
"env": [
"STEPFUN_API_KEY"
],
"doc": "https://platform.stepfun.ai/docs/en/step-plan/integrations/reasoning-api",
"api": "https://api.stepfun.ai/step_plan/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "step-5-preview",
"name": "Step 5 Preview",
"description": "StepFun's next-generation flagship base model for coding and professional knowledge work, with native text, image, and video input and a 1M-token context window",
"released": "2026-09-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-20",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 1000000,
"output": 65536
}
},
{
"id": "step-3.7-flash",
"name": "Step 3.7 Flash",
"description": "Newer StepFun flash model for faster agents, coding, and multimodal prompts",
"released": "2026-05-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2026-03-01",
"last_updated": "2026-05-29",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"input": 256000,
"output": 256000
}
},
{
"id": "step-3.5-flash-2603",
"name": "Step 3.5 Flash 2603",
"description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
"released": "2026-04-02",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "step",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"input": 256000,
"output": 256000
}
},
{
"id": "step-3.5-flash",
"name": "Step 3.5 Flash",
"description": "StepFun flash lane for quick multimodal reasoning and coding assistance",
"released": "2026-01-29",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high"
]
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-13",
"family": "step",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"input": 256000,
"output": 256000
}
}
]
},
{
"id": "tencent-tokenhub",
"name": "Tencent TokenHub",
"env": [
"TENCENT_TOKENHUB_API_KEY"
],
"doc": "https://cloud.tencent.com/document/product/1823/130050",
"api": "https://tokenhub.tencentmaas.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "hy4-preview",
"name": "Hy4 preview",
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
"released": "2026-08-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-28",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1024000,
"output": 64000
},
"cost": {
"input": 0.834,
"output": 2.501,
"cache_read": 0.042
}
},
{
"id": "hy3",
"name": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"released": "2026-07-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-06",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"input": 192000,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "hy3-preview",
"name": "Hy3 preview",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"released": "2026-04-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-20",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 64000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
}
]
},
{
"id": "poe",
"name": "Poe",
"env": [
"POE_API_KEY"
],
"doc": "https://creator.poe.com/docs/external-applications/openai-compatible-api",
"api": "https://api.poe.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "google/gemini-3.8-flash",
"name": "Gemini-3.8-Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.7576,
"output": 3.7879,
"cache_read": 0.0758
}
},
{
"id": "google/gemini-omni-1.1-flash",
"name": "Gemini-Omni-1.1-Flash",
"description": "Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control",
"released": "2026-08-27",
"attachment": true,
"reasoning": true,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-08-27",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"video"
]
},
"limit": {
"context": 131072,
"output": 57920
},
"cost": {
"input": 1.5152,
"output": 9.0909
}
},
{
"id": "google/gemini-3.7-flash",
"name": "Gemini-3.7-Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.7576,
"output": 3.7879,
"cache_read": 0.0758
}
},
{
"id": "google/gemini-3.6-flash",
"name": "Gemini-3.6-Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.7576,
"output": 3.7879,
"cache_read": 0.0758
}
},
{
"id": "google/gemini-3.5-flash-lite",
"name": "Gemini-3.5-Flash-Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.303,
"output": 2.5253,
"cache_read": 0.0303
}
},
{
"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",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 128000
},
"cost": {
"input": 4.2929,
"output": 21.4646,
"cache_read": 0.4293,
"cache_write": 5.3662
}
},
{
"id": "google/gemini-3.5-flash",
"name": "Gemini-3.5-Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5152,
"output": 9.0909,
"cache_read": 0.1515
}
},
{
"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",
"released": "2026-05-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-07",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.2525,
"output": 1.5152
}
},
{
"id": "empiriolabs/deepseek-v4-pro-el",
"name": "DeepSeek-V4-Pro-EL",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 1000000,
"output": 384000
},
"cost": {
"input": 1.67,
"output": 3.33
}
},
{
"id": "empiriolabs/deepseek-v4-flash-el",
"name": "DeepSeek-V4-Flash-EL",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 1000000,
"output": 384000
},
"cost": {
"input": 0.14,
"output": 0.28
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 400000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 4.5455,
"output": 27.2727,
"cache_read": 0.4545
}
},
{
"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",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 400000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 27.2727,
"output": 163.6364
}
},
{
"id": "openai/gpt-image-2",
"name": "GPT-Image-2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-04-21",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-21",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5.0505,
"output": 30.303,
"cache_read": 1.2626
}
},
{
"id": "novita/kimi-k2.6",
"name": "Kimi-K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"input": 262144,
"output": 262144
},
"cost": {
"input": 0.9596,
"output": 4.0404,
"cache_read": 0.1616
}
},
{
"id": "anthropic/claude-opus-4.7",
"name": "Claude-Opus-4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 128000
},
"cost": {
"input": 4.2929,
"output": 21.4646,
"cache_read": 0.4293,
"cache_write": 5.3662
}
},
{
"id": "google/gemma-4-31b",
"name": "Gemma-4-31B",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"released": "2026-04-02",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.6818,
"output": 4.0909,
"cache_read": 0.0682
}
},
{
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4-Nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.1818,
"output": 1.1364,
"cache_read": 0.0182
}
},
{
"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",
"released": "2026-03-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-03-13",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 0
},
"cost": {
"input": 1.2626,
"output": 2.5253,
"cache_read": 0.202
}
},
{
"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",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 27.2727,
"output": 163.6364
}
},
{
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2.2727,
"output": 13.6364,
"cache_read": 0.2273
}
},
{
"id": "openai/gpt-5.3-instant",
"name": "GPT-5.3-Instant",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2026-03-03",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-03",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 111616,
"output": 16384
},
"cost": {
"input": 1.6,
"output": 13,
"cache_read": 0.16
}
},
{
"id": "google/gemini-3.1-pro",
"name": "Gemini-3.1-Pro",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 2.0202,
"output": 12.1212,
"cache_read": 0.202
}
},
{
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude-Sonnet-4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 983040,
"output": 128000
},
"cost": {
"input": 2.5758,
"output": 12.8788,
"cache_read": 0.2576,
"cache_write": 3.2197
}
},
{
"id": "novita/glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 205000,
"output": 131072
},
"cost": {
"input": 1,
"output": 3.2,
"cache_read": 0.2
}
},
{
"id": "anthropic/claude-opus-4.6",
"name": "Claude-Opus-4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 983040,
"output": 128000
},
"cost": {
"input": 4.2929,
"output": 21.4646,
"cache_read": 0.4293,
"cache_write": 5.3662
}
},
{
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3-Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.5909,
"output": 12.7273,
"cache_read": 0.1591
}
},
{
"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",
"released": "2026-02-05",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex-spark",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 100000,
"output": 16384
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "fireworks-ai/kimi-k2.5-fw",
"name": "Kimi-K2.5-FW",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"input": 245760,
"output": 16384
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "novita/kimi-k2.5",
"name": "Kimi-K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 262144
},
"cost": {
"input": 0.6,
"output": 3,
"cache_read": 0.1
}
},
{
"id": "novita/glm-4.7-flash",
"name": "glm-4.7-flash",
"description": "Budget GLM lane for fast coding help, routing, and everyday automation",
"released": "2026-01-19",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-04",
"last_updated": "2026-01-19",
"family": "glm-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 65500
},
"cost": {
"input": 0.0707,
"output": 0.404
}
},
{
"id": "novita/minimax-m2.1",
"name": "minimax-m2.1",
"description": "Earlier MiniMax agent model for practical coding and productivity tasks",
"released": "2025-12-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"last_updated": "2025-12-23",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 205000,
"output": 131072
},
"cost": {
"input": 0.303,
"output": 1.2121,
"cache_read": 0.1515
}
},
{
"id": "novita/glm-4.7-n",
"name": "glm-4.7-n",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 205000,
"output": 131072
}
},
{
"id": "novita/glm-4.7",
"name": "glm-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 205000,
"output": 131072
}
},
{
"id": "xai/grok-4-fast-reasoning",
"name": "Grok-4-Fast-Reasoning",
"description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
"released": "2025-12-18",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-18",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"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",
"released": "2025-12-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-18",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "google/gemini-3-flash",
"name": "Gemini-3-Flash",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"released": "2025-12-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-12-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.404,
"output": 2.4242,
"cache_read": 0.0404
}
},
{
"id": "google/gemini-deep-research",
"name": "gemini-deep-research",
"description": "Legacy model retained for compatibility with older integrations",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-11",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 0
},
"cost": {
"input": 1.6,
"output": 9.6
}
},
{
"id": "openai/gpt-5.2-codex",
"name": "GPT-5.2-Codex",
"description": "Code-specialist GPT for repository edits, reviews, and long-running software agents",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.6,
"output": 13,
"cache_read": 0.16
}
},
{
"id": "openai/gpt-5.2-instant",
"name": "GPT-5.2-Instant",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2025-12-11",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 1.6,
"output": 13,
"cache_read": 0.16
}
},
{
"id": "openai/gpt-5.2-pro",
"name": "GPT-5.2-Pro",
"description": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 19.0909,
"output": 152.7273
}
},
{
"id": "openai/gpt-5.2",
"name": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.5909,
"output": 12.7273,
"cache_read": 0.1591
}
},
{
"id": "novita/glm-4.6v",
"name": "glm-4.6v",
"description": "GLM vision model for visual reasoning, documents, and multimodal agents",
"released": "2025-12-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-04",
"last_updated": "2025-12-08",
"family": "glm",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 131000,
"output": 32768
}
},
{
"id": "novita/deepseek-v3.2",
"name": "DeepSeek-V3.2",
"description": "Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 0
},
"cost": {
"input": 0.2626,
"output": 0.3838,
"cache_read": 0.1313
}
},
{
"id": "poetools/claude-code",
"name": "claude-code",
"description": "Claude model for careful reasoning, writing, coding, and tool use",
"released": "2025-11-27",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-27",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/gpt-image-1.5",
"name": "gpt-image-1.5",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-11-25",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-25",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 128000,
"output": 0
}
},
{
"id": "anthropic/claude-opus-4.5",
"name": "Claude-Opus-4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
},
{
"type": "budget_tokens",
"min": 0,
"max": 63999
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 196608,
"output": 64000
},
"cost": {
"input": 4.2929,
"output": 21.4646,
"cache_read": 0.4293,
"cache_write": 5.3662
}
},
{
"id": "google/nano-banana-pro",
"name": "Nano-Banana-Pro",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"released": "2025-11-20",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2025-11-20",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 65536,
"output": 0
},
"cost": {
"input": 2.0202,
"output": 12.1212,
"cache_read": 0.202
}
},
{
"id": "xai/grok-4.1-fast-reasoning",
"name": "Grok-4.1-Fast-Reasoning",
"description": "xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning",
"released": "2025-11-19",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-19",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 30000
}
},
{
"id": "xai/grok-4.1-fast-non-reasoning",
"name": "Grok-4.1-Fast-Non-Reasoning",
"description": "xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses",
"released": "2025-11-19",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-19",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 2000000,
"output": 30000
}
},
{
"id": "google/gemini-3-pro",
"name": "Gemini-3-Pro",
"description": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2025-11-18",
"family": "gemini-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.6,
"output": 9.6,
"cache_read": 0.16
}
},
{
"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",
"released": "2025-11-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.22,
"output": 1.8,
"cache_read": 0.022
}
},
{
"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",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.1,
"output": 9,
"cache_read": 0.11
}
},
{
"id": "openai/gpt-5.1-instant",
"name": "GPT-5.1-Instant",
"description": "Chat-tuned GPT-5.1 for polished assistants, writing, and product conversations",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 1.1,
"output": 9,
"cache_read": 0.11
}
},
{
"id": "openai/gpt-5.1-codex",
"name": "GPT-5.1-Codex",
"description": "Codex GPT for repository edits, code review, and practical software agents",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.1,
"output": 9,
"cache_read": 0.11
}
},
{
"id": "openai/gpt-5.1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.1364,
"output": 9.0909,
"cache_read": 0.1136
}
},
{
"id": "novita/kimi-k2-thinking",
"name": "kimi-k2-thinking",
"description": "Thinking Kimi model for slower research passes, planning, and hard technical questions",
"released": "2025-11-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2024-08",
"last_updated": "2025-11-06",
"family": "kimi-thinking",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 0
}
},
{
"id": "anthropic/claude-haiku-4.5",
"name": "Claude-Haiku-4.5",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 63999
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 192000,
"output": 64000
},
"cost": {
"input": 0.8586,
"output": 4.2929,
"cache_read": 0.0859,
"cache_write": 1.0732
}
},
{
"id": "google/veo-3.1-fast",
"name": "Veo-3.1-Fast",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-15",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-15",
"family": "veo",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "google/veo-3.1",
"name": "Veo-3.1",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-15",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-15",
"family": "veo",
"modalities": {
"input": [
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "google/veo-3-fast",
"name": "Veo-3-Fast",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-13",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-13",
"family": "veo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "openai/gpt-image-1-mini",
"name": "GPT-Image-1-Mini",
"description": "Cost-efficient GPT Image 1 variant for image generation and editing",
"released": "2025-10-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-06",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/sora-2",
"name": "Sora-2",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-06",
"family": "sora",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/sora-2-pro",
"name": "Sora-2-Pro",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-10-06",
"family": "sora",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/gpt-5-pro",
"name": "GPT-5-Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"released": "2025-10-06",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-10-06",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 13.6364,
"output": 109.0909
}
},
{
"id": "novita/glm-4.6",
"name": "GLM-4.6",
"description": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks",
"released": "2025-09-30",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-04",
"last_updated": "2025-09-30",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 0.6061,
"output": 2.2222,
"cache_read": 0.1111
}
},
{
"id": "anthropic/claude-sonnet-4.5",
"name": "Claude-Sonnet-4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 31999
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 983040,
"output": 32768
},
"cost": {
"input": 2.5758,
"output": 12.8788,
"cache_read": 0.2576,
"cache_write": 3.2197
}
},
{
"id": "openai/gpt-5-codex",
"name": "GPT-5-Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-09-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
"family": "gpt-codex",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.1,
"output": 9
}
},
{
"id": "xai/grok-code-fast-1",
"name": "Grok Code Fast 1",
"description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
"released": "2025-09-02",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-09-02",
"family": "grok",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.5,
"cache_read": 0.02
}
},
{
"id": "elevenlabs/elevenlabs-music",
"name": "ElevenLabs-Music",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2025-08-29",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-08-29",
"family": "elevenlabs",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 2000,
"output": 0
}
},
{
"id": "google/nano-banana",
"name": "Nano-Banana",
"description": "Nano Banana image model for fast generation, edits, and character-consistent assets",
"released": "2025-08-26",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-06",
"last_updated": "2025-08-26",
"family": "gemini-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 65536,
"output": 0
},
"cost": {
"input": 0.21,
"output": 1.8,
"cache_read": 0.021
}
},
{
"id": "elevenlabs/elevenlabs-v3",
"name": "ElevenLabs-v3",
"description": "Expressive text-to-speech model with inline audio tags across 70+ languages",
"released": "2025-08-20",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-08-20",
"family": "elevenlabs",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 128000,
"output": 0
}
},
{
"id": "openai/gpt-5-nano",
"name": "GPT-5-nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.0455,
"output": 0.3636,
"cache_read": 0.0045
}
},
{
"id": "openai/gpt-5",
"name": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.1364,
"output": 9.0909,
"cache_read": 0.1136
}
},
{
"id": "openai/gpt-5-mini",
"name": "GPT-5-mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2273,
"output": 1.8182,
"cache_read": 0.0227
}
},
{
"id": "openai/gpt-5-chat",
"name": "GPT-5-Chat",
"description": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 272000,
"output": 16384
},
"cost": {
"input": 1.1,
"output": 9,
"cache_read": 0.11
}
},
{
"id": "anthropic/claude-opus-4.1",
"name": "Claude-Opus-4.1",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-08-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 31999
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-03-31",
"last_updated": "2025-08-05",
"family": "claude-opus",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 196608,
"output": 32000
},
"cost": {
"input": 13,
"output": 64,
"cache_read": 1.3,
"cache_write": 16
}
},
{
"id": "cerebras/gpt-oss-120b-cs",
"name": "GPT-OSS-120B-CS",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 0
},
"cost": {
"input": 0.3535,
"output": 0.7576
}
},
{
"id": "cerebras/qwen3-235b-2507-cs",
"name": "qwen3-235b-2507-cs",
"description": "Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use",
"released": "2025-07-21",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": false,
"last_updated": "2025-07-21",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "xai/grok-4",
"name": "Grok-4",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2025-07-10",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-07-10",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 128000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.75
}
},
{
"id": "openai/o4-mini-deep-research",
"name": "o4-mini-deep-research",
"description": "Research model for long-horizon investigation, synthesis, and analytical reports",
"released": "2025-06-26",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-06-26",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.8,
"output": 7.2,
"cache_read": 0.45
}
},
{
"id": "openai/o3-deep-research",
"name": "o3-deep-research",
"description": "Research model for long-horizon investigation, synthesis, and analytical reports",
"released": "2025-06-26",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-06-26",
"family": "o",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 9,
"output": 36,
"cache_read": 2.2
}
},
{
"id": "google/imagen-4-fast",
"name": "Imagen-4-Fast",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-06-25",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-06-25",
"family": "imagen",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"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",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash-lite",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1024000,
"output": 64000
},
"cost": {
"input": 0.07,
"output": 0.28
}
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini-2.5-Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 32768
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1065535,
"output": 65535
},
"cost": {
"input": 0.87,
"output": 7,
"cache_read": 0.087
}
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini-2.5-Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1065535,
"output": 65535
},
"cost": {
"input": 0.21,
"output": 1.8,
"cache_read": 0.021
}
},
{
"id": "openai/o3-pro",
"name": "o3-pro",
"description": "High-effort o3 tier for difficult technical reasoning and careful answers",
"released": "2025-06-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-06-10",
"family": "o-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 18.1818,
"output": 72.7273
}
},
{
"id": "google/lyria",
"name": "Lyria",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2025-06-04",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-06-04",
"family": "lyria",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "google/imagen-4-ultra",
"name": "Imagen-4-Ultra",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-05-24",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-05-24",
"family": "imagen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "anthropic/claude-sonnet-4",
"name": "Claude-Sonnet-4",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-05-22",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-03-31",
"last_updated": "2025-05-22",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 983040,
"output": 64000
},
"cost": {
"input": 2.6,
"output": 13,
"cache_read": 0.26,
"cache_write": 3.2
}
},
{
"id": "anthropic/claude-opus-4",
"name": "Claude-Opus-4",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-05-22",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-03-31",
"last_updated": "2025-05-22",
"family": "claude-opus",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 192512,
"output": 28672
},
"cost": {
"input": 13,
"output": 64,
"cache_read": 1.3,
"cache_write": 16
}
},
{
"id": "google/imagen-4",
"name": "Imagen-4",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-05-22",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-05-22",
"family": "imagen",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "google/veo-3",
"name": "Veo-3",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-05-21",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-05-21",
"family": "veo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "runwayml/runway-gen-4-turbo",
"name": "Runway-Gen-4-Turbo",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-05-09",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-05-09",
"family": "runway",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 256,
"output": 0
}
},
{
"id": "cerebras/qwen3-32b-cs",
"name": "qwen3-32b-cs",
"description": "Dense open Qwen model for self-hosted chat, reasoning, and coding",
"released": "2025-04-28",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-04",
"last_updated": "2025-04-28",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/gpt-image-1",
"name": "GPT-Image-1",
"description": "OpenAI image model for production generation, edits, and brand-safe visual workflows",
"released": "2025-04-24",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-04-24",
"family": "gpt-image",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 128000,
"output": 0
}
},
{
"id": "openai/o3",
"name": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.8182,
"output": 7.2727,
"cache_read": 0.4545
}
},
{
"id": "openai/o4-mini",
"name": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 0.99,
"output": 4,
"cache_read": 0.25
}
},
{
"id": "openai/gpt-4.1-mini",
"name": "GPT-4.1-mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.3636,
"output": 1.4545,
"cache_read": 0.0909
}
},
{
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 1.8182,
"output": 7.2727,
"cache_read": 0.4545
}
},
{
"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",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-nano",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.09,
"output": 0.36,
"cache_read": 0.022
}
},
{
"id": "xai/grok-3-mini",
"name": "Grok 3 Mini",
"description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
"released": "2025-04-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-04-11",
"family": "grok",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 0.3,
"output": 0.5,
"cache_read": 0.075
}
},
{
"id": "xai/grok-3",
"name": "Grok 3",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2025-04-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-04-11",
"family": "grok",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.75
}
},
{
"id": "openai/o1-pro",
"name": "o1-pro",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"released": "2025-03-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2025-03-19",
"family": "o-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 140,
"output": 540
}
},
{
"id": "openai/gpt-4o-mini-search",
"name": "GPT-4o-mini-Search",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2025-03-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-03-11",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.14,
"output": 0.54
}
},
{
"id": "openai/gpt-4o-search",
"name": "GPT-4o-Search",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2025-03-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-03-11",
"family": "gpt",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 2.2727,
"output": 9.0909
}
},
{
"id": "ideogramai/ideogram-v2a-turbo",
"name": "Ideogram-v2a-Turbo",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-02-27",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-02-27",
"family": "ideogram",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 150,
"output": 0
}
},
{
"id": "ideogramai/ideogram-v2a",
"name": "Ideogram-v2a",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-02-27",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-02-27",
"family": "ideogram",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 150,
"output": 0
}
},
{
"id": "lumalabs/ray2",
"name": "Ray2",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-02-20",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2025-02-20",
"family": "ray",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 5000,
"output": 0
}
},
{
"id": "anthropic/claude-sonnet-3.7",
"name": "Claude-Sonnet-3.7",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-02-19",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-10-31",
"last_updated": "2025-02-19",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 196608,
"output": 128000
},
"cost": {
"input": 2.6,
"output": 13,
"cache_read": 0.26,
"cache_write": 3.2
}
},
{
"id": "openai/o3-mini",
"name": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"released": "2024-12-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-01-29",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 0.99,
"output": 4
}
},
{
"id": "openai/o3-mini-high",
"name": "o3-mini-high",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"released": "2024-12-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-01-29",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 0.99,
"output": 4
}
},
{
"id": "google/gemini-2.0-flash",
"name": "Gemini-2.0-Flash",
"description": "Earlier Gemini Flash workhorse for responsive multimodal apps and tool use",
"released": "2024-12-11",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-06",
"last_updated": "2024-12-11",
"family": "gemini-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 990000,
"output": 8192
},
"cost": {
"input": 0.1,
"output": 0.42
}
},
{
"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",
"released": "2024-12-11",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-06",
"last_updated": "2024-12-11",
"family": "gemini-flash-lite",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 990000,
"output": 8192
},
"cost": {
"input": 0.052,
"output": 0.21
}
},
{
"id": "cerebras/llama-3.3-70b-cs",
"name": "llama-3.3-70b-cs",
"description": "Popular open Llama workhorse for multilingual chat, coding, and self-hosting",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 0,
"output": 0
}
},
{
"id": "openai/o1",
"name": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"released": "2024-12-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-12-05",
"family": "o",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 14,
"output": 54
}
},
{
"id": "topazlabs-co/topazlabs",
"name": "TopazLabs",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2024-12-03",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-12-03",
"family": "topazlabs",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 204,
"output": 0
}
},
{
"id": "google/veo-2",
"name": "Veo-2",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2024-12-02",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-12-02",
"family": "veo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "anthropic/claude-sonnet-3.5-june",
"name": "Claude-Sonnet-3.5-June",
"description": "Legacy model retained for compatibility with older integrations",
"released": "2024-11-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-11-18",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 189096,
"output": 8192
},
"cost": {
"input": 2.6,
"output": 13,
"cache_read": 0.26,
"cache_write": 3.2
}
},
{
"id": "anthropic/claude-haiku-3.5",
"name": "Claude-Haiku-3.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2024-10-22",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-07-31",
"last_updated": "2024-10-22",
"family": "claude-haiku",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 189096,
"output": 8192
},
"cost": {
"input": 0.68,
"output": 3.4,
"cache_read": 0.068,
"cache_write": 0.85
}
},
{
"id": "anthropic/claude-sonnet-3.5",
"name": "Claude-Sonnet-3.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2024-10-22",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04-30",
"last_updated": "2024-10-22",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 189096,
"output": 8192
},
"cost": {
"input": 2.6,
"output": 13,
"cache_read": 0.26,
"cache_write": 3.2
}
},
{
"id": "google/imagen-3-fast",
"name": "Imagen-3-Fast",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2024-10-17",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-10-17",
"family": "imagen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "google/imagen-3",
"name": "Imagen-3",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2024-10-15",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-10-15",
"family": "imagen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 480,
"output": 0
}
},
{
"id": "runwayml/runway",
"name": "Runway",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2024-10-11",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-10-11",
"family": "runway",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 256,
"output": 0
}
},
{
"id": "openai/gpt-4-classic-0314",
"name": "GPT-4-Classic-0314",
"description": "Legacy model retained for compatibility with older integrations",
"released": "2024-08-26",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-08-26",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 4096
},
"cost": {
"input": 27,
"output": 54
}
},
{
"id": "ideogramai/ideogram-v2",
"name": "Ideogram-v2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2024-08-21",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-08-21",
"family": "ideogram",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 150,
"output": 0
}
},
{
"id": "trytako/tako",
"name": "Tako",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"released": "2024-08-15",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-08-15",
"family": "tako",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 2048,
"output": 0
}
},
{
"id": "openai/chatgpt-4o-latest",
"name": "ChatGPT-4o-Latest",
"description": "Legacy model retained for compatibility with older integrations",
"released": "2024-08-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-08-14",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 4.5,
"output": 14
}
},
{
"id": "openai/gpt-4o-aug",
"name": "GPT-4o-Aug",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2024-08-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-08-06",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 2.2727,
"output": 9.0909,
"cache_read": 1.1364
}
},
{
"id": "cerebras/llama-3.1-8b-cs",
"name": "Llama-3.1-8B-CS",
"description": "Compact open Llama model for lightweight chat, drafting, and self-hosting",
"released": "2024-07-23",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": false,
"knowledge": "2023-12",
"last_updated": "2024-07-23",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 0
},
"cost": {
"input": 0.1,
"output": 0.1
}
},
{
"id": "elevenlabs/elevenlabs-v2.5-turbo",
"name": "ElevenLabs-v2.5-Turbo",
"description": "Low-latency multilingual text-to-speech model, superseded by Flash v2.5",
"released": "2024-07-19",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-07-19",
"family": "elevenlabs",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 128000,
"output": 0
}
},
{
"id": "openai/gpt-4o-mini",
"name": "GPT-4o-mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 124096,
"output": 4096
},
"cost": {
"input": 0.1364,
"output": 0.5455,
"cache_read": 0.0682
}
},
{
"id": "openai/gpt-4o",
"name": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"released": "2024-05-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-08-06",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
}
},
{
"id": "ideogramai/ideogram",
"name": "Ideogram",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2024-04-03",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2024-04-03",
"family": "ideogram",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 150,
"output": 0
}
},
{
"id": "anthropic/claude-haiku-3",
"name": "Claude-Haiku-3",
"description": "Legacy model retained for compatibility with older integrations",
"released": "2024-03-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-08-31",
"last_updated": "2024-03-13",
"family": "claude-haiku",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 189096,
"output": 8192
},
"cost": {
"input": 0.21,
"output": 1.1,
"cache_read": 0.021,
"cache_write": 0.26
}
},
{
"id": "openai/gpt-4-classic",
"name": "GPT-4-Classic",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-11",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 4096
},
"cost": {
"input": 27,
"output": 54
}
},
{
"id": "openai/gpt-4-turbo",
"name": "GPT-4-Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-12",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 9,
"output": 27
}
},
{
"id": "openai/dall-e-3",
"name": "DALL-E-3",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2023-11-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2023-11-06",
"family": "dall-e",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 800,
"output": 0
}
},
{
"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",
"released": "2023-09-20",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2023-09-20",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 3500,
"output": 1024
},
"cost": {
"input": 1.4,
"output": 1.8
}
},
{
"id": "stabilityai/stablediffusionxl",
"name": "StableDiffusionXL",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2023-07-09",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"last_updated": "2023-07-09",
"family": "stable-diffusion",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 200,
"output": 0
}
},
{
"id": "openai/gpt-3.5-turbo",
"name": "GPT-3.5-Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-03-01",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2021-09-01",
"last_updated": "2023-11-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 16384,
"output": 2048
},
"cost": {
"input": 0.45,
"output": 1.4
}
},
{
"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",
"released": "2023-03-01",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2021-09-01",
"last_updated": "2023-11-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 4524,
"output": 2048
},
"cost": {
"input": 0.45,
"output": 1.4
}
}
]
},
{
"id": "fastrouter",
"name": "FastRouter",
"env": [
"FASTROUTER_API_KEY"
],
"doc": "https://fastrouter.ai/models",
"api": "https://go.fastrouter.ai/api/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"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",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "google/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5,
"output": 9,
"cache_read": 0.15
}
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.74,
"output": 3.48,
"cache_read": 0.145
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-image-2",
"name": "GPT Image 2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-04-21",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-21",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 128000,
"output": 0
}
},
{
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.75,
"output": 3.5,
"cache_read": 0.15
}
},
{
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 30000
},
"cost": {
"input": 1.25,
"output": 2.5,
"cache_read": 0.2,
"tiers": [
{
"input": 2.5,
"output": 5,
"tier": {
"type": "context",
"size": 200000
}
}
],
"context_over_200k": {
"input": 2.5,
"output": 5
}
}
},
{
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-16",
"family": "grok-build",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "z-ai/glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 1.05,
"output": 3.5,
"cache_read": 0.205
}
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.3
}
},
{
"id": "google/veo3.1-lite",
"name": "Veo 3.1 Lite",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2026-03-31",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-03-31",
"family": "veo",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 400000,
"output": 0
}
},
{
"id": "minimax/minimax-m2.7-highspeed",
"name": "MiniMax-M2.7-highspeed",
"description": "Low-latency M2.7 variant for interactive coding plans and agent loops",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.6,
"output": 2.4,
"cache_read": 0.06,
"cache_write": 0.375
}
},
{
"id": "minimax/minimax-m2.7",
"name": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06,
"cache_write": 0.375
}
},
{
"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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "google/gemini-3.1-flash-image-preview",
"name": "Nano Banana 2 Preview",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-02-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-26",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 65536,
"output": 65536
},
"cost": {
"input": 0.5,
"output": 3
}
},
{
"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",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "sarvam/sarvam-30b",
"name": "Sarvam 30B",
"description": "Efficient Indian-language reasoning model for chat, coding, and multilingual work",
"released": "2026-02-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-18",
"family": "sarvam",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.02,
"output": 0.1
}
},
{
"id": "sarvam/sarvam-105b",
"name": "Sarvam 105B",
"description": "Flagship Indian-language reasoning model for enterprise multilingual applications",
"released": "2026-02-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-18",
"family": "sarvam",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.04,
"output": 0.16,
"cache_read": 0.025
}
},
{
"id": "anthropic/claude-sonnet-4.6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024,
"max": 32000
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "z-ai/glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.6,
"output": 2.08,
"cache_read": 0.12
}
},
{
"id": "bytedance/seedance-2",
"name": "Seedance 2",
"description": "ByteDance unified multimodal audio-video model supporting text, image, video and audio references, editing, extension and synchronized stereo sound.",
"released": "2026-02-12",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-10-04",
"family": "seed",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 4096,
"output": 0
}
},
{
"id": "openai/gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-02-05",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "wanx/wan-v2-6",
"name": "Wan 2.6",
"description": "Video model for text- and image-to-video with audio input and synchronized sound",
"released": "2025-12-03",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-12-03",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 400000,
"output": 0
}
},
{
"id": "google/gemini-3-pro-image-preview",
"name": "Nano Banana Pro Preview",
"description": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits",
"released": "2025-11-20",
"attachment": true,
"reasoning": true,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-11-20",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 65536,
"output": 32768
},
"cost": {
"input": 2,
"output": 12
}
},
{
"id": "google/veo3.1-fast",
"name": "Veo 3.1 Fast",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-15",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-01-01",
"family": "veo",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 400000,
"output": 0
}
},
{
"id": "google/veo3.1",
"name": "Veo 3.1",
"description": "Video model for prompt-guided generation, editing, and motion workflows",
"released": "2025-10-15",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-01",
"family": "veo",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"video"
]
},
"limit": {
"context": 400000,
"output": 0
}
},
{
"id": "openai/gpt-5-nano",
"name": "GPT-5 Nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-10-01",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.05,
"output": 0.4,
"cache_read": 0.005
}
},
{
"id": "openai/gpt-5",
"name": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-10-01",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "openai/gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-10-01",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "anthropic/claude-opus-4.1",
"name": "Claude Opus 4.1",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-08-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024,
"max": 32000
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-08-05",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 15,
"output": 75,
"cache_read": 1.5,
"cache_write": 18.75
}
},
{
"id": "openai/gpt-oss-20b",
"name": "GPT OSS 20B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.07,
"output": 0.25,
"cache_read": 0.007
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.09,
"output": 0.36
}
},
{
"id": "qwen/qwen3-coder",
"name": "Qwen3 Coder",
"description": "Open Qwen coding heavyweight for repository reasoning and agentic engineering",
"released": "2025-07-22",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-07-22",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 1.2
}
},
{
"id": "moonshotai/kimi-k2",
"name": "Kimi K2",
"description": "Kimi model for long-context chat, coding, and agentic reasoning",
"released": "2025-07-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-10",
"last_updated": "2025-07-11",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.55,
"output": 2.2
}
},
{
"id": "x-ai/grok-4",
"name": "Grok 4",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2025-07-09",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07",
"last_updated": "2025-07-09",
"family": "grok",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.75,
"cache_write": 15
}
},
{
"id": "google/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 128,
"max": 32768
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "google/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"id": "leonardo-ai/lucid-realism",
"name": "Lucid Realism",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-06-01",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-06-01",
"family": "lucid",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 4096,
"output": 0
}
},
{
"id": "leonardo-ai/lucid-origin",
"name": "Lucid Origin",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-06-01",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-06-01",
"family": "lucid",
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 4096,
"output": 0
}
},
{
"id": "anthropic/claude-sonnet-4",
"name": "Claude Sonnet 4",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-05-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024,
"max": 32000
}
],
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-05-22",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "openai/gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"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",
"released": "2025-01-23",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-10",
"last_updated": "2025-01-23",
"family": "deepseek-thinking",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.03,
"output": 0.14
}
}
]
},
{
"id": "aiand",
"name": "ai&",
"env": [
"AIAND_API_KEY"
],
"doc": "https://docs.aiand.com/",
"api": "https://api.aiand.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-ai/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 0.6,
"cache_read": 0.02
}
},
{
"id": "zai-org/glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048550,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03
}
},
{
"id": "zai-org/glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1,
"output": 4,
"cache_read": 0.3
}
},
{
"id": "qwen/qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.4,
"output": 3,
"cache_read": 0.2
}
},
{
"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.",
"released": "2026-08-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": false,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-07",
"family": "motif",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.5,
"output": 2,
"cache_read": 0.2
}
},
{
"id": "moonshotai/kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 3,
"output": 12.5,
"cache_read": 0.5
}
},
{
"id": "zai-org/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 1,
"output": 4,
"cache_read": 0.3
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.75,
"output": 3.5,
"cache_read": 0.2
}
},
{
"id": "deepseek-ai/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 384000
},
"cost": {
"input": 0.15,
"output": 0.25,
"cache_read": 0.08
}
},
{
"id": "deepseek-ai/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 384000
},
"cost": {
"input": 1,
"output": 2.5,
"cache_read": 0.25
}
},
{
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-22",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.32,
"output": 3.2,
"cache_read": 0.2
}
},
{
"id": "google/gemma-4-31b-it",
"name": "Gemma 4 31B IT",
"description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "openai/gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.08
}
}
]
},
{
"id": "databricks",
"name": "Databricks",
"env": [
"DATABRICKS_HOST",
"DATABRICKS_TOKEN"
],
"doc": "https://docs.databricks.com/aws/en/machine-learning/foundation-models/",
"api": "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "databricks-gpt-5-6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-gpt-5-6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-gpt-5-6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-glm-5-2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"id": "databricks-kimi-k2-7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "databricks-gemini-3-5-flash",
"name": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5,
"output": 9,
"cache_read": 0.15
}
},
{
"id": "databricks-gpt-5-5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "databricks-gpt-5-4-nano",
"name": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "databricks-gpt-5-4-mini",
"name": "GPT-5.4 mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "databricks-gpt-5-4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "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",
"released": "2026-03-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-03-03",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.25,
"output": 1.5,
"cache_read": 0.025
}
},
{
"id": "databricks-gemini-3-1-pro",
"name": "Gemini 3.1 Pro Preview",
"description": "Reasoning-first Gemini preview for agentic coding and complex problem solving",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "databricks-claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "High-end Claude for difficult coding, planning, and slower expert reasoning",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-03-13",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "databricks-gemini-3-flash",
"name": "Gemini 3 Flash Preview",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"released": "2025-12-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-12-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.5,
"output": 3,
"cache_read": 0.05
}
},
{
"id": "databricks-gpt-5-2",
"name": "GPT-5.2",
"description": "Reliable GPT generation for broad coding, writing, and tool-assisted product work",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "databricks-claude-opus-4-5",
"name": "Claude Opus 4.5 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-11-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "databricks-gemini-3-pro",
"name": "Gemini 3 Pro Preview",
"description": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-11-18",
"family": "gemini-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-gpt-5-1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "databricks-claude-haiku-4-5",
"name": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "databricks-claude-sonnet-4-5",
"name": "Claude Sonnet 4.5 (latest)",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-09-29",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "databricks-gpt-5",
"name": "GPT-5",
"description": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "databricks-gpt-5-nano",
"name": "GPT-5 Nano",
"description": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.05,
"output": 0.4,
"cache_read": 0.005
}
},
{
"id": "databricks-gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Small GPT-5 for responsive agents, coding help, and everyday automation",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "databricks-gpt-oss-20b",
"name": "GPT OSS 20B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 25000
},
"cost": {
"input": 0.07,
"output": 0.3
}
},
{
"id": "databricks-gpt-oss-120b",
"name": "GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 25000
},
"cost": {
"input": 0.15,
"output": 0.6
}
},
{
"id": "databricks-claude-opus-4-1",
"name": "Claude Opus 4.1 (latest)",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-08-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-08-05",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 15,
"output": 75,
"cache_read": 1.5,
"cache_write": 18.75
}
},
{
"id": "databricks-gemini-2-5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 0,
"max": 24576
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03
}
},
{
"id": "databricks-gemini-2-5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 128,
"max": 32768
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "databricks-claude-sonnet-4",
"name": "Claude Sonnet 4",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-05-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-05-22",
"family": "claude-sonnet",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
}
]
},
{
"id": "runinfra",
"name": "RunInfra",
"env": [
"RUNINFRA_GATEWAY_KEY"
],
"doc": "https://runinfra.ai/docs",
"api": "https://api.runinfra.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "zai-org/GLM-5.3-Flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 0.11,
"output": 0.45,
"cache_read": 0.03
}
},
{
"id": "ornith-ai/Ornith-1.5-35B-A3B",
"name": "Ornith 1.5 35B A3B",
"description": "Mixture-of-experts coding-reasoning model for agentic software tasks, tool use, and image understanding",
"released": "2026-08-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-23",
"family": "ornith",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01
}
},
{
"id": "zai-org/GLM-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 1.3,
"output": 4.2,
"cache_read": 0.13
}
},
{
"id": "Qwen/Qwen3.8-27B",
"name": "Qwen3.8 27B",
"description": "Dense 27B vision-language model for coding, agent tasks, and image and video understanding",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01
}
},
{
"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",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 0.6,
"output": 1.9,
"cache_read": 0.03
}
},
{
"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",
"released": "2026-08-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-12",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.2
}
},
{
"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",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-08-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.05,
"output": 0.15,
"cache_read": 0.01
}
},
{
"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",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 32768
},
"cost": {
"input": 0.13,
"output": 0.27,
"cache_read": 0.01
}
}
]
},
{
"id": "deepseek",
"name": "DeepSeek",
"env": [
"DEEPSEEK_API_KEY"
],
"doc": "https://api-docs.deepseek.com/quick_start/pricing",
"api": "https://api.deepseek.com",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.003
}
},
{
"id": "deepseek-flash",
"name": "DeepSeek V4.1 Flash 1017",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.003
}
},
{
"id": "deepseek-v4-flash-vision-exp",
"name": "DeepSeek V4 Flash Vision Exp",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.003
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.66,
"output": 1.98,
"cache_read": 0.022
}
}
]
},
{
"id": "atomic-chat",
"name": "Atomic Chat",
"env": [
"ATOMIC_CHAT_API_KEY"
],
"doc": "https://atomic.chat",
"api": "http://127.0.0.1:1337/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "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",
"released": "2026-04-02",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2026-04-02",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-02",
"family": "gemma",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2026-02-23",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2026-02-23",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-23",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "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",
"released": "2024-07-23",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-07-23",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 4096
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "cloudferro-sherlock",
"name": "CloudFerro Sherlock",
"env": [
"CLOUDFERRO_SHERLOCK_API_KEY"
],
"doc": "https://docs.sherlock.cloudferro.com/",
"api": "https://api-sherlock.cloudferro.com/openai/v1/",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "zai-org/GLM-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 0.34,
"output": 4.48
}
},
{
"id": "MiniMaxAI/MiniMax-M2.5",
"name": "MiniMax-M2.5",
"description": "MiniMax model for chat, coding, office work, and agentic tasks",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01",
"last_updated": "2026-02-12",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 196000,
"input": 180000,
"output": 16000
},
"cost": {
"input": 0.3,
"output": 1.2
}
},
{
"id": "openai/gpt-oss-120b",
"name": "OpenAI GPT OSS 120B",
"description": "Open GPT reasoning model for self-hosted agents and controllable deployments",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131000,
"output": 131000
},
"cost": {
"input": 2.92,
"output": 2.92
}
},
{
"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",
"released": "2025-03-13",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-03",
"last_updated": "2025-03-13",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 32000
},
"cost": {
"input": 0.67,
"output": 0.67
}
},
{
"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",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-10-09",
"last_updated": "2024-12-06",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 70000,
"output": 70000
},
"cost": {
"input": 2.92,
"output": 2.92
}
}
]
},
{
"id": "crossmodel",
"name": "CrossModel",
"env": [
"CROSSMODEL_API_KEY"
],
"doc": "https://www.crossmodel.ai/docs",
"api": "https://api.crossmodel.ai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "gemini/gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2
}
},
{
"id": "anthropic/claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.625,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "openai/gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5
}
}
},
{
"id": "anthropic/claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "xiaomi/mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.47,
"output": 0.94,
"cache_read": 0.005,
"cache_write": 0.47
}
},
{
"id": "xiaomi/mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.16,
"output": 0.32,
"cache_read": 0.004,
"cache_write": 0.16
}
},
{
"id": "openai/gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "x-ai/grok-4.7",
"name": "Grok 4.7",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "qwen/qwen3.8-omni-flash",
"name": "Qwen3.8 Omni Flash",
"description": "Qwen omni model for text, vision, audio, and multimodal agent tasks",
"released": "2026-09-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-17",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.13,
"output": 0.43,
"cache_read": 0.016,
"cache_write": 0.13
}
},
{
"id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006,
"cache_write": 0.3
}
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "gemini/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.75
}
},
{
"id": "anthropic/claude-fable-5-1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "tencent/hy4-preview",
"name": "Hy4 preview",
"description": "A next-generation productivity model with significantly enhanced Agent and complex task execution capabilities.",
"released": "2026-08-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-28",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.96,
"output": 2.88,
"cache_read": 0.048,
"cache_write": 0.96
}
},
{
"id": "z-ai/glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03,
"cache_write": 0.15
}
},
{
"id": "qwen/qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.13,
"output": 0.43,
"cache_read": 0.016,
"cache_write": 0.2
}
},
{
"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",
"released": "2026-08-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-01",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006,
"cache_write": 0.3
}
},
{
"id": "z-ai/glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 1.2,
"output": 4.4,
"cache_read": 0.3,
"cache_write": 1.2
}
},
{
"id": "gemini/gemini-3.7-flash",
"name": "Gemini 3.7 Flash",
"description": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.75
}
},
{
"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",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-03",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 1.88,
"output": 5.63,
"cache_read": 0.23,
"cache_write": 2.35
}
},
{
"id": "anthropic/claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "gemini/gemini-3.6-flash",
"name": "Gemini 3.6 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.75
}
},
{
"id": "gemini/gemini-3.5-flash-lite",
"name": "Gemini 3.5 Flash Lite",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03,
"cache_write": 0.3
}
},
{
"id": "moonshot/kimi-k3",
"name": "Kimi K3",
"description": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work",
"released": "2026-07-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"last_updated": "2026-07-16",
"family": "kimi-k3",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3
}
},
{
"id": "qwen/qwen3.7-flash",
"name": "Qwen3.7 Flash",
"description": "Lightweight multimodal Qwen model for high-throughput text, image, and video tasks",
"released": "2026-07-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-15",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 991808,
"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
}
}
]
}
},
{
"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",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "openai/gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "x-ai/grok-4.5",
"name": "Grok 4.5",
"description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-07-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-08",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "tencent/hy3",
"name": "Hy3",
"description": "Tencent Hy reasoning model for coding, instruction following, and agent tasks",
"released": "2026-07-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-06",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"input": 192000,
"output": 131072
},
"cost": {
"input": 0.16,
"output": 0.64,
"cache_read": 0.04,
"cache_write": 0.16
}
},
{
"id": "anthropic/claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "z-ai/glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 1.2,
"output": 4.4,
"cache_read": 0.3,
"cache_write": 1.2
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 262000
},
"cost": {
"input": 1,
"output": 4.16,
"cache_read": 0.18,
"cache_write": 1
}
},
{
"id": "anthropic/claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "qwen/qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-06-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 0.32,
"output": 1.25,
"cache_read": 0.032,
"cache_write": 0.4,
"tiers": [
{
"input": 0.96,
"output": 3.75,
"cache_read": 0.096,
"cache_write": 1.2,
"tier": {
"type": "context",
"size": 256000
}
}
],
"context_over_200k": {
"input": 0.96,
"output": 3.75,
"cache_read": 0.096,
"cache_write": 1.2
}
}
},
{
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal model for long-context coding, perception, and agent planning",
"released": "2026-06-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "qwen/qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"released": "2026-05-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-21",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 1.88,
"output": 5.63,
"cache_read": 0.375,
"cache_write": 2.35
}
},
{
"id": "gemini/gemini-3.5-flash",
"name": "Gemini 3.5 Flash",
"description": "Fast Gemini model balancing multimodal reasoning, tool use, and cost",
"released": "2026-05-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-05-19",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 1.5,
"output": 9,
"cache_read": 0.15,
"cache_write": 1.5
}
},
{
"id": "qwen/qwen3.6-flash",
"name": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-27",
"family": "qwen3.6",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006,
"cache_write": 0.3
}
},
{
"id": "deepseek/deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.35,
"output": 4.05,
"cache_read": 0.045,
"cache_write": 1.35
}
},
{
"id": "openai/gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-04-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-23",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "moonshot/kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 262000
},
"cost": {
"input": 1,
"output": 4.16,
"cache_read": 0.18,
"cache_write": 1
}
},
{
"id": "x-ai/grok-4.3",
"name": "Grok 4.3",
"description": "xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk",
"released": "2026-04-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-17",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "x-ai/grok-build-0.1",
"name": "Grok Build 0.1",
"description": "Fast Grok coding model tuned for agentic engineering and iterative edits",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-16",
"family": "grok-build",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "z-ai/glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"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
}
}
]
}
},
{
"id": "qwen/qwen3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-04-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "minimax/minimax-m2.7",
"name": "MiniMax-M2.7",
"description": "Open MiniMax flagship for coding agents, office automation, and complex environments",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-03-18",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.33,
"output": 1.32,
"cache_read": 0.066,
"cache_write": 0.42
}
},
{
"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",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075,
"cache_write": 0.75
}
},
{
"id": "openai/gpt-5.4-nano",
"name": "GPT-5.4 nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02,
"cache_write": 0.2
}
},
{
"id": "z-ai/glm-5-turbo",
"name": "GLM-5-Turbo",
"description": "Faster GLM-5 lane for coding agents that need lower latency",
"released": "2026-03-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-16",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"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
}
}
]
}
},
{
"id": "openai/gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"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
}
}
},
{
"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",
"released": "2026-02-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-02-19",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"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,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "z-ai/glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"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
}
}
]
}
},
{
"id": "z-ai/glm-4.7",
"name": "GLM-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"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
}
}
]
}
},
{
"id": "gemini/gemini-3-flash-preview",
"name": "Gemini 3 Flash Preview",
"description": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs",
"released": "2025-12-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-12-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.5,
"output": 3,
"cache_read": 0.05,
"cache_write": 0.5
}
},
{
"id": "anthropic/claude-haiku-4-5",
"name": "Claude Haiku 4.5 (latest)",
"description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
"released": "2025-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-10-15",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"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",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01,
"cache_write": 0.1
}
},
{
"id": "gemini/gemini-2.5-pro",
"name": "Gemini 2.5 Pro",
"description": "Google's proven reasoning model for coding, math, and multimodal analysis",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-pro",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gemini/gemini-2.5-flash",
"name": "Gemini 2.5 Flash",
"description": "Fast Gemini workhorse for multimodal apps where latency and price matter",
"released": "2025-06-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-06-17",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.3,
"output": 2.5,
"cache_read": 0.03,
"cache_write": 0.3
}
},
{
"id": "openai/gpt-4o-mini",
"name": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075,
"cache_write": 0.15
}
}
]
},
{
"id": "azure-cognitive-services",
"name": "Azure Cognitive Services",
"env": [
"AZURE_COGNITIVE_SERVICES_RESOURCE_NAME",
"AZURE_COGNITIVE_SERVICES_API_KEY"
],
"doc": "https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models",
"npm": "@ai-sdk/azure",
"models": [
{
"id": "claude-haiku-5-5",
"name": "Claude Haiku 5.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.5,
"output": 2.5,
"cache_read": 0.05,
"cache_write": 0.625,
"tier": {
"type": "context",
"size": 100000
}
}
]
}
},
{
"id": "gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "Near-Astra performance for complex coding, computer use, and professional work at a lower cost.",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.2,
"cache_write": 5
}
}
},
{
"id": "claude-sonnet-5-5",
"name": "Claude Sonnet 5.5",
"description": "Fast Claude model for everyday coding, agents, and knowledge work",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "gpt-6-sol",
"name": "GPT-6 Sol",
"description": "OpenAI model for complex coding and agentic workflows",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5,
"tiers": [
{
"input": 4,
"output": 15,
"cache_read": 0.4,
"cache_write": 5,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 4,
"output": 15,
"cache_read": 0.4,
"cache_write": 5
}
}
},
{
"id": "claude-opus-5-5",
"name": "Claude Opus 5.5",
"description": "Claude model for long-running agentic coding and knowledge work",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "gpt-6-luna",
"name": "GPT-6 Luna",
"description": "OpenAI's most efficient model for focused, high-volume tasks",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125,
"tiers": [
{
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02,
"cache_write": 0.25
}
}
},
{
"id": "grok-4.7",
"name": "Grok 4.7",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 500000,
"output": 500000
}
},
{
"id": "deepseek-v4.1-flash",
"name": "DeepSeek-V4.1-Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"status": "beta",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "gpt-image-2.5-sunburst",
"name": "GPT Image 2.5 Sunburst",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-09-08",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-08",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "gpt-image-2.5-flare",
"name": "GPT Image 2.5 Flare",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-09-08",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-08",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5,
"tiers": [
{
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 20,
"output": 75,
"cache_read": 2,
"cache_write": 25
}
}
},
{
"id": "claude-fable-5-1",
"name": "Claude Fable 5.1",
"description": "Claude model for demanding reasoning and long-horizon agentic work",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "grok-4.6",
"name": "Grok 4.6",
"description": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 128000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5
}
},
{
"id": "claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-luna",
"name": "GPT-5.6 Luna",
"description": "Cost-efficient GPT-5.6 model for fast, high-volume workloads",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.6-terra",
"name": "GPT-5.6 Terra",
"description": "Balanced GPT-5.6 model for capable, cost-efficient everyday work",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-terra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "claude-sonnet-5",
"name": "Claude Sonnet 5",
"description": "Everyday Claude agent model for coding, planning, browsing, and general work",
"released": "2026-06-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-30",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.19
}
},
{
"id": "claude-fable-5",
"name": "Claude Fable 5",
"description": "Claude model for creative writing, analysis, and controlled agent workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-fable",
"status": "beta",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "claude-mythos-5",
"name": "Claude Mythos 5",
"description": "Restricted Claude model for advanced cybersecurity and biology research workflows",
"released": "2026-06-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-06-09",
"family": "claude-mythos",
"status": "beta",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-31",
"last_updated": "2026-05-28",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-chat-latest",
"name": "GPT Chat Latest",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2026-05-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-05-28",
"status": "beta",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 0.5
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek-V4-Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": false,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0.19,
"output": 0.51
}
},
{
"id": "gpt-5.5",
"name": "GPT-5.5",
"description": "Default frontier GPT for coding, computer use, research, and knowledge work",
"released": "2026-04-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-12-01",
"last_updated": "2026-04-24",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 0.5,
"tiers": [
{
"input": 10,
"output": 45,
"cache_read": 1,
"tier": {
"type": "context",
"size": 272000
}
}
],
"context_over_200k": {
"input": 10,
"output": 45,
"cache_read": 1
}
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek-V4-Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"tool_call": false,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 1.74,
"output": 3.48
}
},
{
"id": "gpt-image-2",
"name": "GPT-Image-2",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-04-21",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-21",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 1.25
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4
}
},
{
"id": "claude-opus-4-7",
"name": "Claude Opus 4.7",
"description": "Stronger Opus tier for advanced software work and high-stakes reasoning",
"released": "2026-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01-31",
"last_updated": "2026-04-16",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "grok-4-20-non-reasoning",
"name": "Grok 4.20 (Non-Reasoning)",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2026-04-08",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-04-08",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 8192
},
"cost": {
"input": 2,
"output": 6
}
},
{
"id": "grok-4-20-reasoning",
"name": "Grok 4.20 (Reasoning)",
"description": "Grok model for agentic tool use, reasoning, coding, and live assistance",
"released": "2026-04-08",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-04-08",
"family": "grok",
"status": "beta",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262000,
"output": 8192
},
"cost": {
"input": 2,
"output": 6
}
},
{
"id": "gpt-5.4-mini",
"name": "GPT-5.4 Mini",
"description": "Strong small GPT for coding subagents, quick tool use, and high-volume work",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.75,
"output": 4.5,
"cache_read": 0.075
}
},
{
"id": "gpt-5.4-nano",
"name": "GPT-5.4 Nano",
"description": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation",
"released": "2026-03-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-17",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.2,
"output": 1.25,
"cache_read": 0.02
}
},
{
"id": "gpt-5.4-pro",
"name": "GPT-5.4 Pro",
"description": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.4",
"name": "GPT-5.4",
"description": "Agent-ready GPT for coding and computer-use workflows at a lower cost",
"released": "2026-03-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-05",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "gpt-5.3-codex",
"name": "GPT-5.3 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-02-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-02-24",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"description": "Claude workhorse for coding agents, careful analysis, and production cost control",
"released": "2026-02-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-08-31",
"last_updated": "2026-03-13",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "claude-opus-4-6",
"name": "Claude Opus 4.6",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2026-02-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"max"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05-31",
"last_updated": "2026-07-17",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"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
}
}
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"provider": {
"npm": "@ai-sdk/openai-compatible",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/models"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.6,
"output": 3
}
},
{
"id": "gpt-5.2-codex",
"name": "GPT-5.2 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2026-01-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2026-01-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "gpt-5.2",
"name": "GPT-5.2",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2025-12-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2025-08-31",
"last_updated": "2025-12-11",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.75,
"output": 14,
"cache_read": 0.175
}
},
{
"id": "deepseek-v3.2",
"name": "DeepSeek-V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.58,
"output": 1.68
}
},
{
"id": "deepseek-v3.2-speciale",
"name": "DeepSeek-V3.2-Speciale",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-12-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.58,
"output": 1.68
}
},
{
"id": "gpt-image-1.5",
"name": "GPT-Image-1.5",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2025-11-25",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-11-25",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 32,
"cache_read": 1.25
}
},
{
"id": "claude-opus-4-5",
"name": "Claude Opus 4.5",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
},
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-08-01",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "claude-sonnet-4-5",
"name": "Claude Sonnet 4.5",
"description": "Balanced Claude model for coding, analysis, agent workflows, and cost control",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-07-31",
"last_updated": "2025-11-18",
"family": "claude-sonnet",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3,
"cache_write": 3.75
}
},
{
"id": "claude-haiku-4-5",
"name": "Claude Haiku 4.5",
"description": "Fast Claude model for responsive assistance, classification, and lightweight agents",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-02-28",
"last_updated": "2025-11-18",
"family": "claude-haiku",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 64000
},
"cost": {
"input": 1,
"output": 5,
"cache_read": 0.1,
"cache_write": 1.25
}
},
{
"id": "claude-opus-4-1",
"name": "Claude Opus 4.1",
"description": "Flagship Claude model for deep reasoning, coding, and long-horizon agents",
"released": "2025-11-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "budget_tokens",
"min": 1024
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-03-31",
"last_updated": "2025-11-18",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://${AZURE_COGNITIVE_SERVICES_RESOURCE_NAME}.services.ai.azure.com/anthropic/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 32000
},
"cost": {
"input": 15,
"output": 75,
"cache_read": 1.5,
"cache_write": 18.75
}
},
{
"id": "gpt-5.1-codex-mini",
"name": "GPT-5.1 Codex Mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "gpt-5.1-codex",
"name": "GPT-5.1 Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5.1",
"name": "GPT-5.1",
"description": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks",
"released": "2025-11-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-14",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5.1-codex-max",
"name": "GPT-5.1 Codex Max",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-11-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-11-13",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-pro",
"name": "GPT-5 Pro",
"description": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning",
"released": "2025-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-10-06",
"family": "gpt-pro",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 15,
"output": 120
}
},
{
"id": "gpt-5-codex",
"name": "GPT-5-Codex",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-09-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-09-15",
"family": "gpt-codex",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-nano",
"name": "GPT-5 Nano",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-nano",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.05,
"output": 0.4,
"cache_read": 0.005
}
},
{
"id": "gpt-5",
"name": "GPT-5",
"description": "GPT model for general reasoning, writing, coding, and tool-assisted tasks",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-09-30",
"last_updated": "2025-08-07",
"family": "gpt",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 1.25,
"output": 10,
"cache_read": 0.125
}
},
{
"id": "gpt-5-mini",
"name": "GPT-5 Mini",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2025-08-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05-30",
"last_updated": "2025-08-07",
"family": "gpt-mini",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 400000,
"input": 272000,
"output": 128000
},
"cost": {
"input": 0.25,
"output": 2,
"cache_read": 0.025
}
},
{
"id": "grok-4-1-fast-reasoning",
"name": "Grok 4.1 Fast (Reasoning)",
"description": "Fast Grok model for responsive chat, reasoning, and tool-assisted work",
"released": "2025-06-27",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2025-06-27",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "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",
"released": "2025-06-27",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"last_updated": "2025-06-27",
"family": "grok",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"input": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.5,
"cache_read": 0.05
}
},
{
"id": "model-router",
"name": "Model Router",
"description": "Automatic model router for matching prompts to suitable backends and budgets",
"released": "2025-05-19",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"last_updated": "2025-11-18",
"family": "model-router",
"provider": {
"npm": "@ai-sdk/azure",
"shape": "completions"
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 16384
},
"cost": {
"input": 0.14,
"output": 0
}
},
{
"id": "codex-mini",
"name": "Codex Mini",
"description": "Coding-optimized GPT model for repository edits, reviews, and agentic software work",
"released": "2025-05-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-04",
"last_updated": "2025-05-16",
"family": "gpt-codex-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.5,
"output": 6,
"cache_read": 0.375
}
},
{
"id": "mistral-medium-2505",
"name": "Mistral Medium 3",
"description": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows",
"released": "2025-05-07",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2025-05-07",
"family": "mistral-medium",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 128000
},
"cost": {
"input": 0.4,
"output": 2
}
},
{
"id": "gpt-image-1",
"name": "GPT-Image-1",
"description": "OpenAI image model for production generation, edits, and brand-safe visual workflows",
"released": "2025-04-24",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2025-04-24",
"family": "gpt-image",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"image"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 5,
"output": 40,
"cache_read": 1.25
}
},
{
"id": "o3",
"name": "o3",
"description": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"id": "o4-mini",
"name": "o4-mini",
"description": "Fast o-series model for compact reasoning, coding, and tool use",
"released": "2025-04-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-04-16",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.275
}
},
{
"id": "cohere-embed-v-4-0",
"name": "Embed v4",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2025-04-15",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2025-04-15",
"family": "cohere-embed",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 1536
},
"cost": {
"input": 0.12,
"output": 0
}
},
{
"id": "gpt-4.1-mini",
"name": "GPT-4.1 mini",
"description": "Affordable GPT-4.1 lane for fast coding help and structured extraction",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.4,
"output": 1.6,
"cache_read": 0.1
}
},
{
"id": "gpt-4.1",
"name": "GPT-4.1",
"description": "Long-lived GPT workhorse for coding, instruction following, and production apps",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 2,
"output": 8,
"cache_read": 0.5
}
},
{
"id": "gpt-4.1-nano",
"name": "GPT-4.1 nano",
"description": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks",
"released": "2025-04-14",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-04",
"last_updated": "2025-04-14",
"family": "gpt-nano",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1047576,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.025
}
},
{
"id": "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",
"released": "2025-04-05",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-08",
"last_updated": "2025-04-05",
"family": "llama",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.78
}
},
{
"id": "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",
"released": "2025-04-05",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-08",
"last_updated": "2025-04-05",
"family": "llama",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 16384
},
"cost": {
"input": 0.25,
"output": 1
}
},
{
"id": "cohere-command-a",
"name": "Command A",
"description": "Cohere command model for multilingual enterprise agents, tools, and chat",
"released": "2025-03-13",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06-01",
"last_updated": "2025-03-13",
"family": "command-a",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 8192
},
"cost": {
"input": 2.5,
"output": 10
}
},
{
"id": "mistral-small-2503",
"name": "Mistral Small 3.1",
"description": "Efficient Mistral model for fast chat, extraction, and production assistants",
"released": "2025-03-01",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-09",
"last_updated": "2025-03-01",
"family": "mistral-small",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0.1,
"output": 0.3
}
},
{
"id": "deepseek-r1",
"name": "DeepSeek-R1",
"description": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools",
"released": "2025-01-20",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2024-07",
"last_updated": "2025-01-20",
"family": "deepseek-thinking",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 163840,
"output": 163840
},
"cost": {
"input": 1.35,
"output": 5.4
}
},
{
"id": "codestral-2501",
"name": "Codestral 25.01",
"description": "Mistral coding model for code completion, generation, and developer workflows",
"released": "2025-01-01",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2024-03",
"last_updated": "2025-01-01",
"family": "codestral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 256000,
"output": 256000
},
"cost": {
"input": 0.3,
"output": 0.9
}
},
{
"id": "o3-mini",
"name": "o3-mini",
"description": "Smaller o-series reasoner for economical coding, math, and planning tasks",
"released": "2024-12-20",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2024-05",
"last_updated": "2025-01-29",
"family": "o-mini",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 1.1,
"output": 4.4,
"cache_read": 0.55
}
},
{
"id": "phi-4-mini-reasoning",
"name": "Phi-4-mini-reasoning",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.075,
"output": 0.3
}
},
{
"id": "phi-4-reasoning-plus",
"name": "Phi-4-reasoning-plus",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-reasoning",
"name": "Phi-4-reasoning",
"description": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use",
"released": "2024-12-11",
"attachment": false,
"reasoning": true,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-multimodal",
"name": "Phi-4-multimodal",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"released": "2024-12-11",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.08,
"output": 0.32
}
},
{
"id": "phi-4",
"name": "Phi-4",
"description": "Open-weight instruction model for adaptable chat and self-hosted production workloads",
"released": "2024-12-11",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.125,
"output": 0.5
}
},
{
"id": "phi-4-mini",
"name": "Phi-4-mini",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2024-12-11",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-10",
"last_updated": "2024-12-11",
"family": "phi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 0.075,
"output": 0.3
}
},
{
"id": "llama-3.3-70b-instruct",
"name": "Llama-3.3-70B-Instruct",
"description": "Open Llama instruction model for multilingual chat, reasoning, and coding",
"released": "2024-12-06",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-12-06",
"family": "llama",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 32768
},
"cost": {
"input": 0.71,
"output": 0.71
}
},
{
"id": "o1",
"name": "o1",
"description": "O-series reasoning model for hard analysis, math, coding, and planning",
"released": "2024-12-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2023-09",
"last_updated": "2024-12-05",
"family": "o",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 100000
},
"cost": {
"input": 15,
"output": 60,
"cache_read": 7.5
}
},
{
"id": "ministral-3b",
"name": "Ministral 3B",
"description": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads",
"released": "2024-10-22",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-03",
"last_updated": "2024-10-22",
"family": "ministral",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.04,
"output": 0.04
}
},
{
"id": "gpt-4o-mini",
"name": "GPT-4o mini",
"description": "Small omni GPT for cheap multimodal assistance and production-scale traffic",
"released": "2024-07-18",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-07-18",
"family": "gpt-mini",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 0.15,
"output": 0.6,
"cache_read": 0.075
}
},
{
"id": "gpt-4o",
"name": "GPT-4o",
"description": "Omni-era GPT for multimodal chat, practical coding, and general assistants",
"released": "2024-05-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-09",
"last_updated": "2024-08-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 16384
},
"cost": {
"input": 2.5,
"output": 10,
"cache_read": 1.25
}
},
{
"id": "text-embedding-3-small",
"name": "text-embedding-3-small",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2024-01-25",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 1536
},
"cost": {
"input": 0.02,
"output": 0
}
},
{
"id": "text-embedding-3-large",
"name": "text-embedding-3-large",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2024-01-25",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 3072
},
"cost": {
"input": 0.13,
"output": 0
}
},
{
"id": "gpt-3.5-turbo-0125",
"name": "GPT-3.5 Turbo 0125",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2024-01-25",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2024-01-25",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 16384,
"output": 4096
},
"cost": {
"input": 0.5,
"output": 1.5
}
},
{
"id": "cohere-embed-v3-english",
"name": "Embed v3 English",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2023-11-07",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2023-11-07",
"family": "cohere-embed",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 1024
},
"cost": {
"input": 0.1,
"output": 0
}
},
{
"id": "cohere-embed-v3-multilingual",
"name": "Embed v3 Multilingual",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2023-11-07",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": false,
"last_updated": "2023-11-07",
"family": "cohere-embed",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 512,
"output": 1024
},
"cost": {
"input": 0.1,
"output": 0
}
},
{
"id": "gpt-3.5-turbo-1106",
"name": "GPT-3.5 Turbo 1106",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2023-11-06",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 16384,
"output": 4096
},
"cost": {
"input": 1,
"output": 2
}
},
{
"id": "gpt-4-turbo-vision",
"name": "GPT-4 Turbo Vision",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-11",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 10,
"output": 30
}
},
{
"id": "gpt-4-turbo",
"name": "GPT-4 Turbo",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-11-06",
"attachment": true,
"reasoning": false,
"tool_call": true,
"open_weights": false,
"temperature": true,
"knowledge": "2023-12",
"last_updated": "2024-04-09",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 4096
},
"cost": {
"input": 10,
"output": 30
}
},
{
"id": "gpt-3.5-turbo-instruct",
"name": "GPT-3.5 Turbo Instruct",
"description": "Compact GPT model for low-latency assistance and high-volume workloads",
"released": "2023-09-21",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"knowledge": "2021-08",
"last_updated": "2023-09-21",
"family": "gpt",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 4096,
"output": 4096
},
"cost": {
"input": 1.5,
"output": 2
}
},
{
"id": "text-embedding-ada-002",
"name": "text-embedding-ada-002",
"description": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines",
"released": "2022-12-15",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"last_updated": "2022-12-15",
"family": "text-embedding",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 1536
},
"cost": {
"input": 0.1,
"output": 0
}
}
]
},
{
"id": "agentrouter",
"name": "AgentRouter",
"env": [
"AGENTROUTER_API_KEY"
],
"doc": "https://agentrouter.org/docs/opencode.html",
"api": "https://agentrouter.org/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
}
},
{
"id": "claude-opus-5",
"name": "Claude Opus 5",
"description": "Strongest Claude Opus model for coding, agents, and professional work",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://agentrouter.org/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
}
},
{
"id": "gpt-5.6-sol",
"name": "GPT-5.6 Sol",
"description": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows",
"released": "2026-07-09",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-02-16",
"last_updated": "2026-07-09",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
}
},
{
"id": "claude-opus-4-8",
"name": "Claude Opus 4.8",
"description": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents",
"released": "2026-05-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-01",
"last_updated": "2026-05-28",
"family": "claude-opus",
"provider": {
"npm": "@ai-sdk/anthropic",
"api": "https://agentrouter.org/v1"
},
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
}
}
]
},
{
"id": "zai-coding-plan",
"name": "Z.AI Coding Plan",
"env": [
"ZHIPU_API_KEY"
],
"doc": "https://docs.z.ai/devpack/overview",
"api": "https://api.z.ai/api/coding/paas/v4",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "Native multimodal GLM model for efficient coding and long-horizon agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.3-highspeed",
"name": "GLM-5.3 Highspeed",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.2-highspeed",
"name": "GLM-5.2 Highspeed",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5-turbo",
"name": "GLM-5-Turbo",
"description": "Faster GLM-5 lane for coding agents that need lower latency",
"released": "2026-03-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-16",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 200000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-4.7",
"name": "GLM-4.7",
"description": "Mature GLM model for dependable coding, reasoning, and structured agent tasks",
"released": "2025-12-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-12-22",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
}
]
},
{
"id": "clarifai",
"name": "Clarifai",
"env": [
"CLARIFAI_PAT"
],
"doc": "https://docs.clarifai.com/compute/inference/",
"api": "https://api.clarifai.com/v2/ext/openai/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "moonshotai/chat-completion/models/Kimi-K2_6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4
}
},
{
"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",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 204800,
"output": 131072
},
"cost": {
"input": 0.3,
"output": 1.2
}
},
{
"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",
"released": "2025-12-01",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-12",
"last_updated": "2025-12-12",
"family": "ministral",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 2.5,
"output": 1.7
}
},
{
"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",
"released": "2025-12-01",
"attachment": false,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-10",
"last_updated": "2026-05-28",
"family": "trinity",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 131072
},
"cost": {
"input": 0.045,
"output": 0.15
}
},
{
"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",
"released": "2025-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-25",
"family": "ministral",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 1.039,
"output": 0.54825
}
},
{
"id": "deepseek-ai/deepseek-ocr/models/DeepSeek-OCR",
"name": "DeepSeek OCR",
"description": "OCR model for extracting structured text from documents and screenshots",
"released": "2025-10-20",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-25",
"family": "deepseek",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0.2,
"output": 0.7
}
},
{
"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",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 16384
},
"cost": {
"input": 0.09,
"output": 0.36
}
},
{
"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",
"released": "2025-08-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-06",
"last_updated": "2025-08-05",
"family": "gpt-oss",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 16384
},
"cost": {
"input": 0.045,
"output": 0.18
}
},
{
"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",
"released": "2025-07-31",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-25",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 0.36,
"output": 1.3
}
},
{
"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",
"released": "2025-07-31",
"attachment": false,
"reasoning": false,
"tool_call": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2025-07-31",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.11458,
"output": 0.74812
}
},
{
"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",
"released": "2025-07-28",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-07-28",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.3,
"output": 0.5
}
},
{
"id": "clarifai/main/models/mm-poly-8b",
"name": "MM Poly 8B",
"description": "Multimodal model for analyzing text, images, documents, and rich media",
"released": "2025-06",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-02-25",
"family": "mm-poly",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 4096
},
"cost": {
"input": 0.658,
"output": 1.11
}
}
]
},
{
"id": "xiaomi-token-plan-ams",
"name": "Xiaomi Token Plan (Europe)",
"env": [
"XIAOMI_API_KEY"
],
"doc": "https://platform.xiaomimimo.com/#/docs",
"api": "https://token-plan-ams.xiaomimimo.com/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo Flash model for multimodal coding agents and long-context automation",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.5-pro",
"name": "MiMo-V2.5-Pro",
"description": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution",
"released": "2026-04-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.5",
"name": "MiMo-V2.5",
"description": "Open MiMo model for multimodal coding agents and long-context automation",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2.5-tts",
"name": "MiMo-V2.5-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2.5-tts-voiceclone",
"name": "MiMo-V2.5-TTS-VoiceClone",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2.5-tts-voicedesign",
"name": "MiMo-V2.5-TTS-VoiceDesign",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-04-22",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-04-22",
"family": "mimo",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "mimo-v2-pro",
"name": "MiMo-V2-Pro",
"description": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks",
"released": "2026-03-18",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-03-18",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0
}
},
{
"id": "mimo-v2-tts",
"name": "MiMo-V2-TTS",
"description": "Speech generation model for controllable voice, narration, and audio delivery",
"released": "2026-03-18",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-03-18",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"audio"
]
},
"limit": {
"context": 8192,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "ambient",
"name": "Ambient",
"env": [
"AMBIENT_API_KEY"
],
"doc": "https://ambient.xyz",
"api": "https://api.ambient.xyz/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "ambient/small",
"name": "Ambient Small",
"description": "Efficient model for low-latency assistance, extraction, and routine automation",
"released": "2026-10-13",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-10-13",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 101072,
"output": 101072
},
"cost": {
"input": 0.001,
"output": 0.001,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "unsloth/qwen3.8-27b-gguf",
"name": "qwen3.8-27b-4q",
"description": "Tool-capable chat model for instruction following and agentic application workflows",
"released": "2026-10-13",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-10-13",
"family": "unsloth",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 101072,
"output": 101072
},
"cost": {
"input": 0.001,
"output": 0.001,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen/qwen3.8-27b",
"name": "Qwen3.8 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0.32,
"output": 3.2,
"cache_read": 0.16,
"cache_write": 0
}
},
{
"id": "deepseek/deepseek-v4-flash-0731",
"name": "DeepSeek V4 Flash 0731",
"description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 0.08,
"output": 0.18,
"cache_read": 0.016,
"cache_write": 0
}
},
{
"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",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 202752
},
"cost": {
"input": 1.2,
"output": 4.2,
"cache_read": 0.26,
"cache_write": 0
}
},
{
"id": "ambient/large",
"name": "Ambient Large",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 202752
},
"cost": {
"input": 0.6,
"output": 2,
"cache_read": 0.15,
"cache_write": 0
}
},
{
"id": "z-ai/glm-5.2",
"name": "GLM-5.2",
"description": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 202752
},
"cost": {
"input": 0.6,
"output": 2,
"cache_read": 0.15,
"cache_write": 0
}
},
{
"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",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.69,
"output": 3.49,
"cache_read": 0.14,
"cache_write": 0
}
},
{
"id": "minimax/minimax-m3",
"name": "MiniMax-M3",
"description": "MiniMax multimodal coding model for long-context reasoning and agent tasks",
"released": "2026-06-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-01",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.23,
"output": 0.96,
"cache_read": 0.05,
"cache_write": 0
}
},
{
"id": "stepfun/step-3.7-flash",
"name": "Step 3.7 Flash",
"description": "StepFun flash model for efficient multimodal reasoning, coding, and tool use",
"released": "2026-05-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-03-01",
"last_updated": "2026-05-29",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.19,
"output": 1.14,
"cache_read": 0.03,
"cache_write": 0
}
},
{
"id": "deepseek/deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek model for efficient chat, coding help, and agent loops",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 1048576
},
"cost": {
"input": 0.14,
"output": 0.28,
"cache_read": 0.028,
"cache_write": 0
}
},
{
"id": "xiaomi/mimo-v2.5",
"name": "MiMo-V2.5",
"description": "MiMo omni model for text, image, video, audio, and agents",
"released": "2026-04-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2024-12",
"last_updated": "2026-04-22",
"family": "mimo",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.4,
"output": 2,
"cache_read": 0.08,
"cache_write": 0
}
},
{
"id": "qwen/qwen3.6-27b",
"name": "Qwen3.6 27B",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-22",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 32768,
"output": 8192
},
"cost": {
"input": 0.32,
"output": 3.2,
"cache_read": 0.16,
"cache_write": 0
}
},
{
"id": "moonshotai/kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.2,
"cache_write": 0
}
},
{
"id": "qwen/qwen3.6-35b-a3b",
"name": "Qwen3.6 35B-A3B",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2026-04-17",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-17",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0.15,
"output": 1,
"cache_read": 0.15,
"cache_write": 0
}
},
{
"id": "zai-org/GLM-5.1-FP8",
"name": "GLM 5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 131072
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen/qwen3-30b-a3b-instruct-2507",
"name": "Qwen3 30B-A3B Instruct 2507",
"description": "Qwen instruction model for multilingual chat, reasoning, and tool use",
"released": "2025-07-28",
"attachment": false,
"reasoning": false,
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2025-07-28",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.09,
"output": 0.3,
"cache_read": 0.09,
"cache_write": 0
}
}
]
},
{
"id": "vispark",
"name": "Vispark",
"env": [
"VISPARK_LAB_API_KEY"
],
"doc": "https://lab.vispark.in/#vision",
"api": "https://api.lab.vispark.in/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "vispark/vision-medium",
"name": "Vision Medium",
"description": "Balanced multimodal model pairing a 1M-token context window with deeper reasoning for analysis, content creation, and tool use across text, image, audio, video, and PDF inputs.",
"released": "2024-05-15",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 4.21,
"output": 12.63
}
},
{
"id": "vispark/vision-small",
"name": "Vision Small",
"description": "Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.",
"released": "2024-05-15",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 1.05,
"output": 3.16
}
},
{
"id": "vispark/vision-large",
"name": "Vision Large",
"description": "Most capable Vision model for complex reasoning, detailed media analysis, and structured output over a 1M-token context window.",
"released": "2024-05-15",
"attachment": true,
"reasoning": true,
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09",
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 7.37,
"output": 22.11
}
}
]
},
{
"id": "alibaba-token-plan-cn",
"name": "Alibaba Token Plan (China)",
"env": [
"ALIBABA_TOKEN_PLAN_API_KEY"
],
"doc": "https://www.alibabacloud.com/help/zh/model-studio/token-plan-overview",
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com/compatible-mode/v1",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "deepseek-v4.1-flash-1017",
"name": "DeepSeek V4.1 Flash 1017",
"description": "October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash model for reasoning and agentic coding",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens",
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.3",
"name": "GLM-5.3",
"description": "Flagship GLM model for long-horizon coding, agents, and complex project delivery",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "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",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens",
"min": 0,
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-03",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "deepseek-v4-flash-0731",
"name": "DeepSeek V4 Flash 0731",
"description": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen3.8-max-preview",
"name": "Qwen3.8 Max Preview",
"description": "Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows",
"released": "2026-07-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
},
{
"type": "budget_tokens",
"min": 0,
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-19",
"family": "qwen",
"status": "deprecated",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "happyhorse-1.1-i2v",
"name": "HappyHorse 1.1 Image-to-Video",
"description": "Video model for image-to-video generation",
"released": "2026-07-17",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-17",
"provider": {
"npm": "@ai-sdk/alibaba",
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com"
},
"modalities": {
"input": [
"image",
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "happyhorse-1.1-t2v",
"name": "HappyHorse 1.1 Text-to-Video",
"description": "Video model for prompt-driven text-to-video generation",
"released": "2026-07-17",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-17",
"provider": {
"npm": "@ai-sdk/alibaba",
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com"
},
"modalities": {
"input": [
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "happyhorse-1.1-r2v",
"name": "HappyHorse 1.1 Reference-to-Video",
"description": "Video model for reference-guided video generation",
"released": "2026-07-17",
"attachment": true,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-07-17",
"provider": {
"npm": "@ai-sdk/alibaba",
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com"
},
"modalities": {
"input": [
"image",
"text"
],
"output": [
"video"
]
},
"limit": {
"context": 0,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "glm-5.2",
"name": "GLM-5.2",
"description": "Open flagship GLM for long-horizon coding agents and million-token context work",
"released": "2026-06-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-06-13",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "kimi-k2.7-code",
"name": "Kimi K2.7 Code",
"description": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking",
"released": "2026-06-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": false,
"knowledge": "2025-01",
"last_updated": "2026-06-12",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen3.7-plus",
"name": "Qwen3.7 Plus",
"description": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding",
"released": "2026-06-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-06-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "wan2.7-image-pro",
"name": "Wan2.7 Image Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-05-29",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-29",
"provider": {
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 8192,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "wan2.7-image",
"name": "Wan2.7 Image",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-05-29",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-29",
"provider": {
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 8192,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen3.7-max",
"name": "Qwen3.7 Max",
"description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
"released": "2026-05-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"max": 262144
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-05-21",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen3.6-flash",
"name": "Qwen3.6 Flash",
"description": "Qwen vision-language model for visual reasoning, documents, and agent tasks",
"released": "2026-04-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"max": 131072
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-04-27",
"family": "qwen3.6",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "deepseek-v4-flash",
"name": "DeepSeek V4 Flash",
"description": "Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-flash",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "deepseek-v4-pro",
"name": "DeepSeek V4 Pro",
"description": "Open MoE flagship with million-token context for coding and long agent runs",
"released": "2026-04-24",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "effort",
"values": [
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-04-24",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 384000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "kimi-k2.6",
"name": "Kimi K2.6",
"description": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context",
"released": "2026-04-20",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-04-20",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 262144
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5.1",
"name": "GLM-5.1",
"description": "Strong GLM coding model for agentic engineering, terminals, and repository generation",
"released": "2026-04-07",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-04-07",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 128000
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen3.6-plus",
"name": "Qwen3.6 Plus",
"description": "Earlier Qwen multimodal workhorse for million-token agent and document tasks",
"released": "2026-04-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
},
{
"type": "budget_tokens",
"max": 131072
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"knowledge": "2025-04",
"last_updated": "2026-04-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "qwen-image-2.0-pro",
"name": "Qwen Image 2.0 Pro",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-03-03",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-03",
"family": "qwen",
"provider": {
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 8192,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "qwen-image-2.0",
"name": "Qwen Image 2.0",
"description": "Image model for prompt-driven generation, editing, and visual design workflows",
"released": "2026-03-03",
"attachment": false,
"reasoning": false,
"tool_call": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-03-03",
"family": "qwen",
"provider": {
"api": "https://token-plan.cn-beijing.maas.aliyuncs.com/api/v1"
},
"modalities": {
"input": [
"text"
],
"output": [
"image"
]
},
"limit": {
"context": 8192,
"output": 0
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "MiniMax-M2.5",
"name": "MiniMax-M2.5",
"description": "Prior MiniMax coding model for agent workflows, office edits, and automation",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"tool_call": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"last_updated": "2026-02-12",
"family": "minimax",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 196608,
"input": 196601,
"output": 32768
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "glm-5",
"name": "GLM-5",
"description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
"released": "2026-02-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": false,
"temperature": true,
"last_updated": "2026-02-12",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 202752,
"output": 16384
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"description": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work",
"released": "2026-01-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"interleaved": {
"field": "reasoning_content"
},
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2026-01-27",
"family": "kimi-k2",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 98304
},
"cost": {
"input": 0,
"output": 0,
"cache_read": 0,
"cache_write": 0
}
},
{
"id": "deepseek-v3.2",
"name": "DeepSeek V3.2",
"description": "DeepSeek chat model for instruction following, coding, and analysis",
"released": "2025-12-03",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "toggle"
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-01",
"last_updated": "2025-12-05",
"family": "deepseek",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
}
]
},
{
"id": "kilo",
"name": "Kilo Gateway",
"env": [
"KILO_API_KEY"
],
"doc": "https://kilo.ai",
"api": "https://api.kilo.ai/api/gateway",
"npm": "@ai-sdk/openai-compatible",
"models": [
{
"id": "recursive/flint-v1.0:free",
"name": "Recursive: Flint (free)",
"description": "Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...",
"released": "2026-10-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-21",
"family": "flint",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "minimax/minimax-m3.1-flash:free",
"name": "MiniMax: MiniMax M3.1 Flash (free)",
"description": "MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...",
"released": "2026-10-19",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-19",
"family": "minimax",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 524288
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "deepseek/deepseek-v4.1-flash-1017",
"name": "DeepSeek V4.1 Flash 1017",
"description": "DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-10-17",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "elorian/glimpse",
"name": "Elorian: Glimpse",
"description": "Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...",
"released": "2026-10-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-17",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 256000
},
"cost": {
"input": 0.6,
"output": 3,
"cache_read": 0.06
}
},
{
"id": "xingchen-agi/xing4.0-29b-a4b:free",
"name": "XingChen: Xing4.0 29B A4B (free)",
"description": "Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...",
"released": "2026-10-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-16",
"family": "agi",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "inception/mercury-3",
"name": "Inception: Mercury 3",
"description": "Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...",
"released": "2026-10-16",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-16",
"family": "mercury",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.2,
"output": 0.7,
"cache_read": 0.02
}
},
{
"id": "moondream/moondream3-preview",
"name": "Moondream: Moondream 3 Preview",
"description": "Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-15",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.3,
"output": 2.5
}
},
{
"id": "moondream/moondream3.1-9b-a2b",
"name": "Moondream: Moondream 3.1",
"description": "Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": false,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-15",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 32000,
"output": 4096
},
"cost": {
"input": 0.3,
"output": 2.5
}
},
{
"id": "meta/muse-spark-open",
"name": "Muse Spark Open",
"description": "Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01-04",
"last_updated": "2026-10-15",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"id": "nvidia/nemotron-3.5-super-vl",
"name": "NVIDIA: Nemotron 3.5 Super VL",
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-10-15",
"family": "nemotron",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.08
}
},
{
"id": "nvidia/nemotron-3.5-super-vl:free",
"name": "NVIDIA: Nemotron 3.5 Super VL (free)",
"description": "NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... **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).",
"released": "2026-10-15",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-10-15",
"family": "nemotron",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0,
"output": 0
}
},
{
"id": "unbiased/pareto-26.10",
"name": "Pareto 26.10",
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
"released": "2026-10-15",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-15",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.8,
"output": 3.2,
"cache_read": 0.03
}
},
{
"id": "liquid/lfm-2.5-24b-a2b",
"name": "LiquidAI: LFM2.5-24B-A2B",
"description": "LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...",
"released": "2026-10-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-13",
"family": "liquid",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 128000,
"output": 8192
},
"cost": {
"input": 0.05,
"output": 0.7,
"cache_read": 0.025
}
},
{
"id": "~unbiased/pareto-latest",
"name": "Pareto Latest",
"description": "This model always redirects to the latest model in the Pareto family.",
"released": "2026-10-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-13",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.8,
"output": 3.2,
"cache_read": 0.03
}
},
{
"id": "scaledown/summarize",
"name": "ScaleDown: Summarize",
"description": "Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...",
"released": "2026-10-13",
"attachment": true,
"reasoning": false,
"tool_call": false,
"structured_output": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-10-13",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 4000
},
"cost": {
"input": 0.05,
"output": 0
}
},
{
"id": "scaledown/extract",
"name": "ScaleDown: Extract",
"description": "Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...",
"released": "2026-10-13",
"attachment": true,
"reasoning": false,
"tool_call": false,
"structured_output": false,
"open_weights": false,
"temperature": false,
"last_updated": "2026-10-13",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 900000
},
"cost": {
"input": 0.05,
"output": 0
}
},
{
"id": "google/gemini-4-argon",
"name": "Gemini 4 Argon",
"description": "Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...",
"released": "2026-10-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-10-13",
"family": "gemini",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 0.1875
}
},
{
"id": "unbiased/pareto-26.9",
"name": "Pareto 26.9",
"description": "Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.",
"released": "2026-10-13",
"attachment": true,
"reasoning": false,
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-13",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 131072
},
"cost": {
"input": 2.5,
"output": 7.5,
"cache_read": 0.25
}
},
{
"id": "meta/muse-wonder",
"name": "Meta: Muse Wonder",
"description": "Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...",
"released": "2026-10-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-12",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2
}
},
{
"id": "anthropic/claude-haiku-5.5",
"name": "Claude Haiku 5.5",
"description": "Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...",
"released": "2026-10-07",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-10-07",
"family": "claude-haiku",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125
}
},
{
"id": "mistralai/mistral-large-4-0",
"name": "Mistral: Mistral Large 4",
"description": "Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 512K-token context window with up...",
"released": "2026-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-06",
"family": "mistral-large",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 262144
},
"cost": {
"input": 1.36,
"output": 4.18,
"cache_read": 0.14
}
},
{
"id": "google/gemini-nano-banana-2.1",
"name": "Nano Banana 2.1",
"description": "Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...",
"released": "2026-10-06",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-10-06",
"family": "gemini-flash",
"modalities": {
"input": [
"image",
"text",
"pdf"
],
"output": [
"text",
"image"
]
},
"limit": {
"context": 65536,
"output": 58982
},
"cost": {
"input": 1.5,
"output": 7.5
}
},
{
"id": "reflection/beam-1.0-501b-a23b",
"name": "Reflection: Beam 1.0 501B A23B",
"description": "Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...",
"released": "2026-10-05",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-06-30",
"last_updated": "2026-10-16",
"family": "beam",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.25,
"output": 1,
"cache_read": 0.05
}
},
{
"id": "inclusionai/ling-3.1-flash",
"name": "inclusionAI: Ling 3.1 Flash",
"description": "Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.",
"released": "2026-09-29",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-29",
"family": "ling",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0.3,
"output": 0.9,
"cache_read": 0.06
}
},
{
"id": "openai/gpt-6.1-sol",
"name": "GPT-6.1 Sol",
"description": "GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-29",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "openai/gpt-6.1-sol-pro",
"name": "OpenAI: GPT-6.1 Sol Pro",
"description": "GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...",
"released": "2026-09-29",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-29",
"family": "gpt",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-sonnet-5.5",
"name": "Claude Sonnet 5.5",
"description": "Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...",
"released": "2026-09-28",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-28",
"family": "claude-sonnet",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "perceptron/perceptron-mk1.5",
"name": "Perceptron: Perceptron Mk1.5",
"description": "Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...",
"released": "2026-09-25",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-25",
"modalities": {
"input": [
"text",
"image",
"video",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 36864,
"output": 8192
},
"cost": {
"input": 0.15,
"output": 1.5
}
},
{
"id": "aion-labs/aion-3.5-mini",
"name": "AionLabs: Aion 3.5 Mini",
"description": "Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...",
"released": "2026-09-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-23",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.7,
"output": 1.4,
"cache_read": 0.18
}
},
{
"id": "aion-labs/aion-3.5",
"name": "AionLabs: Aion 3.5",
"description": "Aion 3.5 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...",
"released": "2026-09-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-23",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 3,
"output": 6,
"cache_read": 0.75
}
},
{
"id": "z-ai/glm-5.3-prime",
"name": "Z.ai: GLM 5.3 Prime",
"description": "GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...",
"released": "2026-09-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-23",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 2.8,
"output": 8.8,
"cache_read": 0.56
}
},
{
"id": "qwen/qwen3.8-max-prime",
"name": "Qwen 3.8 Max Prime",
"description": "Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...",
"released": "2026-09-23",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-23",
"family": "qwen3.8-max",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 4,
"output": 12,
"cache_read": 0.5
}
},
{
"id": "anthropic/claude-opus-5.5",
"name": "Claude Opus 5.5",
"description": "Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-22",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 4,
"output": 20,
"cache_read": 0.2,
"cache_write": 5
}
},
{
"id": "upstage/solar-mini4",
"name": "Upstage: Solar Mini 4",
"description": "Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...",
"released": "2026-09-22",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02",
"last_updated": "2026-09-22",
"family": "solar-mini",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 131072
},
"cost": {
"input": 0.1,
"output": 0.4,
"cache_read": 0.01
}
},
{
"id": "fireworks/ember-1",
"name": "Fireworks: Ember-1",
"description": "Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-22",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 3,
"output": 15,
"cache_read": 0.3
}
},
{
"id": "xiaomi/mimo-v2.6-pro",
"name": "MiMo-V2.6-Pro",
"description": "MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.43,
"output": 0.87,
"cache_read": 0.0036
}
},
{
"id": "xiaomi/mimo-v2.6-flash",
"name": "MiMo-V2.6-Flash",
"description": "MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employs a hybrid attention mechanism for...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-22",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.1,
"output": 0.28,
"cache_read": 0.05
}
},
{
"id": "openai/gpt-6-luna-pro",
"name": "OpenAI: GPT-6 Luna Pro",
"description": "GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-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",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-22",
"family": "gpt",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125
}
},
{
"id": "openai/gpt-6-sol-pro",
"name": "OpenAI: GPT-6 Sol Pro",
"description": "GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-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",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-22",
"family": "gpt",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "openai/gpt-6-sol",
"name": "GPT-6 Sol",
"description": "GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-20",
"last_updated": "2026-09-22",
"family": "gpt-sol",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "openai/gpt-6-luna",
"name": "GPT-6 Luna",
"description": "GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...",
"released": "2026-09-22",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05-18",
"last_updated": "2026-09-22",
"family": "gpt-luna",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125
}
},
{
"id": "x-ai/grok-4.7",
"name": "Grok 4.7",
"description": "Grok 4.7 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-05",
"last_updated": "2026-09-21",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 500000,
"output": 450000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5
}
},
{
"id": "xiaomi/mimo-v2.6-pro-ultraspeed",
"name": "MiMo-V2.6-Pro-UltraSpeed",
"description": "MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original model in quality while delivering roughly 10x...",
"released": "2026-09-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-21",
"family": "mimo",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 4.35,
"output": 8.7,
"cache_read": 0.036
}
},
{
"id": "prism-ml/ternary-bonsai-2-27b",
"name": "PrismML: Ternary Bonsai 2 27B",
"description": "Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks...",
"released": "2026-09-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-18",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.075,
"output": 0.5,
"cache_read": 0.0375
}
},
{
"id": "z-ai/glm-5.3-flashx",
"name": "Z.ai: GLM 5.3 FlashX",
"description": "GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...",
"released": "2026-09-18",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-18",
"family": "glm",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.37,
"output": 1.25,
"cache_read": 0.09
}
},
{
"id": "qwen/qwen3.8-omni-flash",
"name": "Qwen3.8 Omni Flash",
"description": "Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...",
"released": "2026-09-17",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-17",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"audio",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.47,
"cache_read": 0.016
}
},
{
"id": "stepfun/step-5-preview",
"name": "Step 5 Preview",
"description": "Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...",
"released": "2026-09-16",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-20",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"input": 1000000,
"output": 64000
},
"cost": {
"input": 1,
"output": 2.7,
"cache_read": 0.1
}
},
{
"id": "~deepseek/deepseek-flash-latest",
"name": "DeepSeek: DeepSeek Flash Latest",
"description": "This model always redirects to the latest model in the DeepSeek Flash family.",
"released": "2026-09-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-14",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.07,
"output": 0.5,
"cache_read": 0.008
}
},
{
"id": "~deepseek/deepseek-pro-latest",
"name": "DeepSeek: DeepSeek Pro Latest",
"description": "This model always redirects to the latest model in the DeepSeek Pro family.",
"released": "2026-09-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-14",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 0.2235,
"output": 8,
"cache_read": 0.22
}
},
{
"id": "~openai/gpt-astra-latest",
"name": "OpenAI: GPT Astra Latest ($$$$)",
"description": "This model always redirects to the latest model in the OpenAI GPT Astra family.",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "gpt-astra",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "~openai/gpt-terra-latest",
"name": "OpenAI: GPT Terra Latest",
"description": "This model always redirects to the latest model in the OpenAI GPT Terra family.",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "gpt-terra",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2,
"output": 12,
"cache_read": 0.2,
"cache_write": 2.5
}
},
{
"id": "~openai/gpt-sol-latest",
"name": "OpenAI: GPT Sol Latest",
"description": "This model always redirects to the latest model in the OpenAI GPT Sol family.",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "gpt-sol",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 2,
"output": 10,
"cache_read": 0.1,
"cache_write": 2.5
}
},
{
"id": "~openai/gpt-luna-latest",
"name": "OpenAI: GPT Luna Latest",
"description": "This model always redirects to the latest model in the OpenAI GPT Luna family.",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "gpt-luna",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 0.1,
"output": 0.5,
"cache_read": 0.01,
"cache_write": 0.125
}
},
{
"id": "sakana/fugu-ultra-v2",
"name": "Fugu Ultra v2",
"description": "Fugu Ultra v2 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...",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-08-28",
"last_updated": "2026-09-11",
"family": "fugu",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 30,
"cache_read": 0.5
}
},
{
"id": "sakana/fugu-max",
"name": "Fugu Max",
"description": "Fugu Max is the cost-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...",
"released": "2026-09-11",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-11",
"family": "fugu",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25
}
},
{
"id": "deepseek/deepseek-v4.1-flash",
"name": "DeepSeek V4.1 Flash",
"description": "DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the cost-efficient tier of the V4.1 family. DeepSeek reports that it exceeds V4 Pro on performance, speed, and task...",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-09-10",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.006
}
},
{
"id": "inclusionai/ling-3.0-flash-vl",
"name": "inclusionAI: Ling 3.0 Flash VL",
"description": "Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...",
"released": "2026-09-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-10",
"family": "ling",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 32768
},
"cost": {
"input": 0.06,
"output": 0.18,
"cache_read": 0.012
}
},
{
"id": "nex-agi/nex-n2.5-mini",
"name": "Nex AGI: Nex-N2.5-Mini",
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
"released": "2026-09-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"medium",
"high"
]
}
],
"tool_call": false,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-08",
"family": "agi",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0.025,
"output": 0.1,
"cache_read": 0.0025
}
},
{
"id": "nex-agi/nex-n2.5-pro",
"name": "Nex AGI: Nex-N2.5-Pro",
"description": "Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...",
"released": "2026-09-08",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-08",
"family": "agi",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0.075,
"output": 0.25,
"cache_read": 0.015
}
},
{
"id": "inception/mercury-2.5",
"name": "Inception: Mercury 2.5",
"description": "Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...",
"released": "2026-09-08",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-08",
"family": "mercury",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 260000,
"output": 65536
},
"cost": {
"input": 0.2,
"output": 0.75,
"cache_read": 0.02
}
},
{
"id": "openai/gpt-6-astra",
"name": "GPT-6 Astra",
"description": "GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particular strengths in long-horizon...",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-04-30",
"last_updated": "2026-09-04",
"family": "gpt-astra",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"input": 922000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "openai/gpt-6-astra-pro",
"name": "OpenAI: GPT-6 Astra Pro ($$$$)",
"description": "GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), 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",
"released": "2026-09-04",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-09-04",
"family": "gpt",
"modalities": {
"input": [
"pdf",
"image",
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1050000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 1,
"cache_write": 12.5
}
},
{
"id": "meta/muse-spark-1.3-contributor",
"name": "Meta: Muse Spark 1.3 Contributor",
"description": "Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and coding workflows. It is designed to track information...",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.1,
"output": 0.2,
"cache_read": 0.002
}
},
{
"id": "meta/muse-spark-1.3",
"name": "Muse Spark 1.3",
"description": "Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through...",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"id": "google/gemini-3.8-flash",
"name": "Gemini 3.8 Flash",
"description": "Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows.",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.041667
}
},
{
"id": "qwen/qwen3.8-max-0902",
"name": "Qwen3.8 Max 0902",
"description": "Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...",
"released": "2026-09-02",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-09-02",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25,
"cache_write": 2.5
}
},
{
"id": "anthropic/claude-fable-5.1",
"name": "Claude Fable 5.1",
"description": "Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual...",
"released": "2026-09-01",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-06",
"last_updated": "2026-09-01",
"family": "claude-fable",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 10,
"output": 50,
"cache_read": 0.25,
"cache_write": 12.5
}
},
{
"id": "tencent/hy4-preview",
"name": "Hy4 preview",
"description": "Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...",
"released": "2026-08-28",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-28",
"family": "Hy",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 64000
},
"cost": {
"input": 0.834,
"output": 2.501,
"cache_read": 0.042
}
},
{
"id": "~z-ai/glm-flash-latest",
"name": "Z.ai: GLM Flash Latest",
"description": "This model always redirects to the latest model in the GLM Flash family.",
"released": "2026-08-27",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-27",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.0132,
"output": 0.1589,
"cache_read": 0.0132
}
},
{
"id": "z-ai/glm-5.3-flash",
"name": "GLM-5.3-Flash",
"description": "GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-26",
"family": "glm-flash",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.15,
"output": 0.5,
"cache_read": 0.03
}
},
{
"id": "qwen/qwen3.8-flash",
"name": "Qwen3.8 Flash",
"description": "Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.",
"released": "2026-08-26",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-26",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 131072
},
"cost": {
"input": 0.15,
"output": 0.47,
"cache_read": 0.016,
"cache_write": 0.2
}
},
{
"id": "ibm-granite/granite-4.2-8b",
"name": "IBM: Granite 4.2 8B",
"description": "Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...",
"released": "2026-08-25",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-25",
"family": "granite",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 117964
},
"cost": {
"input": 0.06,
"output": 0.25,
"cache_read": 0.015
}
},
{
"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,...",
"released": "2026-08-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-09-01",
"family": "deepseek-flash",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 262144
},
"cost": {
"input": 0.2156,
"output": 0.6468,
"cache_read": 0.00686
}
},
{
"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...",
"released": "2026-08-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-21",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.1,
"output": 0.2,
"cache_read": 0.002
}
},
{
"id": "~z-ai/glm-latest",
"name": "Z.ai: GLM Latest",
"description": "This model always redirects to the latest GLM model from Z.ai.",
"released": "2026-08-19",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-19",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.079,
"output": 1.4,
"cache_read": 0.078
}
},
{
"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...",
"released": "2026-08-14",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "glm",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 1.4,
"output": 4.4,
"cache_read": 0.26
}
},
{
"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...",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-14",
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"limit": {
"context": 512000,
"output": 460800
},
"cost": {
"input": 0,
"output": 0
}
},
{
"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...",
"released": "2026-08-14",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-14",
"family": "qwen",
"modalities": {
"input": [
"text",
"image",
"video"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.425,
"output": 2.55,
"cache_read": 0.085,
"cache_write": 0.53125
}
},
{
"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.",
"released": "2026-08-13",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-22",
"family": "deepseek-thinking",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 393216
},
"cost": {
"input": 1.32,
"output": 3.96,
"cache_read": 0.044
}
},
{
"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...",
"released": "2026-08-13",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-08-13",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.75,
"output": 3.75,
"cache_read": 0.075,
"cache_write": 0.041667
}
},
{
"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.",
"released": "2026-08-12",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02-01",
"last_updated": "2026-08-12",
"family": "grok",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 500000,
"output": 450000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.5
}
},
{
"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",
"released": "2026-08-12",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"last_updated": "2026-08-12",
"family": "qwen",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1010000,
"output": 909000
},
"cost": {
"input": 2,
"output": 6,
"cache_read": 0.25,
"cache_write": 2.5
}
},
{
"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...",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-11",
"family": "liquid",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 65536,
"output": 8192
},
"cost": {
"input": 0,
"output": 0
}
},
{
"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...",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-08-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 235929
},
"cost": {
"input": 0.025,
"output": 0.12,
"cache_read": 0.0125
}
},
{
"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).",
"released": "2026-08-11",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"knowledge": "2025-09",
"last_updated": "2026-08-11",
"family": "nemotron",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 65536
},
"cost": {
"input": 0,
"output": 0
}
},
{
"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...",
"released": "2026-08-10",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2026-01-04",
"last_updated": "2026-08-10",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 131072,
"output": 16384
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.04
}
},
{
"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.",
"released": "2026-08-06",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-02",
"last_updated": "2026-08-06",
"family": "solar-pro",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 131072
},
"cost": {
"input": 0.3,
"output": 1.2,
"cache_read": 0.06
}
},
{
"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...",
"released": "2026-08-05",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high",
"xhigh"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-05",
"family": "muse",
"modalities": {
"input": [
"text",
"image",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 1.25,
"output": 4.25,
"cache_read": 0.15
}
},
{
"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,...",
"released": "2026-08-03",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"last_updated": "2026-08-03",
"family": "sakana-namazu",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 65536
},
"cost": {
"input": 0.95,
"output": 4,
"cache_read": 0.15
}
},
{
"id": "~deepseek/deepseek-v4-flash-latest",
"name": "DeepSeek: DeepSeek V4 Flash Latest",
"description": "This model always redirects to the latest model in the DeepSeek V4 Flash family.",
"released": "2026-08-01",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"last_updated": "2026-08-01",
"family": "deepseek",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 943718
},
"cost": {
"input": 0.0475,
"output": 0.1568,
"cache_read": 0.028
}
},
{
"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.",
"released": "2026-07-31",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": true,
"temperature": true,
"knowledge": "2025-05",
"last_updated": "2026-07-31",
"family": "deepseek-flash",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.44,
"output": 1.32,
"cache_read": 0.028
}
},
{
"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...",
"released": "2026-07-30",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"minimal",
"low",
"medium",
"high",
"max"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-30",
"family": "ling",
"modalities": {
"input": [
"text",
"image",
"audio"
],
"output": [
"text"
]
},
"limit": {
"context": 524288,
"output": 262144
},
"cost": {
"input": 0.45,
"output": 1.2,
"cache_read": 0.1
}
},
{
"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...",
"released": "2026-07-24",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": false,
"knowledge": "2026-05",
"last_updated": "2026-07-24",
"family": "claude-opus",
"modalities": {
"input": [
"text",
"image",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1000000,
"output": 128000
},
"cost": {
"input": 5,
"output": 25,
"cache_read": 0.5,
"cache_write": 6.25
}
},
{
"id": "inclusionai/ling-3.0-flash",
"name": "inclusionAI: 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...",
"released": "2026-07-23",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-23",
"family": "ling",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 262144,
"output": 32768
},
"cost": {
"input": 0.06,
"output": 0.18,
"cache_read": 0.012
}
},
{
"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...",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.375,
"output": 1.875,
"cache_read": 0.0375,
"cache_write": 0.020833
}
},
{
"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.",
"released": "2026-07-21",
"attachment": true,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"minimal",
"low",
"medium",
"high"
]
}
],
"tool_call": true,
"structured_output": true,
"open_weights": false,
"temperature": true,
"knowledge": "2026-03",
"last_updated": "2026-07-21",
"family": "gemini-flash-lite",
"modalities": {
"input": [
"text",
"image",
"video",
"audio",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 65536
},
"cost": {
"input": 0.15,
"output": 1.25,
"cache_read": 0.015,
"cache_write": 0.041667
}
},
{
"id": "poolside/laguna-s-2.1",
"name": "Poolside: Laguna S 2.1 (retires Oct 31)",
"description": "Laguna S 2.1 is the latest coding agent model from [Poolside](). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and...",
"released": "2026-07-21",
"attachment": false,
"reasoning": true,
"reasoning_options": [
{
"type": "effort",
"values": [
"none",
"high"
]
}
],
"tool_call": true,
"structured_output": false,
"open_weights": true,
"temperature": true,
"last_updated": "2026-07-21",
"family": "laguna",
"status": "deprecated",
"modalities": {
"input": [
"text"
],
"output": [
"text"
]
},
"limit": {
"context": 1048576,
"output": 131072
},
"cost": {
"input": 0.1,
"output": 0.2,
"cache_read": 0.01
}
},
{
"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](