{"generated_at":"2026-07-29T08:15:45.766Z","models":[{"id":"ai21/jamba-large-1.7","name":"AI21: Jamba Large 1.7","provider":"ai21","provider_display":"AI21","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":4096,"uptime_30m":100,"pricing":{"input":2,"output":8,"cache_read":null,"cache_write":null},"org":"ai21"},{"id":"aion-labs/aion-2.0","name":"AionLabs: Aion-2.0","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.7999999999999999,"output":1.5999999999999999,"cache_read":0.19999999999999998,"cache_write":null},"org":"aion-labs"},{"id":"aion-labs/aion-3.0","name":"AionLabs: Aion-3.0","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":3,"output":6,"cache_read":0.75,"cache_write":null},"org":"aion-labs"},{"id":"aion-labs/aion-3.0-mini","name":"AionLabs: Aion-3.0-Mini","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.7,"output":1.4,"cache_read":0.18,"cache_write":null},"org":"aion-labs"},{"id":"aion-labs/aion-rp-llama-3.1-8b","name":"AionLabs: Aion-RP 1.0 (8B)","provider":"aionlabs","provider_display":"AionLabs","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.7999999999999999,"output":1.5999999999999999,"cache_read":null,"cache_write":null},"org":"aion-labs"},{"id":"allenai/olmo-3-32b-think","name":"AllenAI: Olmo 3 32B Think","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":65536,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.15,"output":0.5,"cache_read":null,"cache_write":null},"org":"allenai","zdr":true},{"id":"amazon/nova-2-lite-v1","name":"Amazon: Nova 2 Lite","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65535,"uptime_30m":100,"pricing":{"input":0.3,"output":2.5,"cache_read":null,"cache_write":null},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-2-lite-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-01","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":18.2,"coding_index":23,"agentic_index":3.1,"design_arena_best":null}},{"id":"amazon/nova-lite-v1","name":"Amazon: Nova Lite 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":300000,"max_completion_tokens":5120,"uptime_30m":null,"pricing":{"input":0.06,"output":0.24,"cache_read":0.015,"cache_write":null},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-lite-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false}},{"id":"amazon/nova-micro-v1","name":"Amazon: Nova Micro 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":5120,"uptime_30m":11.90227764346609,"pricing":{"input":0.035,"output":0.14,"cache_read":0.00875,"cache_write":null},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-micro-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"amazon/nova-premier-v1","name":"Amazon: Nova Premier 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":2.5,"output":12.5,"cache_read":0.625,"cache_write":null},"org":"amazon","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":860,"win_rate":26.2,"rank":116}}},{"id":"amazon/nova-pro-v1","name":"Amazon: Nova Pro 1.0","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":300000,"max_completion_tokens":5120,"uptime_30m":100,"pricing":{"input":0.7999999999999999,"output":3.1999999999999997,"cache_read":0.2,"cache_write":null},"org":"amazon","zdr":true,"modelsdev":{"base_url":null,"model_id":"amazon.nova-pro-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2024-12-03","knowledge_cutoff":"2024-10","description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":821,"win_rate":21.4,"rank":119}}},{"id":"anthracite-org/magnum-v4-72b","name":"Magnum v4 72B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":16384,"max_completion_tokens":2048,"uptime_30m":null,"pricing":{"input":3,"output":5,"cache_read":null,"cache_write":null},"org":"anthracite-org","zdr":true},{"id":"anthropic/claude-3-haiku","name":"Anthropic: Claude 3 Haiku","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":4096,"uptime_30m":100,"pricing":{"input":0.25,"output":1.25,"cache_read":0.03,"cache_write":0.3},"org":"anthropic","zdr":true},{"id":"anthropic/claude-fable-5","name":"anthropic/claude-fable-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":10,"output":50,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-10","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"anthropic.claude-fable-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":98.98190045248869,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5","name":"Anthropic: Claude Fable 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.24418604651163,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-10","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"anthropic.claude-fable-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-06-09","knowledge_cutoff":"2026-01-31","description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":96.42058165548099,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-fable-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-06-07","knowledge_cutoff":null,"description":"Claude model for creative writing, analysis, and controlled agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-fable-5:batch","name":"Anthropic: Claude Fable 5 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":98.55349344978166,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","benchmarks":{"intelligence_index":59.9,"coding_index":76.5,"agentic_index":52.8,"design_arena_best":{"category":"gamedev","elo":1394,"win_rate":66.5,"rank":1}}},{"id":"anthropic/claude-haiku-4-5","name":"anthropic/claude-haiku-4-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":1,"output":5,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-11-18","knowledge_cutoff":"2025-02-31","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":98.81472239550843,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5","name":"Anthropic: Claude Haiku 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.97053865165229,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":100,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":98.81472239550843,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-haiku-4.5:batch","name":"Anthropic: Claude Haiku 4.5 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.97053865165229,"pricing":{"input":1,"output":5,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"anthropic","benchmarks":{"intelligence_index":29.6,"coding_index":43.9,"agentic_index":16.4,"design_arena_best":{"category":"asciiart","elo":1178,"win_rate":49.3,"rank":36}}},{"id":"anthropic/claude-opus-4","name":"Anthropic: Claude Opus 4","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1227,"win_rate":59.9,"rank":41}}},{"id":"anthropic/claude-opus-4-7","name":"anthropic/claude-opus-4-7","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"}},{"id":"anthropic/claude-opus-4-8","name":"anthropic/claude-opus-4-8","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1","name":"Anthropic: Claude Opus 4.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.1:batch","name":"Anthropic: Claude Opus 4.1 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":15,"output":75,"cache_read":1.5,"cache_write":18.75},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1228,"win_rate":58.5,"rank":40}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.29078014184397,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.9798305768455,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.30555555555556,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5","name":"Anthropic: Claude Opus 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.29078014184397,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.9798305768455,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":99.30555555555556,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.5:batch","name":"Anthropic: Claude Opus 4.5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1286,"win_rate":59.4,"rank":23}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.92565055762081,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.93708996135527,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6","name":"Anthropic: Claude Opus 4.6","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-05","knowledge_cutoff":"2025-05-31","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.92565055762081,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.93708996135527,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.6:batch","name":"Anthropic: Claude Opus 4.6 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1334,"win_rate":62.9,"rank":6}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.82110912343471,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.95014955134596,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7","name":"Anthropic: Claude Opus 4.7","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-16","knowledge_cutoff":"2026-01-31","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7-fast","name":"Anthropic: Claude Opus 4.7 (Fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":30,"output":150,"cache_read":3,"cache_write":37.5},"org":"anthropic","benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.82110912343471,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.95014955134596,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.7:batch","name":"Anthropic: Claude Opus 4.7 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":53.5,"coding_index":73.6,"agentic_index":44.4,"design_arena_best":{"category":"fullstack","elo":1503,"win_rate":80.1,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.49748743718592,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.94797086368366,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8","name":"Anthropic: Claude Opus 4.8","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.75083056478405,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-28","knowledge_cutoff":"2026-01","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8-fast","name":"Anthropic: Claude Opus 4.8 (Fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.49748743718592,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.94797086368366,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-4.8:batch","name":"Anthropic: Claude Opus 4.8 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.75083056478405,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","benchmarks":{"intelligence_index":55.7,"coding_index":74.3,"agentic_index":47.2,"design_arena_best":{"category":"androidnative","elo":1341,"win_rate":68,"rank":1}}},{"id":"anthropic/claude-opus-5","name":"anthropic/claude-opus-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":5,"output":25,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-23","knowledge_cutoff":"2026-05","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":98.98837933181159,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev":{"base_url":null,"model_id":"jp.anthropic.claude-opus-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","provider":"claude-platform-on-aws","provider_display":"Claude Platform on AWS","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-23","knowledge_cutoff":"2026-05","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.69933854479855,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-opus-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-24","knowledge_cutoff":"2026-05","description":"Strongest Claude Opus model for coding, agents, and professional work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-23","knowledge_cutoff":"2026-05","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-opus-5-fast","name":"Claude Opus 5 (Fast)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-23","knowledge_cutoff":"2026-05","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":60.7,"coding_index":78,"agentic_index":55.3,"design_arena_best":{"category":"uicomponent","elo":1405,"win_rate":66.8,"rank":2}}},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":28.9,"coding_index":37.6,"agentic_index":16.6,"design_arena_best":{"category":"3d","elo":1196,"win_rate":57.8,"rank":47}}},{"id":"anthropic/claude-sonnet-4","name":"Anthropic: Claude Sonnet 4","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":28.9,"coding_index":37.6,"agentic_index":16.6,"design_arena_best":{"category":"3d","elo":1196,"win_rate":57.8,"rank":47}}},{"id":"anthropic/claude-sonnet-4-6","name":"anthropic/claude-sonnet-4-6","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.9999999999999996,"output":15,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":99.77779188622945,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":99.94047619047619,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5","name":"Anthropic: Claude Sonnet 4.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":99.77779188622945,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":99.94047619047619,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":64000,"uptime_30m":100,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.5:batch","name":"Anthropic: Claude Sonnet 4.5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","benchmarks":{"intelligence_index":36.4,"coding_index":52.1,"agentic_index":24.6,"design_arena_best":{"category":"asciiart","elo":1244,"win_rate":56.4,"rank":11}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.60070898502171,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":47.2,"coding_index":63,"agentic_index":40.8,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59,"rank":13}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":47.2,"coding_index":63,"agentic_index":40.8,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59,"rank":13}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.87012987012987,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-17","knowledge_cutoff":"2025-08-31","description":"Claude workhorse for coding agents, careful analysis, and production cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":47.2,"coding_index":63,"agentic_index":40.8,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59,"rank":13}}},{"id":"anthropic/claude-sonnet-4.6","name":"Anthropic: Claude Sonnet 4.6","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.81034664418922,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"org":"anthropic","zdr":true,"benchmarks":{"intelligence_index":47.2,"coding_index":63,"agentic_index":40.8,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59,"rank":13}}},{"id":"anthropic/claude-sonnet-5","name":"anthropic/claude-sonnet-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":10,"cache_read":null,"cache_write":null},"org":"anthropic","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.90497867544693,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","zdr":true,"modelsdev":{"base_url":null,"model_id":"us.anthropic.claude-sonnet-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.68180503326583,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","zdr":true,"modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"high","source":"models.dev","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5","name":"Anthropic: Claude Sonnet 5","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.venice.ai"},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.90497867544693,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"us.anthropic.claude-sonnet-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":99.68180503326583,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-06-30","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","provider":"anthropic","provider_display":"Anthropic","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","modelsdev":{"base_url":null,"model_id":"claude-sonnet-5","doc_url":"https://docs.anthropic.com/en/docs/about-claude/models","confidence":"medium","source":"models.dev","release_date":"2026-06-29","knowledge_cutoff":"2026-01-31","description":"Everyday Claude agent model for coding, planning, browsing, and general work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"anthropic/claude-sonnet-5:batch","name":"Anthropic: Claude Sonnet 5 (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2,"output":10,"cache_read":0.19999999999999998,"cache_write":2.5},"org":"anthropic","benchmarks":{"intelligence_index":53.4,"coding_index":71.5,"agentic_index":46.7,"design_arena_best":{"category":"gamedev","elo":1351,"win_rate":59.5,"rank":3}}},{"id":"arcee-ai/trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.22,"output":0.85,"cache_read":0.06,"cache_write":null},"org":"arcee-ai","zdr":true,"benchmarks":{"intelligence_index":18.2,"coding_index":25.8,"agentic_index":3.7,"design_arena_best":{"category":"website","elo":1162,"win_rate":41.3,"rank":68}}},{"id":"arcee-ai/trinity-large-thinking","name":"Arcee AI: Trinity Large Thinking","provider":"arcee","provider_display":"Arcee AI","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":80000,"uptime_30m":null,"pricing":{"input":0.25,"output":0.7999999999999999,"cache_read":0.06,"cache_write":null},"org":"arcee-ai","benchmarks":{"intelligence_index":18.2,"coding_index":25.8,"agentic_index":3.7,"design_arena_best":{"category":"website","elo":1162,"win_rate":41.3,"rank":68}}},{"id":"arcee-ai/virtuoso-large","name":"Arcee AI: Virtuoso Large","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":0.75,"output":1.2,"cache_read":null,"cache_write":null},"org":"arcee-ai","zdr":true},{"id":"baidu/ernie-4.5-vl-424b-a47b","name":"Baidu: ERNIE 4.5 VL 424B A47B ","provider":"novita","provider_display":"Novita","quantization":"fp16","discount":0,"context_length":123000,"max_completion_tokens":16000,"uptime_30m":null,"pricing":{"input":0.42,"output":1.25,"cache_read":null,"cache_write":null},"org":"baidu","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"baidu/ernie-4.5-vl-424b-a47b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-06-30","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true}},{"id":"bottlecapai/ThinkingCap-Qwen3.6-27B","name":"ThinkingCap Qwen3.6 27B","provider":"sference","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.4,"output":2.6,"cache_read":0.05,"cache_write":null},"org":"bottlecapai","benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"bytedance-seed/seed-1.6","name":"ByteDance Seed: Seed 1.6","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true},{"id":"bytedance-seed/seed-1.6-flash","name":"ByteDance Seed: Seed 1.6 Flash","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.075,"output":0.3,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true},{"id":"bytedance-seed/seed-2.0-lite","name":"ByteDance Seed: Seed-2.0-Lite","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true},{"id":"bytedance-seed/seed-2.0-mini","name":"ByteDance Seed: Seed-2.0-Mini","provider":"seed","provider_display":"Seed","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"bytedance","zdr":true},{"id":"ByteDance/Seed-1.8","name":"ByteDance/Seed-1.8","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.25,"output":2,"cache_read":0.05,"cache_write":null},"org":"bytedance"},{"id":"ByteDance/Seed-2.0-code","name":"ByteDance/Seed-2.0-code","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.5,"output":2.9999999999999996,"cache_read":0.1,"cache_write":null},"org":"bytedance"},{"id":"ByteDance/Seed-2.0-mini","name":"ByteDance/Seed-2.0-mini","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.1,"output":0.4,"cache_read":0.020000000000000004,"cache_write":null},"org":"bytedance"},{"id":"ByteDance/Seed-2.0-pro","name":"ByteDance/Seed-2.0-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.5,"output":2.9999999999999996,"cache_read":0.1,"cache_write":null},"org":"bytedance"},{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":2048,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.09999999999999999,"cache_write":null},"org":"bytedance","zdr":true},{"id":"cognitivecomputations/dolphin-mistral-24b-venice-edition","name":"Venice: Uncensored","provider":"venice","provider_display":"Venice","quantization":"fp16","discount":0,"context_length":128000,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":0.8999999999999999,"cache_read":null,"cache_write":null},"org":"cognitivecomputations","zdr":true},{"id":"cohere/command-a","name":"Cohere: Command A","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":null,"pricing":{"input":2.5,"output":10,"cache_read":null,"cache_write":null},"org":"cohere","benchmarks":{"intelligence_index":22.5,"coding_index":27.8,"agentic_index":9.2,"design_arena_best":null}},{"id":"cohere/command-r-08-2024","name":"Cohere: Command R (08-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":100,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r-08-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-08-30","knowledge_cutoff":"2024-06-01","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"cohere/command-r-plus-08-2024","name":"Cohere: Command R+ (08-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":null,"pricing":{"input":2.5,"output":10,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r-plus-08-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-08-30","knowledge_cutoff":"2024-06-01","description":"Cohere's RAG workhorse for long-context enterprise search and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"cohere/command-r7b-12-2024","name":"Cohere: Command R7B (12-2024)","provider":"cohere","provider_display":"Cohere","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4000,"uptime_30m":99.81718464351006,"pricing":{"input":0.0375,"output":0.15,"cache_read":null,"cache_write":null},"org":"cohere","modelsdev":{"base_url":null,"model_id":"command-r7b-12-2024","doc_url":"https://docs.cohere.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-12-02","knowledge_cutoff":"2024-06-01","description":"Cohere retrieval model for long-context chat and enterprise RAG workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"deepcogito/cogito-v2.1-671b","name":"Deep Cogito: Cogito v2.1 671B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":1.25,"output":1.25,"cache_read":null,"cache_write":null},"org":"deepcogito","zdr":true},{"id":"deepseek-ai/DeepSeek-R1-0528","name":"deepseek-ai/DeepSeek-R1-0528","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.5,"output":2.15,"cache_read":0.35,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-20","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1208,"win_rate":60.7,"rank":44}}},{"id":"deepseek-ai/DeepSeek-V3","name":"deepseek-ai/DeepSeek-V3","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.32,"output":0.8899999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-26","knowledge_cutoff":"2024-07","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.together.ai/docs/serverless-models"}},{"id":"deepseek-ai/DeepSeek-V3-0324","name":"deepseek-ai/DeepSeek-V3-0324","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.24000000000000002,"output":0.9,"cache_read":0.135,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-03-25","knowledge_cutoff":"2024-07","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"deepseek-ai/DeepSeek-V3.1","name":"deepseek-ai/DeepSeek-V3.1","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.25,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-21","knowledge_cutoff":null,"description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"deepseek-ai/DeepSeek-V3.1-Terminus","name":"deepseek-ai/DeepSeek-V3.1-Terminus","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.27,"output":0.95,"cache_read":0.12999999960000003,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41}}},{"id":"deepseek-ai/DeepSeek-V3.2","name":"deepseek-ai/DeepSeek-V3.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.26,"output":0.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"deepseek-ai/DeepSeek-V4-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.09,"output":0.18,"cache_read":0.018,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-ai/DeepSeek-V4-Flash","name":"DeepSeek V4 Flash","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-ai/DeepSeek-V4-Pro","name":"deepseek-ai/DeepSeek-V4-Pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2999999999999998,"output":2.5999999999999996,"cache_read":0.10000000399999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"DeepSeek-V3.1","name":"DeepSeek-V3.1","org":"deepseek","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":3,"output":4.5,"cache_read":null,"cache_write":null},"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-21","knowledge_cutoff":null,"description":"A large hybrid model that supports both thinking and non-thinking modes via prompt templates.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"crof","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.18,"output":0.35,"cache_read":0.04,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":163840,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"deepseek-v3.2","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2025-07-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"DeepSeek-V3.2","name":"DeepSeek-V3.2","org":"deepseek","provider":"sambanova","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":3,"output":4.5,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.12,"output":0.21,"cache_read":0.003,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"deepseek-v4-flash","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.2,"output":0.4,"cache_read":0.04,"cache_write":0},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-v4-flash","name":"DeepSeek-V4-Flash","provider":"makora","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.09,"output":0.195,"cache_read":0.0196,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-v4-flash","name":"DeepSeek V4 Flash","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"deepseek","subscription":true,"max_completion_tokens":384000,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"deepseek-v4-flash","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek model for efficient chat, coding help, and agent loops","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.35,"output":0.8,"cache_read":0.003,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"deepseek-v4-pro","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.4,"output":4.8,"cache_read":0.2,"cache_write":0},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek-v4-pro","name":"DeepSeek-V4-Pro","provider":"makora","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.39,"output":2.79,"cache_read":0.301,"cache_write":null},"org":"deepseek","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.74,"output":3.48,"cache_read":0.0145,"cache_write":null},"org":"deepseek","subscription":true,"max_completion_tokens":384000,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"deepseek-v4-pro","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek-v4-pro-lightning","name":"DeepSeek: DeepSeek V4 Pro (Lightning)","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.8,"output":1.6,"cache_read":0.02,"cache_write":null},"org":"deepseek","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"deepseek-v4-pro-lightning","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.3,"context_length":128000,"max_completion_tokens":16000,"uptime_30m":99.75641837579772,"pricing":{"input":0.20020000000000002,"output":0.8000999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2025-09","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://api-docs.deepseek.com/quick_start/pricing"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1145,"win_rate":48.5,"rank":76}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":16384,"uptime_30m":98.35237429082147,"pricing":{"input":0.32,"output":0.8899999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2025-09","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://api-docs.deepseek.com/quick_start/pricing"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1145,"win_rate":48.5,"rank":76}}},{"id":"deepseek/deepseek-chat","name":"DeepSeek: DeepSeek V3","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":64000,"max_completion_tokens":16000,"uptime_30m":99.57108616122115,"pricing":{"input":0.39999999999999997,"output":1.3,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-01","knowledge_cutoff":"2025-09","description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://api-docs.deepseek.com/quick_start/pricing"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1145,"win_rate":48.5,"rank":76}}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":16384,"uptime_30m":68.15096388813467,"pricing":{"input":0.24,"output":0.8999999999999999,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":15.4,"coding_index":21.2,"agentic_index":1.5,"design_arena_best":null}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":88.6413875191294,"pricing":{"input":0.25,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":15.4,"coding_index":21.2,"agentic_index":1.5,"design_arena_best":null}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":65536,"uptime_30m":96.72059466550066,"pricing":{"input":0.27,"output":1.12,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":15.4,"coding_index":21.2,"agentic_index":1.5,"design_arena_best":null}},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek: DeepSeek V3 0324","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":100,"pricing":{"input":0.5,"output":1.5,"cache_read":0.25,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":15.4,"coding_index":21.2,"agentic_index":1.5,"design_arena_best":null}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":163840,"max_completion_tokens":32768,"uptime_30m":99.97605077236258,"pricing":{"input":0.25,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.27,"output":1,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":39.95937711577522,"pricing":{"input":0.27,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":99.37389629153958,"pricing":{"input":0.3,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":161000,"max_completion_tokens":161000,"uptime_30m":85.31185851886941,"pricing":{"input":0.55,"output":1.6500000000000001,"cache_read":0.55,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":32768,"uptime_30m":99.69818913480886,"pricing":{"input":0.6,"output":1.7,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":31.874999999999996,"pricing":{"input":0.6,"output":1.7,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek: DeepSeek V3.1","provider":"sambanova","provider_display":"SambaNova","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":7168,"uptime_30m":99.92435703479576,"pricing":{"input":0.65,"output":1.5,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1147,"win_rate":48,"rank":74}}},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":64000,"max_completion_tokens":16000,"uptime_30m":100,"pricing":{"input":0.7,"output":2.5,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-20","knowledge_cutoff":"2024-07","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.together.ai/docs/serverless-models"},"benchmarks":{"intelligence_index":18.5,"coding_index":24.6,"agentic_index":3.1,"design_arena_best":null}},{"id":"deepseek/deepseek-r1","name":"DeepSeek: R1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":4096,"uptime_30m":96.41025641025641,"pricing":{"input":1.4849999999999999,"output":5.9399999999999995,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-r1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-01-20","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":18.5,"coding_index":24.6,"agentic_index":3.1,"design_arena_best":null}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":98.91304347826086,"pricing":{"input":0.5,"output":2.1799999999999997,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-20","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1208,"win_rate":60.7,"rank":44}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":0.5710000000000001,"output":2.2859999999999996,"cache_read":null,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-20","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1208,"win_rate":60.7,"rank":44}}},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek: R1 0528","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.7,"output":2.5,"cache_read":0.35,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-r1-0528","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-05-28","knowledge_cutoff":"2024-07","description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1208,"win_rate":60.7,"rank":44}}},{"id":"deepseek/deepseek-r1-distill-llama-70b","name":"DeepSeek: R1 Distill Llama 70B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":8192,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.7999999999999999,"output":0.7999999999999999,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-r1-distill-llama-70b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-01-27","knowledge_cutoff":null,"description":"DeepSeek reasoning model for multi-step analysis, math, coding, and tools","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":62.67942583732058,"pricing":{"input":0.27,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41}}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.27,"output":1,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v3.1-terminus","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41}}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.3,"output":0.95,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41}}},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek: DeepSeek V3.1 Terminus","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.4,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":0.3426,"output":1.0284,"cache_read":null,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-22","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":30.4,"coding_index":43.5,"agentic_index":18.1,"design_arena_best":{"category":"uicomponent","elo":1218,"win_rate":59.3,"rank":41}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.26,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":99.77392614920875,"pricing":{"input":0.2072,"output":0.3108,"cache_read":0.02072,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.25,"context_length":128000,"max_completion_tokens":64000,"uptime_30m":99.79905942710559,"pricing":{"input":0.2145,"output":0.32175,"cache_read":0.02145,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":94.38943894389439,"pricing":{"input":0.25899999999999995,"output":0.42,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":99.89280062618047,"pricing":{"input":0.26,"output":0.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":65536,"uptime_30m":99.98441104944816,"pricing":{"input":0.26899999999999996,"output":0.39999999999999997,"cache_read":0.13449999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v3.2","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-01","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":null,"uptime_30m":97.49430523917995,"pricing":{"input":0.29,"output":0.43,"cache_read":0.03,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":160000,"max_completion_tokens":32768,"uptime_30m":77.28459530026109,"pricing":{"input":0.33,"output":0.48,"cache_read":0.16,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v3.2","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2025-12-04","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":98.24475865431496,"pricing":{"input":0.3705,"output":1.1115000000000002,"cache_read":0.0741,"cache_write":0.46345},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":128000,"uptime_30m":96.60217083529967,"pricing":{"input":0.425,"output":1.3599999999999999,"cache_read":0.15,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":99.94243610407553,"pricing":{"input":0.5,"output":1.5,"cache_read":0.25,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"deepseek-ai/DeepSeek-V3.2","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-01","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":65536,"uptime_30m":99.54545454545455,"pricing":{"input":0.56,"output":1.68,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek: DeepSeek V3.2","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":64000,"uptime_30m":98.90453834115806,"pricing":{"input":1,"output":1,"cache_read":0.5,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-11","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":32,"coding_index":44.2,"agentic_index":18.3,"design_arena_best":{"category":"website","elo":1200,"win_rate":50.2,"rank":55}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":65536,"uptime_30m":99.02857142857144,"pricing":{"input":0.27,"output":0.41,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v3.2-exp","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-29","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1205,"win_rate":56.4,"rank":44}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":95.54140127388536,"pricing":{"input":0.27,"output":0.41,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-29","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1205,"win_rate":56.4,"rank":44}}},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek: DeepSeek V3.2 Exp","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":163840,"max_completion_tokens":163840,"uptime_30m":99.43630214205186,"pricing":{"input":0.27,"output":0.41,"cache_read":0.27,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-29","knowledge_cutoff":null,"description":"DeepSeek chat model for instruction following, coding, and analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1205,"win_rate":56.4,"rank":44}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.35,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.78233830845771,"pricing":{"input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.35,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":98.69043385490754,"pricing":{"input":0.091,"output":0.182,"cache_read":0.0182,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.33,"context_length":1048575,"max_completion_tokens":384000,"uptime_30m":99.62462811454073,"pricing":{"input":0.09380000000000001,"output":0.18760000000000002,"cache_read":0.01876,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Flash","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0.3,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":98.32857142857144,"pricing":{"input":0.098,"output":0.196,"cache_read":0.014,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":99.66043770674963,"pricing":{"input":0.112,"output":0.224,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":91.05159490069487,"pricing":{"input":0.13,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":99.81421357242711,"pricing":{"input":0.134,"output":0.268,"cache_read":0.026799999999999997,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":99.45262801952786,"pricing":{"input":0.13799999999999998,"output":0.275,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-flash","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":98.89910924325325,"pricing":{"input":0.13899999999999998,"output":0.27799999999999997,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":97.97160243407707,"pricing":{"input":0.13899999999999998,"output":0.27799999999999997,"cache_read":0.06949999999999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"ionstream","provider_display":"Ionstream","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":55.16665274413165,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":95.32485971198702,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":98.59678085018572,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/deepseek-v4-flash","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":99.06341532272293,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"ambient","provider_display":"Ambient","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":59.78595259759955,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":384000,"max_completion_tokens":384000,"uptime_30m":99.9882988930753,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":99.40162524961171,"pricing":{"input":0.14,"output":0.28,"cache_read":0.028,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"deepseek","provider_display":"DeepSeek","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":99.95756291741228,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.deepseek.com","model_id":"deepseek-v4-flash","doc_url":"https://api-docs.deepseek.com/quick_start/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":99.68475452196382,"pricing":{"input":0.14,"output":0.28,"cache_read":0.07,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek: DeepSeek V4 Flash","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":94.69900306748467,"pricing":{"input":0.19999999999999998,"output":1,"cache_read":null,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":40.3,"coding_index":56.2,"agentic_index":31.1,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":50.3,"rank":32}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"deepseek","provider_display":"DeepSeek","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":99.9462510077936,"pricing":{"input":0.435,"output":0.87,"cache_read":0.003625,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.deepseek.com","model_id":"deepseek-v4-pro","doc_url":"https://api-docs.deepseek.com/quick_start/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.63,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":99.23371647509579,"pricing":{"input":0.6253,"output":1.2506,"cache_read":0.0518,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.615,"context_length":1024000,"max_completion_tokens":384000,"uptime_30m":93.10712282669658,"pricing":{"input":0.6699,"output":1.3398,"cache_read":0.055825,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.61,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":97.18237704918032,"pricing":{"input":0.6786,"output":1.3572,"cache_read":0.05655,"cache_write":null},"org":"deepseek","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"ionstream","provider_display":"Ionstream","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":77.0279255319149,"pricing":{"input":1.131,"output":2.262,"cache_read":0.094,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.27,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":99.5290665176076,"pricing":{"input":1.1680000000000001,"output":2.3360000000000003,"cache_read":0.09855000000000001,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"deepseek/deepseek-v4-pro","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":393216,"uptime_30m":97.0513900589722,"pricing":{"input":1.392,"output":2.784,"cache_read":0.348,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"deepseek-v4-pro","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":393216,"uptime_30m":98.98381249042536,"pricing":{"input":1.4160000000000001,"output":2.8320000000000003,"cache_read":0.118,"cache_write":null},"org":"deepseek","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":85.8264081255771,"pricing":{"input":1.5016200000000002,"output":3.1350000000000002,"cache_read":0.135,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":94.72599917593737,"pricing":{"input":1.6500000000000001,"output":3.3009999999999997,"cache_read":0.33,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-v4-pro","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":393216,"uptime_30m":97.97603195739015,"pricing":{"input":1.68,"output":3.38,"cache_read":0.13,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":1.74,"output":3.48,"cache_read":0.145,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":89.02728351126927,"pricing":{"input":1.74,"output":3.48,"cache_read":0.09999999999999999,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":393216,"max_completion_tokens":393216,"uptime_30m":100,"pricing":{"input":1.74,"output":3.48,"cache_read":0.145,"cache_write":null},"org":"deepseek","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":512000,"max_completion_tokens":384000,"uptime_30m":94.51395572666024,"pricing":{"input":1.74,"output":3.48,"cache_read":0.19999999999999998,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":null,"model_id":"deepseek-ai/DeepSeek-V4-Pro","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":null,"description":"Flagship DeepSeek model for coding, reasoning, and agentic work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":95.96309111880046,"pricing":{"input":1.74,"output":3.48,"cache_read":0.14,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek: DeepSeek V4 Pro","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":384000,"uptime_30m":91.83531053733427,"pricing":{"input":1.74,"output":3.48,"cache_read":0.145,"cache_write":null},"org":"deepseek","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/deepseek-v4-pro","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-05","description":"Open MoE flagship with million-token context for coding and long agent runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.3,"coding_index":59.4,"agentic_index":36.4,"design_arena_best":{"category":"3d","elo":1318,"win_rate":59.6,"rank":10}}},{"id":"gemma-4-26b-a4b","name":"Gemma-4-26B-A4B","provider":"makora","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.34,"cache_read":0.034,"cache_write":null},"org":"makora","zdr":true,"subscription":true},{"id":"gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B","provider":"hyper","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.13,"output":0.424,"cache_read":0,"cache_write":0.065},"org":"google","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.3,"cache_read":0.02,"cache_write":null},"org":"google","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"gemma-4-31b-it","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"gemma-4-31B-it","name":"gemma-4-31B-it","org":"google","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.38,"output":1.15,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"glm-4.5","name":"GLM-4.5","provider":"ember","quantization":null,"discount":0,"context_length":131000,"pricing":{"input":0.5700000000000001,"output":2.09,"cache_read":0.10450000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-28","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1227,"win_rate":59.7,"rank":38}}},{"id":"glm-4.5-air","name":"GLM-4.5 Air","provider":"ember","quantization":null,"discount":0,"context_length":131000,"pricing":{"input":0.12349999999999998,"output":0.8075,"cache_read":0.02375,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-13","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":59.4,"rank":42}}},{"id":"glm-4.5v","name":"GLM-4.5V","provider":"ember","quantization":null,"discount":0,"context_length":65536,"pricing":{"input":0.54,"output":1.5999999999999999,"cache_read":0.09,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-11","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"glm-4.6","name":"GLM-4.6","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.38,"output":1.55,"cache_read":0.07,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-11-15","knowledge_cutoff":"2024-10","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"glm-4.7","name":"Z.AI: GLM 4.7","provider":"crof","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.25,"output":1.1,"cache_read":0.05,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":202752,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"glm-4.7","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"glm-4.7","name":"GLM-4.7","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.38,"output":1.6624999999999999,"cache_read":0.07600000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"glm-4.7-flash","name":"Z.AI: GLM 4.7 Flash","provider":"crof","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.04,"output":0.3,"cache_read":0.008,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"glm-4.7-flash","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"glm-4.7-flash","name":"GLM-4.7 Flash","provider":"ember","quantization":null,"discount":0,"context_length":200000,"pricing":{"input":0.057,"output":0.38,"cache_read":0.009500000000000001,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"glm-5","name":"Z.ai: GLM 5","provider":"crof","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.48,"output":1.9,"cache_read":0.1,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":202752,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"glm-5","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"glm-5","name":"GLM-5","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":0.5700000000000001,"output":1.824,"cache_read":0.114,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"glm-5","name":"GLM-5","provider":"hyper","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.81,"output":2.624,"cache_read":0,"cache_write":0.405},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"glm-5.1","name":"Z.ai: GLM 5.1","provider":"crof","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.45,"output":2.15,"cache_read":0.08,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":202752,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"glm-5.1","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"glm-5.1","name":"GLM-5.1","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":0.9309999999999999,"output":2.926,"cache_read":0.1729,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"GLM-5.1","name":"GLM-5.1","provider":"wafer","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":1,"output":3.2,"cache_read":0.1,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"GLM-5.1","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":"2025-04","description":"General Language Model 5.1 — high-quality bilingual (EN/ZH) generation with strong coding and reasoning capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"glm-5.1","name":"GLM-5.1","provider":"hyper","quantization":null,"discount":0,"context_length":202800,"pricing":{"input":1.52432,"output":4.79072,"cache_read":0.283088,"cache_write":0},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"glm-5.1","name":"GLM-5.1","provider":"opencode","quantization":null,"discount":0,"context_length":202000,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","subscription":true,"max_completion_tokens":32768,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"glm-5.1","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"glm-5.2","name":"Z.ai: GLM 5.2","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":1.05,"cache_read":0.05,"cache_write":null},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"glm-5.2","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm-5.2","name":"GLM-5.2","provider":"ember","quantization":null,"discount":0,"context_length":203000,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"GLM-5.2","name":"GLM-5.2","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.26,"output":3.96,"cache_read":0.23,"cache_write":0},"org":"z-ai","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"GLM-5.2","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm-5.2","name":"GLM-5.2","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.4,"output":4.4,"cache_read":0.28,"cache_write":0},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm-5.2","name":"GLM-5.2","provider":"opencode","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"glm-5.2","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm-5.2-fp8","name":"GLM-5.2-FP8","provider":"makora","quantization":null,"discount":0,"context_length":980000,"pricing":{"input":0.94,"output":2.8,"cache_read":0.18,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm-5.2-nvfp4","name":"GLM-5.2-NVFP4","provider":"makora","quantization":null,"discount":0,"context_length":980000,"pricing":{"input":0.72,"output":2.38,"cache_read":0.12,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"glm5.2-fast","name":"GLM5.2-Fast","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2.1,"output":6.6,"cache_read":0.21,"cache_write":0},"org":"wafer","max_completion_tokens":131072,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"glm5.2-fast","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"The same model served for high TPS.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"google/gemini-1.5-flash","name":"google/gemini-1.5-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.075,"output":0.3,"cache_read":null,"cache_write":null},"org":"google"},{"id":"google/gemini-1.5-flash-8b","name":"google/gemini-1.5-flash-8b","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.0375,"output":0.15,"cache_read":null,"cache_write":null},"org":"google"},{"id":"google/gemini-2.5-flash","name":"google/gemini-2.5-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":2.5,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1156,"win_rate":48.4,"rank":66}}},{"id":"google/gemini-2.5-flash","name":"Google: Gemini 2.5 Flash","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":98.57586465360318,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1156,"win_rate":48.4,"rank":66}}},{"id":"google/gemini-2.5-flash-lite","name":"Google: Gemini 2.5 Flash Lite","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":95.17072192307099,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.01,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false}},{"id":"google/gemini-2.5-flash-lite:batch","name":"Google: Gemini 2.5 Flash Lite (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":95.17072192307099,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.01,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false}},{"id":"google/gemini-2.5-flash:batch","name":"Google: Gemini 2.5 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":98.57586465360318,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1156,"win_rate":48.4,"rank":66}}},{"id":"google/gemini-2.5-pro","name":"google/gemini-2.5-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.25,"output":10,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.8,"coding_index":33.3,"agentic_index":7.1,"design_arena_best":{"category":"dataviz","elo":1275,"win_rate":71.8,"rank":19}}},{"id":"google/gemini-2.5-pro","name":"Google: Gemini 2.5 Pro","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.00080680196115,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.8,"coding_index":33.3,"agentic_index":7.1,"design_arena_best":{"category":"dataviz","elo":1275,"win_rate":71.8,"rank":19}}},{"id":"google/gemini-2.5-pro:batch","name":"Google: Gemini 2.5 Pro (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.01328037731164,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":0.375},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-2.5-pro","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":"2025-01","description":"Google's proven reasoning model for coding, math, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.8,"coding_index":33.3,"agentic_index":7.1,"design_arena_best":{"category":"dataviz","elo":1275,"win_rate":71.8,"rank":19}}},{"id":"google/gemini-3-flash-preview","name":"Google: Gemini 3 Flash Preview","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":98.16147018297177,"pricing":{"input":0.5,"output":3,"cache_read":0.049999999999999996,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1241,"win_rate":62.7,"rank":36}}},{"id":"google/gemini-3-flash-preview:batch","name":"Google: Gemini 3 Flash Preview (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":97.49277850722149,"pricing":{"input":0.5,"output":3,"cache_read":0.049999999999999996,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3-flash-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-17","knowledge_cutoff":"2025-01","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1241,"win_rate":62.7,"rank":36}}},{"id":"google/gemini-3.1-flash-lite","name":"google/gemini-3.1-flash-lite","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.25,"output":1.4999999999999998,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-03","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25,"coding_index":34.7,"agentic_index":6.2,"design_arena_best":{"category":"asciiart","elo":1204,"win_rate":50.6,"rank":19}}},{"id":"google/gemini-3.1-flash-lite","name":"Google: Gemini 3.1 Flash Lite","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":98.47491141173477,"pricing":{"input":0.25,"output":1.5,"cache_read":0.024999999999999998,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25,"coding_index":34.7,"agentic_index":6.2,"design_arena_best":{"category":"asciiart","elo":1204,"win_rate":50.6,"rank":19}}},{"id":"google/gemini-3.1-flash-lite:batch","name":"Google: Gemini 3.1 Flash Lite (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":98.47491141173477,"pricing":{"input":0.25,"output":1.5,"cache_read":0.024999999999999998,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-flash-lite-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false}},{"id":"google/gemini-3.1-pro","name":"google/gemini-3.1-pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":11.999999999999998,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":46.5,"coding_index":68.8,"agentic_index":21.4,"design_arena_best":{"category":"svg","elo":1337,"win_rate":69.7,"rank":2}}},{"id":"google/gemini-3.1-pro-preview","name":"Google: Gemini 3.1 Pro Preview","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":90.2793830457136,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":0.375},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":46.5,"coding_index":68.8,"agentic_index":21.4,"design_arena_best":{"category":"svg","elo":1337,"win_rate":69.7,"rank":2}}},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Google: Gemini 3.1 Pro Preview Custom Tools","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":0.375},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview-customtools","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false}},{"id":"google/gemini-3.1-pro-preview:batch","name":"Google: Gemini 3.1 Pro Preview (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":90.2793830457136,"pricing":{"input":2,"output":12,"cache_read":0.19999999999999998,"cache_write":0.375},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.1-pro-preview","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-02-19","knowledge_cutoff":"2025-01","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":46.5,"coding_index":68.8,"agentic_index":21.4,"design_arena_best":{"category":"svg","elo":1337,"win_rate":69.7,"rank":2}}},{"id":"google/gemini-3.5-flash","name":"google/gemini-3.5-flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.4999999999999998,"output":9,"cache_read":null,"cache_write":null},"org":"google","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":50.2,"coding_index":70.1,"agentic_index":37.4,"design_arena_best":{"category":"gamedev","elo":1318,"win_rate":57.6,"rank":12}}},{"id":"google/gemini-3.5-flash","name":"Google: Gemini 3.5 Flash","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.61708149504703,"pricing":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":50.2,"coding_index":70.1,"agentic_index":37.4,"design_arena_best":{"category":"gamedev","elo":1318,"win_rate":57.6,"rank":12}}},{"id":"google/gemini-3.5-flash-lite","name":"Google: Gemini 3.5 Flash Lite","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.94942638877798,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":36.5,"coding_index":49.3,"agentic_index":26.8,"design_arena_best":null}},{"id":"google/gemini-3.5-flash-lite:batch","name":"Google: Gemini 3.5 Flash Lite (batch)","provider":"google","provider_display":"Google AI Studio","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.94942638877798,"pricing":{"input":0.3,"output":2.5,"cache_read":0.03,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash-lite","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":36.5,"coding_index":49.3,"agentic_index":26.8,"design_arena_best":null}},{"id":"google/gemini-3.5-flash:batch","name":"Google: Gemini 3.5 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":99.61708149504703,"pricing":{"input":1.5,"output":9,"cache_read":0.15,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.5-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-05-19","knowledge_cutoff":"2025-01","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":50.2,"coding_index":70.1,"agentic_index":37.4,"design_arena_best":{"category":"gamedev","elo":1318,"win_rate":57.6,"rank":12}}},{"id":"google/gemini-3.6-flash","name":"Google: Gemini 3.6 Flash","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":98.92123069066768,"pricing":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.08333333333333334},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":50.1,"coding_index":69.2,"agentic_index":38.7,"design_arena_best":{"category":"dataviz","elo":1354,"win_rate":63.6,"rank":4}}},{"id":"google/gemini-3.6-flash:batch","name":"Google: Gemini 3.6 Flash (batch)","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":65536,"uptime_30m":98.92123069066768,"pricing":{"input":1.5,"output":7.5,"cache_read":0.15,"cache_write":0.08333333333333334},"org":"google","modelsdev":{"base_url":null,"model_id":"gemini-3.6-flash","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":"2026-03","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":50.1,"coding_index":69.2,"agentic_index":38.7,"design_arena_best":{"category":"dataviz","elo":1354,"win_rate":63.6,"rank":4}}},{"id":"google/gemma-2-27b-it","name":"Google: Gemma 2 27B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":8192,"max_completion_tokens":2048,"uptime_30m":null,"pricing":{"input":0.65,"output":0.65,"cache_read":null,"cache_write":null},"org":"google","zdr":true},{"id":"google/gemma-3-12b-it","name":"google/gemma-3-12b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.05,"output":0.15,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2024-12","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":5.5,"coding_index":5.8,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-27b-it","name":"google/gemma-3-27b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.08,"output":0.16,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-10","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.47425519485938,"pricing":{"input":0.08,"output":0.44999999999999996,"cache_read":0.04,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-10","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":110000,"max_completion_tokens":8192,"uptime_30m":42.32766593156435,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":0.125},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"google/gemma-3-27b-it","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-20","knowledge_cutoff":"2025-10","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":98304,"max_completion_tokens":16384,"uptime_30m":68.75725900116144,"pricing":{"input":0.119,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-3-27b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-03-25","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-27b-it","name":"Google: Gemma 3 27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":97.08491761723701,"pricing":{"input":0.15,"output":0.45999999999999996,"cache_read":0.075,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-20","knowledge_cutoff":"2025-10","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":7.4,"coding_index":10.1,"agentic_index":0.3,"design_arena_best":null}},{"id":"google/gemma-3-4b-it","name":"google/gemma-3-4b-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.05,"output":0.1,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":2.7,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemma-3n-e4b-it","name":"Google: Gemma 3n 4B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.06,"output":0.12,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google/gemma-3n-E4B-it","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2025-05-20","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":3.2,"agentic_index":null,"design_arena_best":null}},{"id":"google/gemma-4-26B-A4B-it","name":"google/gemma-4-26B-A4B-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.07,"output":0.33999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":99.70134248033592,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":null,"model_id":"@cf/google/gemma-4-26b-a4b-it","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":31.453381282343656,"pricing":{"input":0.12,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":99.77560179518564,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-4-26b-a4b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"ionstream","provider_display":"Ionstream","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":89.12866147571376,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":97.65829515706807,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"venice","provider_display":"Venice","quantization":"bf16","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":97.66385463984426,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google-gemma-4-26b-a4b-it","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"nextbit","provider_display":"NextBit","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.85771543086173,"pricing":{"input":0.15,"output":0.44999999999999996,"cache_read":0.049999999999999996,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://ai.google.dev/gemini-api/docs/models"},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-26b-a4b-it","name":"Google: Gemma 4 26B A4B ","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":96.9762503932054,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"gemma-4-26b-a4b-it","doc_url":"https://ai.google.dev/gemini-api/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.7,"coding_index":39.3,"agentic_index":11,"design_arena_best":null}},{"id":"google/gemma-4-31B-it","name":"google/gemma-4-31B-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.13,"output":0.38,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Gemma 4","provider":"lilac","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.11,"output":0.35,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"subscription":true,"max_completion_tokens":262100,"modelsdev":{"base_url":"https://api.getlilac.com/v1","model_id":"google/gemma-4-31b-it","doc_url":"https://docs.getlilac.com/inference/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-01","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":97.28793998845931,"pricing":{"input":0.09999999999999999,"output":0.33999999999999997,"cache_read":0.09999999999999999,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"openinference","provider_display":"OpenInference","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":8192,"uptime_30m":99.03316917728853,"pricing":{"input":0.09999999999999999,"output":0.35,"cache_read":0.09999999999999999,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"venice","provider_display":"Venice","quantization":"bf16","discount":0,"context_length":256000,"max_completion_tokens":8192,"uptime_30m":99.50907337599719,"pricing":{"input":0.12,"output":0.36,"cache_read":0.09,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google-gemma-4-31b-it","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-04-03","knowledge_cutoff":null,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"chutes","provider_display":"Chutes","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":82.95283869029738,"pricing":{"input":0.12,"output":0.37,"cache_read":0.06,"cache_write":null},"org":"google","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.55084965065124,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":95.55884529977794,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"google/gemma-4-31b-it","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.97384367234841,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"google","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"google/gemma-4-31B-it","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"morph","provider_display":"Morph","quantization":"fp4","discount":0,"context_length":175000,"max_completion_tokens":175000,"uptime_30m":99.84101748807632,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.08,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"crusoe","provider_display":"Crusoe","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262141,"uptime_30m":99.75907484741407,"pricing":{"input":0.14,"output":0.39999999999999997,"cache_read":0.14,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.27000075545818,"pricing":{"input":0.15,"output":0.39999999999999997,"cache_read":0.06,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.46625766871165,"pricing":{"input":0.15,"output":0.45999999999999996,"cache_read":0.075,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.9793559042114,"pricing":{"input":0.22,"output":0.55,"cache_read":0.12,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":85.98035895699289,"pricing":{"input":0.28,"output":0.86,"cache_read":null,"cache_write":null},"org":"google","zdr":true,"modelsdev":{"base_url":null,"model_id":"google/gemma-4-31B-it","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":"2025-01","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31b-it","name":"Google: Gemma 4 31B","provider":"cerebras","provider_display":"Cerebras","quantization":"fp16","discount":0,"context_length":131072,"max_completion_tokens":40960,"uptime_30m":100,"pricing":{"input":0.9900000000000001,"output":1.49,"cache_read":0.9900000000000001,"cache_write":null},"org":"google","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":null,"description":"Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 140+ languages.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31B-it-turbo","name":"google/gemma-4-31B-it-turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":0.33999999999999997,"cache_read":null,"cache_write":null},"org":"google","benchmarks":{"intelligence_index":29.4,"coding_index":43.4,"agentic_index":14.4,"design_arena_best":null}},{"id":"google/gemma-4-31B-it-Ultra","name":"google/gemma-4-31B-it-Ultra","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.27,"output":0.76,"cache_read":null,"cache_write":null},"org":"google"},{"id":"google/gemma-4-E4B-it","name":"google/gemma-4-E4B-it","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.02,"output":0.1,"cache_read":null,"cache_write":null},"org":"google"},{"id":"gpt-oss-120b","name":"gpt-oss-120b","org":"openai","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.22,"output":0.59,"cache_read":null,"cache_write":null},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"gpt-oss-120b","name":"gpt-oss-120b","provider":"hyper","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.176,"output":0.652,"cache_read":0,"cache_write":0.088},"org":"openai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"greg-1-mini","name":"Crof: Greg 1 Mini","provider":"crof","quantization":null,"discount":0,"context_length":229376,"pricing":{"input":0.07,"output":0.15,"cache_read":0.01,"cache_write":null},"org":"crof","zdr":true,"max_completion_tokens":229376,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"greg-1-mini","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"greg-2-super","name":"Crof: Greg 2 Super","provider":"crof","quantization":null,"discount":0,"context_length":229376,"pricing":{"input":1.5,"output":5,"cache_read":0.25,"cache_write":null},"org":"crof","zdr":true,"max_completion_tokens":229376,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"greg-2-super","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-06-14","knowledge_cutoff":null,"description":"General-purpose chat model for instruction following, writing, and analysis","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"greg-2-ultra","name":"Crof: Greg 2 Ultra","provider":"crof","quantization":null,"discount":0,"context_length":229376,"pricing":{"input":3,"output":10,"cache_read":0.5,"cache_write":null},"org":"crof","zdr":true,"max_completion_tokens":229376,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"greg-2-ultra","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-06-14","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"greg-rp","name":"Crof: Greg (Roleplay)","provider":"crof","quantization":null,"discount":0,"context_length":229376,"pricing":{"input":0.1,"output":0.3,"cache_read":0.02,"cache_write":null},"org":"crof","zdr":true,"max_completion_tokens":229376,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"greg-rp","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":null,"description":"General-purpose chat model for instruction following, writing, and analysis","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"Gryphe/MythoMax-L2-13b","name":"Gryphe/MythoMax-L2-13b","provider":"deepinfra","quantization":null,"discount":0,"context_length":4096,"pricing":{"input":0.4,"output":0.4,"cache_read":null,"cache_write":null},"org":"gryphe","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-04-25","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":4096,"max_completion_tokens":4096,"uptime_30m":99.88399071925754,"pricing":{"input":0.06,"output":0.06,"cache_read":null,"cache_write":null},"org":"gryphe","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-04-25","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"gryphe/mythomax-l2-13b","name":"MythoMax 13B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":2048,"uptime_30m":99.53488372093024,"pricing":{"input":0.44999999999999996,"output":0.65,"cache_read":null,"cache_write":null},"org":"gryphe","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-04-25","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"hf:moonshotai/Kimi-K3","name":"moonshotai/Kimi-K3","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"moonshot","pricing":{"input":3,"output":15,"cache_read":0.6000000000000001,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:moonshotai/Kimi-K3","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","provider":"synthetic","quantization":null,"discount":0,"context_length":262144,"org":"nvidia","pricing":{"input":0.3,"output":1,"cache_read":0.06,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-03-11","knowledge_cutoff":null,"description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7,"design_arena_best":null}},{"id":"hf:openai/gpt-oss-120b","name":"openai/gpt-oss-120b","provider":"synthetic","quantization":null,"discount":0,"context_length":131072,"org":"openai","pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":32768,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:openai/gpt-oss-120b","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"hf:Qwen/Qwen3.6-27B","name":"Qwen/Qwen3.6-27B","provider":"synthetic","quantization":null,"discount":0,"context_length":262144,"org":"qwen","pricing":{"input":0.44999999999999996,"output":3.5999999999999996,"cache_read":0.09,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:Qwen/Qwen3.6-27B","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"hf:zai-org/GLM-4.7-Flash","name":"zai-org/GLM-4.7-Flash","provider":"synthetic","quantization":null,"discount":0,"context_length":196608,"org":"z-ai","pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:zai-org/GLM-4.7-Flash","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"hf:zai-org/GLM-5.2","name":"zai-org/GLM-5.2","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"z-ai","pricing":{"input":1,"output":3,"cache_read":0.2,"cache_write":null},"zdr":true,"subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://api.synthetic.new/openai/v1","model_id":"hf:zai-org/GLM-5.2","doc_url":"https://synthetic.new/pricing","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"ibm-granite/granite-4.0-h-micro","name":"IBM: Granite 4.0 Micro","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":131000,"max_completion_tokens":131000,"uptime_30m":100,"pricing":{"input":0.017,"output":0.112,"cache_read":null,"cache_write":null},"org":"ibm","modelsdev":{"base_url":null,"model_id":"@cf/ibm-granite/granite-4.0-h-micro","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2025-10-07","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"ibm-granite/granite-4.1-8b","name":"IBM: Granite 4.1 8B","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.09999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"ibm","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-29","knowledge_cutoff":null,"description":"Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat capabilities.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":9.5,"agentic_index":null,"design_arena_best":null}},{"id":"inception/mercury-2","name":"Inception: Mercury 2","provider":"inception","provider_display":"Inception","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":50000,"uptime_30m":100,"pricing":{"input":0.25,"output":0.75,"cache_read":0.024999999999999998,"cache_write":null},"org":"inception","zdr":true,"modelsdev":{"base_url":"https://api.inceptionlabs.ai/v1/","model_id":"mercury-2","doc_url":"https://platform.inceptionlabs.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-02-24","knowledge_cutoff":"2025-01-01","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":21.4,"coding_index":31.1,"agentic_index":9.6,"design_arena_best":{"category":"asciiart","elo":1045,"win_rate":28.2,"rank":54}}},{"id":"inclusionai/ling-2.6-1t","name":"inclusionAI: Ling-2.6-1T","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.75,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.075,"output":0.625,"cache_read":0.015,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"inclusionai/ling-2.6-1t","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"inclusionai/ling-2.6-flash","name":"inclusionAI: Ling-2.6-flash","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.9,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":98.97495034915754,"pricing":{"input":0.01,"output":0.03,"cache_read":0.002,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"inclusionai/ling-2.6-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.1,"coding_index":25.3,"agentic_index":2.3,"design_arena_best":null}},{"id":"inclusionai/ring-2.6-1t","name":"inclusionAI: Ring-2.6-1T","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.75,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.075,"output":0.625,"cache_read":0.015,"cache_write":null},"org":"inclusionai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"inclusionai/ring-2.6-1t","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-05-08","knowledge_cutoff":null,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":30.6,"coding_index":42.8,"agentic_index":18.9,"design_arena_best":null}},{"id":"kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.35,"output":1.7,"cache_read":0.07,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"kimi-k2.5","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-01","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"kimi-k2.5","name":"Kimi K2.5","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.35624999999999996,"output":1.9800000000000002,"cache_read":0.22499999999999998,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"kimi-k2.5","name":"Kimi K2.5","provider":"hyper","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.528,"output":2.79,"cache_read":0,"cache_write":0.264},"org":"moonshot","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"kimi-k2.5-lightning","name":"MoonshotAI: Kimi K2.5 (Lightning)","provider":"crof","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":1,"output":3,"cache_read":0.2,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":32768,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"kimi-k2.5-lightning","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.5,"output":1.99,"cache_read":0.05,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"kimi-k2.6","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"Kimi-K2.6","name":"Kimi-K2.6","provider":"wafer","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":1.14,"output":4.8,"cache_read":0.19,"cache_write":0},"org":"moonshot","max_completion_tokens":65536,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"Kimi-K2.6","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Kimi K2.6 sparse MoE model with a 262K context window. Available serverless and not included in standard Wafer Pass. Non-ZDR only: requests with `Wafer-ZDR: required` are rejected.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"kimi-k2.6","name":"Kimi K2.6","provider":"hyper","quantization":null,"discount":0,"context_length":262000,"pricing":{"input":0.95,"output":4,"cache_read":0,"cache_write":0.16},"org":"moonshot","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"kimi-k2.6","name":"Kimi K2.6","provider":"opencode","quantization":null,"discount":0,"context_length":262000,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"kimi-k2.6","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2024-10","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.55,"output":2.25,"cache_read":0.05,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"kimi-k2.7-code","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","provider":"hyper","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":0},"org":"moonshot","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"kimi-k2.7-code","name":"Kimi K2.7 Code","provider":"opencode","quantization":null,"discount":0,"context_length":262000,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"kimi-k2.7-code","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"kimi-k3","name":"MoonshotAI: Kimi K3","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":8,"cache_read":0.25,"cache_write":null},"org":"moonshot","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"kimi-k3","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"kimi-k3","name":"Kimi K3","provider":"hyper","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":3.2664,"output":16.332,"cache_read":0.32664,"cache_write":0},"org":"moonshot","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"kimi-k3","name":"Kimi-K3","provider":"makora","quantization":null,"discount":0,"context_length":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"kwaipilot/kat-coder-air-v2.5","name":"Kwaipilot: KAT-Coder-Air V2.5","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":80000,"uptime_30m":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.03,"cache_write":null},"org":"kwaipilot"},{"id":"kwaipilot/kat-coder-pro-v2","name":"Kwaipilot: KAT-Coder-Pro V2","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":80000,"uptime_30m":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"kwaipilot","benchmarks":{"intelligence_index":33.7,"coding_index":59.5,"agentic_index":15.5,"design_arena_best":null}},{"id":"kwaipilot/kat-coder-pro-v2","name":"Kwaipilot: KAT-Coder-Pro V2","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":144000,"uptime_30m":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"kwaipilot","benchmarks":{"intelligence_index":33.7,"coding_index":59.5,"agentic_index":15.5,"design_arena_best":null}},{"id":"kwaipilot/kat-coder-pro-v2.5","name":"Kwaipilot: KAT-Coder-Pro V2.5","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":80000,"uptime_30m":null,"pricing":{"input":0.74,"output":2.96,"cache_read":0.15,"cache_write":null},"org":"kwaipilot"},{"id":"llama-3.3-70b-instruct","name":"Llama 3.3 70B Instruct","provider":"hyper","quantization":null,"discount":0,"context_length":128000,"pricing":{"input":0.6066,"output":1.0386,"cache_read":0,"cache_write":0.3033},"org":"meta","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"llama-4-maverick-17b-128e-instruct-fp8","name":"Llama 4 Maverick 17B 128E Instruct FP8","provider":"hyper","quantization":null,"discount":0,"context_length":430000,"pricing":{"input":0.284,"output":0.934,"cache_read":0,"cache_write":0.142},"org":"meta","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"mancer/weaver","name":"Mancer: Weaver (alpha)","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":8000,"max_completion_tokens":2000,"uptime_30m":null,"pricing":{"input":0.5,"output":0.75,"cache_read":null,"cache_write":null},"org":"mancer","zdr":true},{"id":"meituan/longcat-2.0","name":"Meituan: LongCat 2.0","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0.6,"context_length":1048756,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.006,"cache_write":null},"org":"meituan"},{"id":"Meta-Llama-3.3-70B-Instruct","name":"Meta-Llama-3.3-70B-Instruct","org":"meta","provider":"sambanova","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.6,"output":1.2,"cache_read":null,"cache_write":null},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":97.87881969967447,"pricing":{"input":0.39999999999999997,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":null,"description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.72,"output":0.72,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta.llama3-1-70b-instruct-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"medium","source":"models.dev","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"meta-llama/llama-3.1-70b-instruct","name":"Meta: Llama 3.1 70B Instruct","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":99.96642041638684,"pricing":{"input":0.7999999999999999,"output":0.7999999999999999,"cache_read":0.7999999999999999,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":null,"description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":99.96689837802052,"pricing":{"input":0.02,"output":0.04,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":16384,"max_completion_tokens":16384,"uptime_30m":99.04541373281036,"pricing":{"input":0.02,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-3.1-8b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-07-24","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.9814574448359,"pricing":{"input":0.049999999999999996,"output":0.08,"cache_read":0.024999999999999998,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"fp8","discount":0,"context_length":32000,"max_completion_tokens":32000,"uptime_30m":100,"pricing":{"input":0.15200000000000002,"output":0.28700000000000003,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.1-8b-instruct-fp8","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2024-07-25","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.22,"output":0.22,"cache_read":0.22,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-23","knowledge_cutoff":"2023-12","description":"Efficient conversational model optimized for responsive multilingual chatbot interactions.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta-llama/llama-3.2-1b-instruct","name":"Meta: Llama 3.2 1B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":60000,"max_completion_tokens":60000,"uptime_30m":null,"pricing":{"input":0.027,"output":0.201,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.2-1b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2024-09-25","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.33,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-09-25","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://developers.cloudflare.com/workers-ai/models/"}},{"id":"meta-llama/llama-3.2-3b-instruct","name":"Meta: Llama 3.2 3B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":80000,"max_completion_tokens":80000,"uptime_30m":100,"pricing":{"input":0.0509,"output":0.335,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.2-3b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2024-09-25","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":94.4252317056301,"pricing":{"input":0.09999999999999999,"output":0.32,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":75.21891418563924,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.013,"cache_write":0.16},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"meta-llama/Llama-3.3-70B-Instruct","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-12-05","knowledge_cutoff":"2025-08","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":128000,"uptime_30m":99.81169694284449,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":6000,"max_completion_tokens":120000,"uptime_30m":97.66737352317479,"pricing":{"input":0.135,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-3.3-70b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-12-07","knowledge_cutoff":"2023-12","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":95.44937428896473,"pricing":{"input":0.22,"output":0.5,"cache_read":0.11,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.82486865148861,"pricing":{"input":0.25,"output":0.75,"cache_read":0.13,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"fp8","discount":0,"context_length":24000,"max_completion_tokens":24000,"uptime_30m":98.99749373433583,"pricing":{"input":0.293,"output":2.2529999999999997,"cache_read":null,"cache_write":null},"org":"meta","modelsdev":{"base_url":null,"model_id":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"medium","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"sambanova","provider_display":"SambaNova","quantization":"bf16","discount":0.25,"context_length":16000,"max_completion_tokens":3072,"uptime_30m":96.05263157894737,"pricing":{"input":0.44999999999999996,"output":0.8999999999999999,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.52559300873908,"pricing":{"input":0.59,"output":0.7899999999999999,"cache_read":0.295,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp16","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.71,"output":0.71,"cache_read":0.71,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":null,"uptime_30m":98.94179894179894,"pricing":{"input":0.72,"output":0.72,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-01","knowledge_cutoff":"2023-12","description":"Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-3.3-70b-instruct","name":"Meta: Llama 3.3 70B Instruct","provider":"together","provider_display":"Together","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":2048,"uptime_30m":92.73743016759776,"pricing":{"input":1.04,"output":1.04,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"medium","source":"models.dev","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Compact Llama instruction model for fast chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/Llama-3.3-70B-Instruct-Turbo","name":"meta-llama/Llama-3.3-70B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.1,"output":0.32,"cache_read":null,"cache_write":null},"org":"meta","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-06","knowledge_cutoff":"2023-12","description":"Compact Llama instruction model for fast chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.together.ai/docs/serverless-models"},"benchmarks":{"intelligence_index":9.4,"coding_index":11.9,"agentic_index":0.3,"design_arena_best":null}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":16384,"uptime_30m":99.96025239727729,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/"},"benchmarks":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3,"design_arena_best":{"category":"3d","elo":956,"win_rate":40.2,"rank":99}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":0.25,"output":0.87,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"llama-4-maverick","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3,"design_arena_best":{"category":"3d","elo":956,"win_rate":40.2,"rank":99}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":8192,"uptime_30m":99.93931118191473,"pricing":{"input":0.27,"output":0.85,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2025-04-06","knowledge_cutoff":null,"description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3,"design_arena_best":{"category":"3d","elo":956,"win_rate":40.2,"rank":99}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":32768,"uptime_30m":99.80550152820229,"pricing":{"input":0.35,"output":1,"cache_read":0.16999999999999998,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/"},"benchmarks":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3,"design_arena_best":{"category":"3d","elo":956,"win_rate":40.2,"rank":99}}},{"id":"meta-llama/llama-4-maverick","name":"Meta: Llama 4 Maverick","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.35,"output":1.15,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/"},"benchmarks":{"intelligence_index":14.3,"coding_index":16.3,"agentic_index":1.3,"design_arena_best":{"category":"3d","elo":956,"win_rate":40.2,"rank":99}}},{"id":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","name":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.2,"output":0.8,"cache_read":null,"cache_write":null},"org":"meta","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for strong reasoning and fast responses","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":327680,"max_completion_tokens":16384,"uptime_30m":99.7836668469443,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"benchmarks":{"intelligence_index":10,"coding_index":8.2,"agentic_index":1.1,"design_arena_best":{"category":"dataviz","elo":925,"win_rate":39.3,"rank":106}}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":99.94241289951051,"pricing":{"input":0.11,"output":0.33999999999999997,"cache_read":0.055,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":null,"model_id":"meta-llama/llama-4-scout-17b-16e-instruct","doc_url":"https://console.groq.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open multimodal Llama model for long-context analysis and efficient agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":10,"coding_index":8.2,"agentic_index":1.1,"design_arena_best":{"category":"dataviz","elo":925,"win_rate":39.3,"rank":106}}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.85754985754986,"pricing":{"input":0.18,"output":0.59,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"meta-llama/llama-4-scout-17b-16e-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2025-04-06","knowledge_cutoff":null,"description":"Open multimodal Llama model for long-context analysis and efficient agents","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":10,"coding_index":8.2,"agentic_index":1.1,"design_arena_best":{"category":"dataviz","elo":925,"win_rate":39.3,"rank":106}}},{"id":"meta-llama/llama-4-scout","name":"Meta: Llama 4 Scout","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":1310720,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.25,"output":0.7,"cache_read":null,"cache_write":null},"org":"meta","zdr":true,"benchmarks":{"intelligence_index":10,"coding_index":8.2,"agentic_index":1.1,"design_arena_best":{"category":"dataviz","elo":925,"win_rate":39.3,"rank":106}}},{"id":"meta-llama/Llama-4-Scout-17B-16E-Instruct","name":"meta-llama/Llama-4-Scout-17B-16E-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":327680,"pricing":{"input":0.1,"output":0.3,"cache_read":null,"cache_write":null},"org":"meta","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04-05","knowledge_cutoff":"2024-08","description":"Open Llama with long-context vision for efficient multimodal agents","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://developers.cloudflare.com/workers-ai/models/"}},{"id":"meta-llama/Llama-Guard-4-12B","name":"meta-llama/Llama-Guard-4-12B","provider":"deepinfra","quantization":null,"discount":0,"context_length":163840,"pricing":{"input":0.18,"output":0.18,"cache_read":null,"cache_write":null},"org":"meta","zdr":true},{"id":"meta-llama/llama-guard-4-12b","name":"Meta: Llama Guard 4 12B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":null,"uptime_30m":99.97592681752528,"pricing":{"input":0.19999999999999998,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"meta","zdr":true},{"id":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","name":"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.4,"output":0.4,"cache_read":null,"cache_write":null},"org":"meta"},{"id":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","name":"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.02,"output":0.04,"cache_read":null,"cache_write":null},"org":"meta","benchmarks":{"intelligence_index":7.6,"coding_index":5.4,"agentic_index":0.5,"design_arena_best":null}},{"id":"meta/muse-spark-1.1","name":"Meta: Muse Spark 1.1","provider":"meta","provider_display":"Meta","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":1.25,"output":4.25,"cache_read":0.15,"cache_write":null},"org":"meta","benchmarks":{"intelligence_index":50.6,"coding_index":71.3,"agentic_index":37.5,"design_arena_best":{"category":"gamedev","elo":1323,"win_rate":55.6,"rank":10}}},{"id":"microsoft/phi-4","name":"microsoft/phi-4","provider":"deepinfra","quantization":null,"discount":0,"context_length":16384,"pricing":{"input":0.07,"output":0.14,"cache_read":null,"cache_write":null},"org":"microsoft","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-12-11","knowledge_cutoff":"2023-10","description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"microsoft/wizardlm-2-8x22b","name":"WizardLM-2 8x22B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":65535,"max_completion_tokens":8000,"uptime_30m":100,"pricing":{"input":0.62,"output":0.62,"cache_read":null,"cache_write":null},"org":"microsoft","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"microsoft/wizardlm-2-8x22b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-04-24","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"mimo-v2.5","name":"MiMo V2.5","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"mimo-v2.5","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"crof","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.4,"output":0.8,"cache_read":0.003,"cache_write":null},"org":"xiaomi","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"mimo-v2.5-pro","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"mimo-v2.5-pro","name":"MiMo V2.5 Pro","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.74,"output":3.48,"cache_read":0.0145,"cache_write":null},"org":"xiaomi","subscription":true,"max_completion_tokens":128000,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"mimo-v2.5-pro","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"mimo-v2.5-pro-ultraspeed","name":"mimo-v2.5-pro-ultraspeed","provider":"xiaomimimo","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":3.915,"output":7.83,"cache_read":0.0324,"cache_write":null},"org":"xiaomimimo","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://api.xiaomimimo.com/v1","model_id":"mimo-v2.5-pro-ultraspeed","doc_url":"https://platform.xiaomimimo.com/#/docs","confidence":"high","source":"models.dev","release_date":"2026-06-08","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"crof","quantization":null,"discount":0,"context_length":204800,"pricing":{"input":0.11,"output":0.95,"cache_read":0.02,"cache_write":0.375},"org":"minimax","zdr":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"minimax-m2.5","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax-m2.5","name":"MiniMax M2.5","provider":"ember","quantization":null,"discount":0,"context_length":196608,"pricing":{"input":0.14250000000000002,"output":0.855,"cache_read":0.04,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax-m2.5","name":"MiniMax M2.5","provider":"opencode","quantization":null,"discount":0,"context_length":204800,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"minimax-m2.5","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":"2025-01","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"MiniMax-M2.7","name":"MiniMax-M2.7","org":"minimax","provider":"sambanova","quantization":null,"discount":0,"context_length":196608,"pricing":{"input":0.6,"output":2.4,"cache_read":0.06,"cache_write":0},"zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax-m2.7","name":"MiniMax M2.7","provider":"hyper","quantization":null,"discount":0,"context_length":204800,"pricing":{"input":0.348,"output":1.332,"cache_read":0,"cache_write":0.174},"org":"minimax","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax-m2.7","name":"MiniMax M2.7","provider":"opencode","quantization":null,"discount":0,"context_length":204000,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"minimax-m2.7","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":"2025-01","description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"MiniMax-M3","name":"MiniMax-M3","provider":"wafer","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.33,"output":1.32,"cache_read":0.07,"cache_write":0},"org":"minimax","max_completion_tokens":128000,"modelsdev":{"base_url":"https://pass.wafer.ai/v1","model_id":"MiniMax-M3","doc_url":"https://docs.wafer.ai/wafer-pass","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax-m3","name":"MiniMax M3","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"max_completion_tokens":131072,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"minimax-m3","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-05-31","knowledge_cutoff":"2025-01","description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-01","name":"MiniMax: MiniMax-01","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":1000192,"max_completion_tokens":1000192,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":1.1,"cache_read":null,"cache_write":null},"org":"minimax","subscription":true},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":40000,"uptime_30m":100,"pricing":{"input":0.39999999999999997,"output":2.2,"cache_read":null,"cache_write":null},"org":"minimax","subscription":true},{"id":"minimax/minimax-m1","name":"MiniMax: MiniMax M1","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":1000000,"max_completion_tokens":40000,"uptime_30m":null,"pricing":{"input":0.55,"output":2.2,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimaxai/minimax-m1-80k","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2025-06-17","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0.15,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.255,"output":1.02,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-27","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1174,"win_rate":48.1,"rank":61}}},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":null,"pricing":{"input":0.3,"output":1.2,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-27","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1174,"win_rate":48.1,"rank":61}}},{"id":"minimax/minimax-m2","name":"MiniMax: MiniMax M2","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-10-27","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1174,"win_rate":48.1,"rank":61}}},{"id":"minimax/minimax-m2-her","name":"MiniMax: MiniMax M2-her","provider":"minimax","provider_display":"Minimax","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":2048,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","subscription":true},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":99.25925925925925,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2.1","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-23","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1259,"win_rate":60.9,"rank":32}}},{"id":"minimax/minimax-m2.1","name":"MiniMax: MiniMax M2.1","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-23","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1259,"win_rate":60.9,"rank":32}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"inceptron","provider_display":"Inceptron","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":100,"pricing":{"input":0.15,"output":0.8999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.15,"output":1.2,"cache_read":0.075,"cache_write":null},"org":"minimax","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"MiniMaxAI/MiniMax-M2.5-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":1.38,"cache_read":0.075,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":128000,"uptime_30m":99.80916030534351,"pricing":{"input":0.22499999999999998,"output":0.8999999999999999,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"minimax-m2.5","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":"2025-08","description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0.2,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":77.7327935222672,"pricing":{"input":0.24,"output":0.96,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":198000,"max_completion_tokens":32768,"uptime_30m":99.16736053288926,"pricing":{"input":0.27,"output":0.95,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.1,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":99.79445015416239,"pricing":{"input":0.27,"output":1.08,"cache_read":0.027,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":99.54648526077098,"pricing":{"input":0.295,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":99.83870967741936,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"MiniMaxAI/MiniMax-M2.5","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"Prior MiniMax coding model for agent workflows, office edits, and automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":99.82342554443791,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131100,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2.5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":100,"pricing":{"input":0.3,"output":1.2,"cache_read":0.03,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.5","name":"MiniMax: MiniMax M2.5","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":99.00990099009901,"pricing":{"input":0.3,"output":1.2,"cache_read":0.3,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-12","knowledge_cutoff":null,"description":"MoE model with a highly sparse architecture designed for high-throughput and low latency with strong coding capabilities.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1247,"win_rate":57.5,"rank":35}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0.6,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":91.23196448390676,"pricing":{"input":0.24,"output":0.96,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.1,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":99.08256880733946,"pricing":{"input":0.27,"output":1.08,"cache_read":0.054,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"minimax/minimax-m2.7","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":98.80124670342843,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":95.78454332552693,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":196608,"uptime_30m":99.83361064891847,"pricing":{"input":0.3,"output":1.2,"cache_read":0.059,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/minimax-m2p7","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m2.7","name":"MiniMax: MiniMax M2.7","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":196608,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.6,"context_length":1048576,"max_completion_tokens":null,"uptime_30m":96.58590308370044,"pricing":{"input":0.24,"output":0.96,"cache_read":0.048,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":99.00125825731362,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":65536,"uptime_30m":92.84447072738024,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":null,"model_id":"minimax-m3-preview","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":512000,"uptime_30m":99.02432321011406,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":524300,"max_completion_tokens":524288,"uptime_30m":98.79326770403303,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":250000,"uptime_30m":98.70150689323502,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev":{"base_url":null,"model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":78.19460726846424,"pricing":{"input":0.3,"output":1.2,"cache_read":null,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3","name":"MiniMax: MiniMax M3","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":96.43811219946572,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.6,"context_length":1048576,"max_completion_tokens":null,"uptime_30m":96.58590308370044,"pricing":{"input":0.24,"output":0.96,"cache_read":0.048,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":99.00125825731362,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":65536,"uptime_30m":92.84447072738024,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev":{"base_url":null,"model_id":"minimax-m3-preview","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"minimax","provider_display":"Minimax","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":512000,"uptime_30m":99.02432321011406,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","subscription":true,"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":524300,"max_completion_tokens":524288,"uptime_30m":98.79326770403303,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":250000,"uptime_30m":98.70150689323502,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","modelsdev":{"base_url":null,"model_id":"MiniMaxAI/MiniMax-M3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"medium","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":78.19460726846424,"pricing":{"input":0.3,"output":1.2,"cache_read":null,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":524288,"max_completion_tokens":512000,"uptime_30m":98.61325115562404,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimax/minimax-m3:batch","name":"MiniMax: MiniMax M3 (batch)","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":96.43811219946572,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"MiniMaxAI/MiniMax-M2.7","name":"MiniMaxAI/MiniMax-M2.7","provider":"deepinfra","quantization":null,"discount":0,"context_length":196608,"pricing":{"input":0.25,"output":1,"cache_read":0.05,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-12","knowledge_cutoff":null,"description":"MiniMax model for chat, coding, office work, and agentic tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"MiniMaxAI/MiniMax-M2.7-Turbo","name":"MiniMaxAI/MiniMax-M2.7-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":196608,"pricing":{"input":0.38,"output":1.7,"cache_read":0.07000000140000001,"cache_write":null},"org":"minimax","benchmarks":{"intelligence_index":38.1,"coding_index":52.6,"agentic_index":25.6,"design_arena_best":{"category":"website","elo":1271,"win_rate":53.9,"rank":27}}},{"id":"MiniMaxAI/MiniMax-M3","name":"MiniMaxAI/MiniMax-M3","provider":"deepinfra","quantization":null,"discount":0,"context_length":524288,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":null},"org":"minimax","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"MiniMax multimodal coding model for long-context reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"minimaxai/minimax-m3","name":"MiniMax M3","provider":"lilac","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.28,"output":1.1,"cache_read":0.049999999999999996,"cache_write":null},"org":"minimax","zdr":true,"subscription":true,"max_completion_tokens":1048576,"modelsdev":{"base_url":"https://api.getlilac.com/v1","model_id":"minimaxai/minimax-m3","doc_url":"https://docs.getlilac.com/inference/models","confidence":"high","source":"models.dev","release_date":"2026-06-01","knowledge_cutoff":null,"description":"MiniMax multimodal model for long-context coding, perception, and agent planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.4,"coding_index":58.6,"agentic_index":35.4,"design_arena_best":{"category":"codecategories","elo":1285,"win_rate":54.4,"rank":22}}},{"id":"mistralai/codestral-2508","name":"Mistral: Codestral 2508","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":null,"uptime_30m":99.83844911147011,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.03,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1077,"win_rate":45.5,"rank":85}}},{"id":"mistralai/devstral-2512","name":"Mistral: Devstral 2 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","modelsdev":{"base_url":null,"model_id":"devstral-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2025-12-09","knowledge_cutoff":"2025-12","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":19.2,"coding_index":31.3,"agentic_index":10.6,"design_arena_best":null}},{"id":"mistralai/ministral-14b-2512","name":"Mistral: Ministral 3 14B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":0.19999999999999998,"cache_read":0.02,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":11.1,"coding_index":14.4,"agentic_index":2.2,"design_arena_best":{"category":"website","elo":1106,"win_rate":44.8,"rank":87}}},{"id":"mistralai/ministral-3b-2512","name":"Mistral: Ministral 3 3B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":99.92977528089888,"pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":0.01,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":6.3,"coding_index":4.8,"agentic_index":1.6,"design_arena_best":{"category":"website","elo":1052,"win_rate":38.2,"rank":99}}},{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":99.91457858769932,"pricing":{"input":0.15,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":9,"coding_index":9.7,"agentic_index":1.2,"design_arena_best":{"category":"website","elo":1090,"win_rate":42.9,"rank":90}}},{"id":"mistralai/ministral-8b-2512","name":"Mistral: Ministral 3 8B 2512","provider":"nextbit","provider_display":"NextBit","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.835255354201,"pricing":{"input":0.3,"output":0.3,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"benchmarks":{"intelligence_index":9,"coding_index":9.7,"agentic_index":1.2,"design_arena_best":{"category":"website","elo":1090,"win_rate":42.9,"rank":90}}},{"id":"mistralai/mistral-large","name":"Mistral Large","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral"},{"id":"mistralai/mistral-large-2407","name":"Mistral Large 2407","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral"},{"id":"mistralai/mistral-large-2512","name":"Mistral: Mistral Large 3 2512","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.98493522145225,"pricing":{"input":0.5,"output":1.5,"cache_read":0.049999999999999996,"cache_write":null},"org":"mistral","modelsdev":{"base_url":null,"model_id":"mistral-large-2512","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2024-11-01","knowledge_cutoff":"2024-11","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":15.9,"coding_index":20.1,"agentic_index":5.5,"design_arena_best":{"category":"website","elo":1187,"win_rate":49.5,"rank":61}}},{"id":"mistralai/mistral-medium-3","name":"Mistral: Mistral Medium 3","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1140,"win_rate":54.6,"rank":65}}},{"id":"mistralai/mistral-medium-3-5","name":"Mistral: Mistral Medium 3.5","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":1.5,"output":7.5,"cache_read":null,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":29.9,"coding_index":46.9,"agentic_index":19,"design_arena_best":null}},{"id":"mistralai/mistral-medium-3.1","name":"Mistral: Mistral Medium 3.1","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.39999999999999997,"output":2,"cache_read":0.04,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":14.7,"coding_index":20.5,"agentic_index":6.2,"design_arena_best":{"category":"dataviz","elo":1175,"win_rate":47.3,"rank":61}}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":97.215740135746,"pricing":{"input":0.019000000000000003,"output":0.03,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-01","knowledge_cutoff":"2024-07","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.mistral.ai/getting-started/models/"}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"io-net","provider_display":"Io Net","quantization":"fp16","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":97.73536663318419,"pricing":{"input":0.035,"output":0.13,"cache_read":0.0175,"cache_write":0.04},"org":"mistral","zdr":true,"modelsdev":{"base_url":"https://api.intelligence.io.solutions/api/v1","model_id":"mistralai/Mistral-Nemo-Instruct-2407","doc_url":"https://io.net/docs/guides/intelligence/io-intelligence","confidence":"medium","source":"models.dev","release_date":"2024-07-01","knowledge_cutoff":"2024-05","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":60288,"max_completion_tokens":16000,"uptime_30m":74.33389544688028,"pricing":{"input":0.04,"output":0.16999999999999998,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"mistralai/mistral-nemo","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-07-30","knowledge_cutoff":null,"description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"mistralai/mistral-nemo","name":"Mistral: Mistral Nemo","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":128000,"uptime_30m":99.98662833455907,"pricing":{"input":0.15,"output":0.15,"cache_read":0.015,"cache_write":null},"org":"mistral","modelsdev":{"base_url":null,"model_id":"mistral-nemo","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2024-07-01","knowledge_cutoff":"2024-07","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"mistralai/Mistral-Nemo-Instruct-2407","name":"mistralai/Mistral-Nemo-Instruct-2407","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.019000000000000003,"output":0.030000000000000002,"cache_read":null,"cache_write":null},"org":"mistral","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-07-18","knowledge_cutoff":null,"description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/"}},{"id":"mistralai/mistral-saba","name":"Mistral: Saba","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":0.19999999999999998,"output":0.6,"cache_read":0.02,"cache_write":null},"org":"mistral"},{"id":"mistralai/Mistral-Small-24B-Instruct-2501","name":"mistralai/Mistral-Small-24B-Instruct-2501","provider":"deepinfra","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.05,"output":0.08,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true},{"id":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":256000,"uptime_30m":99.9763649255495,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"mistral","modelsdev":{"base_url":null,"model_id":"mistral-small-2603","doc_url":"https://docs.mistral.ai/getting-started/models/","confidence":"high","source":"models.dev","release_date":"2026-03-16","knowledge_cutoff":"2025-06","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":19.6,"coding_index":26.6,"agentic_index":4.7,"design_arena_best":null}},{"id":"mistralai/mistral-small-2603","name":"Mistral: Mistral Small 4","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":99.62311557788944,"pricing":{"input":0.1875,"output":0.75,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"modelsdev":{"base_url":null,"model_id":"mistral-small-2603","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2026-03-16","knowledge_cutoff":"2025-06","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":19.6,"coding_index":26.6,"agentic_index":4.7,"design_arena_best":null}},{"id":"mistralai/mistral-small-3.1-24b-instruct","name":"Mistral: Mistral Small 3.1 24B","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.351,"output":0.5549999999999999,"cache_read":null,"cache_write":null},"org":"mistral","modelsdev":{"base_url":null,"model_id":"@cf/mistralai/mistral-small-3.1-24b-instruct","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2025-03-18","knowledge_cutoff":null,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":96.44872543296361,"pricing":{"input":0.075,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":957,"win_rate":43.3,"rank":101}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.10822861775436,"pricing":{"input":0.09,"output":0.3,"cache_read":0.049999999999999996,"cache_write":null},"org":"mistral","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":957,"win_rate":43.3,"rank":101}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":16384,"uptime_30m":96.19333834209868,"pricing":{"input":0.09375,"output":0.25,"cache_read":null,"cache_write":null},"org":"mistral","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":957,"win_rate":43.3,"rank":101}}},{"id":"mistralai/mistral-small-3.2-24b-instruct","name":"Mistral: Mistral Small 3.2 24B","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":99.71244608364069,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":null},"org":"mistral","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":957,"win_rate":43.3,"rank":101}}},{"id":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","name":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","provider":"deepinfra","quantization":null,"discount":0,"context_length":128000,"pricing":{"input":0.075,"output":0.2,"cache_read":null,"cache_write":null},"org":"mistral"},{"id":"mistralai/mixtral-8x22b-instruct","name":"Mistral: Mixtral 8x22B Instruct","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":65536,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":2,"output":6,"cache_read":0.19999999999999998,"cache_write":null},"org":"mistral"},{"id":"mistralai/voxtral-small-24b-2507","name":"Mistral: Voxtral Small 24B 2507","provider":"mistral","provider_display":"Mistral","quantization":"unknown","discount":0,"context_length":32000,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":null},"org":"mistral","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-01","knowledge_cutoff":null,"description":"Efficient Mistral model for fast chat, extraction, and production assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"}},{"id":"moonshotai/kimi-k2","name":"MoonshotAI: Kimi K2 0711","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":100352,"uptime_30m":96.98603283508945,"pricing":{"input":0.5700000000000001,"output":2.3,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"benchmarks":{"intelligence_index":17.3,"coding_index":21,"agentic_index":1.8,"design_arena_best":{"category":"website","elo":1138,"win_rate":48.8,"rank":79}}},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":100352,"uptime_30m":97.02361695244257,"pricing":{"input":0.6,"output":2.5,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2-0905","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-05","knowledge_cutoff":"2024-10","description":"Kimi model for long-context chat, coding, and agentic reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1132,"win_rate":48.3,"rank":81}}},{"id":"moonshotai/kimi-k2-0905","name":"MoonshotAI: Kimi K2 0905","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":1,"output":3,"cache_read":0.5,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-05","knowledge_cutoff":"2024-10","description":"Kimi model for long-context chat, coding, and agentic reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1132,"win_rate":48.3,"rank":81}}},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":100352,"uptime_30m":99.12854030501089,"pricing":{"input":0.6,"output":2.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2-thinking","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-11-07","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":17.3,"coding_index":21,"agentic_index":1.8,"design_arena_best":{"category":"website","elo":1138,"win_rate":48.8,"rank":79}}},{"id":"moonshotai/kimi-k2-thinking","name":"MoonshotAI: Kimi K2 Thinking","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.53372434017595,"pricing":{"input":0.6,"output":2.5,"cache_read":null,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-11-01","knowledge_cutoff":"2024-08","description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":17.3,"coding_index":21,"agentic_index":1.8,"design_arena_best":{"category":"website","elo":1138,"win_rate":48.8,"rank":79}}},{"id":"moonshotai/Kimi-K2.5","name":"moonshotai/Kimi-K2.5","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.45,"output":2.25,"cache_read":0.070000002,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":99.37888198757764,"pricing":{"input":0.375,"output":2.025,"cache_read":0.203,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"kimi-k2.5","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-01","knowledge_cutoff":"2025-01","description":"Kimi model for long-context chat, coding, and agentic reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"chutes","provider_display":"Chutes","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":65535,"uptime_30m":99.62121212121212,"pricing":{"input":0.44,"output":2,"cache_read":0.22,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"moonshotai/Kimi-K2.5-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-01","knowledge_cutoff":"2024-10","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.44999999999999996,"output":2.25,"cache_read":0.07,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.90234375,"pricing":{"input":0.49,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.1,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":99.95978282726725,"pricing":{"input":0.54,"output":2.7,"cache_read":0.09,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":94.7513812154696,"pricing":{"input":0.56,"output":3.5,"cache_read":0.22,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.05,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.96451132088863,"pricing":{"input":0.5700000000000001,"output":2.8499999999999996,"cache_read":0.095,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"moonshot","provider_display":"Moonshot AI","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.6,"output":3,"cache_read":0.09999999999999999,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.5","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-01","knowledge_cutoff":"2025-01","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/kimi-k2.5","name":"MoonshotAI: Kimi K2.5","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.6,"output":3,"cache_read":0.22,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-02","knowledge_cutoff":"2025-01","description":"Kimi K2.5 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters and a total of 1 trillion parameters.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":35.4,"coding_index":46.8,"agentic_index":21.7,"design_arena_best":{"category":"website","elo":1275,"win_rate":55.5,"rank":24}}},{"id":"moonshotai/Kimi-K2.6","name":"moonshotai/Kimi-K2.6","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.7499999999999999,"output":3.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","provider":"lilac","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.7,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://api.getlilac.com/v1","model_id":"moonshotai/kimi-k2.6","doc_url":"https://docs.getlilac.com/inference/models","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"inceptron","provider_display":"Inceptron","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.95340167753962,"pricing":{"input":0.6,"output":3.41,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"baidu","provider_display":"Baidu","quantization":"fp4","discount":0.32,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.54128440366972,"pricing":{"input":0.646,"output":2.7199999999999998,"cache_read":0.1088,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.73856209150327,"pricing":{"input":0.65,"output":3.41,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.36,"pricing":{"input":0.66,"output":3.4,"cache_read":0.144,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"chutes","provider_display":"Chutes","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":65535,"uptime_30m":100,"pricing":{"input":0.66,"output":3.5,"cache_read":0.33,"cache_write":null},"org":"moonshot","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"moonshotai/Kimi-K2.6-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-12","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"modelrun","provider_display":"ModelRun","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.97086247086247,"pricing":{"input":0.7,"output":3.4,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":99.27272727272727,"pricing":{"input":0.7,"output":3.5,"cache_read":0.35,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"parasail","provider_display":"Parasail","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.56803455723542,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"venice","provider_display":"Venice","quantization":"int4","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":99.39024390243902,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.23664122137404,"pricing":{"input":0.76,"output":3.1999999999999997,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"kimi-k2.6","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.77,"output":3.4,"cache_read":0.14,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":89.00523560209425,"pricing":{"input":0.7999999999999999,"output":3.4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.6","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.1,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":92.12121212121212,"pricing":{"input":0.855,"output":3.5999999999999996,"cache_read":0.144,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":94.15204678362574,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"moonshot","provider_display":"Moonshot AI","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":66.95652173913044,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.6","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.581589958159,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","modelsdev":{"base_url":null,"model_id":"@cf/moonshotai/kimi-k2.6","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"sail-research","provider_display":"Sail Research","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":1,"output":4,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":1.0899999999999999,"output":4.6,"cache_read":0.37,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131000,"uptime_30m":100,"pricing":{"input":1.2,"output":4.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K2.6","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":262000,"max_completion_tokens":262000,"uptime_30m":null,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"moonshotai/Kimi-K2.6","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-04-21","knowledge_cutoff":"2025-01","description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/kimi-k2.6","name":"MoonshotAI: Kimi K2.6","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262000,"uptime_30m":null,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/kimi-k2p6","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":44.2,"coding_index":61.8,"agentic_index":30.3,"design_arena_best":{"category":"3d","elo":1332,"win_rate":60.6,"rank":8}}},{"id":"moonshotai/Kimi-K2.7-Code","name":"moonshotai/Kimi-K2.7-Code","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.74,"output":3.5,"cache_read":0.149999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"coreweave","provider_display":"CoreWeave","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.71,"output":3.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"inceptron","provider_display":"Inceptron","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.89858012170384,"pricing":{"input":0.72,"output":3.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"ambient","provider_display":"Ambient","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.77854487519915,"pricing":{"input":0.73,"output":3.5,"cache_read":0.15,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"venice","provider_display":"Venice","quantization":"int4","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.75,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"parasail","provider_display":"Parasail","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.76,"output":3.5,"cache_read":0.16,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.85916,"output":3.8,"cache_read":0.17993,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"novita","provider_display":"Novita","quantization":"int4","discount":0.04,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.912,"output":3.84,"cache_read":0.18239999999999998,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"moonshotai/kimi-k2.7-code","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"moonshot","provider_display":"Moonshot AI","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k2.7-code","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","modelsdev":{"base_url":null,"model_id":"@cf/moonshotai/kimi-k2.7-code","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":"2025-01","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"int4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.95,"output":4,"cache_read":0.16,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K2.7-Code","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-14","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/kimi-k2.7-code","name":"MoonshotAI: Kimi K2.7 Code","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262000,"uptime_30m":null,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/kimi-k2p7-code","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Kimi coding model for software agents, refactors, and repository reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":41.9,"coding_index":60.8,"agentic_index":29.6,"design_arena_best":{"category":"website","elo":1301,"win_rate":55.7,"rank":14}}},{"id":"moonshotai/Kimi-K3","name":"Kimi K3","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":2.25,"output":11.25,"cache_read":0.225,"cache_write":null},"org":"moonshot","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"modal","provider_display":"Modal","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":96.20071684587813,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":99.62825278810409,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"moonshotai/Kimi-K3","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Kimi multimodal agent model for visual understanding, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":99.27536231884058,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":98.88308674209458,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/kimi-k3","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-07-27","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":97.1309578898658,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"modelsdev":{"base_url":null,"model_id":"moonshotai/Kimi-K3","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"moonshotai/kimi-k3","name":"MoonshotAI: Kimi K3","provider":"moonshot","provider_display":"Moonshot AI","quantization":"mxfp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.03717759505236,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write":null},"org":"moonshot","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.moonshot.ai/v1","model_id":"kimi-k3","doc_url":"https://platform.moonshot.ai/docs/api/chat","confidence":"high","source":"models.dev","release_date":"2026-07-16","knowledge_cutoff":null,"description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":57.1,"coding_index":76.2,"agentic_index":50.1,"design_arena_best":{"category":"3d","elo":1457,"win_rate":69.4,"rank":1}}},{"id":"morph/morph-v3-fast","name":"Morph: Morph V3 Fast","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":81920,"max_completion_tokens":38000,"uptime_30m":null,"pricing":{"input":0.7999999999999999,"output":1.2,"cache_read":null,"cache_write":null},"org":"morph","zdr":true,"modelsdev":{"base_url":"https://api.morphllm.com/v1","model_id":"morph-v3-fast","doc_url":"https://docs.morphllm.com/api-reference/introduction","confidence":"high","source":"models.dev","release_date":"2024-08-15","knowledge_cutoff":null,"description":"Efficient model for low-latency assistance, extraction, and routine automation","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"morph/morph-v3-large","name":"Morph: Morph V3 Large","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":null,"pricing":{"input":0.8999999999999999,"output":1.9,"cache_read":null,"cache_write":null},"org":"morph","zdr":true,"modelsdev":{"base_url":"https://api.morphllm.com/v1","model_id":"morph-v3-large","doc_url":"https://docs.morphllm.com/api-reference/introduction","confidence":"high","source":"models.dev","release_date":"2024-08-15","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"nex-agi/nex-n2-mini","name":"Nex AGI: Nex-N2-Mini","provider":"nex-agi","provider_display":"Nex AGI","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.024999999999999998,"output":0.09999999999999999,"cache_read":0.0025,"cache_write":null},"org":"nex-agi"},{"id":"nex-agi/nex-n2-pro","name":"Nex AGI: Nex-N2-Pro","provider":"nex-agi","provider_display":"Nex AGI","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":96.29629629629629,"pricing":{"input":0.25,"output":1,"cache_read":0.024999999999999998,"cache_write":null},"org":"nex-agi","benchmarks":{"intelligence_index":41,"coding_index":59.1,"agentic_index":31,"design_arena_best":{"category":"3d","elo":1307,"win_rate":54.6,"rank":15}}},{"id":"nex-agi/nex-n2-pro","name":"Nex AGI: Nex-N2-Pro","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":256000,"uptime_30m":null,"pricing":{"input":0.5,"output":2.5,"cache_read":0.25,"cache_write":null},"org":"nex-agi","zdr":true,"benchmarks":{"intelligence_index":41,"coding_index":59.1,"agentic_index":31,"design_arena_best":{"category":"3d","elo":1307,"win_rate":54.6,"rank":15}}},{"id":"NousResearch/Hermes-3-Llama-3.1-405B","name":"NousResearch/Hermes-3-Llama-3.1-405B","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":1,"output":1,"cache_read":null,"cache_write":null},"org":"nous","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-25","knowledge_cutoff":null,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.venice.ai"}},{"id":"NousResearch/Hermes-3-Llama-3.1-70B","name":"NousResearch/Hermes-3-Llama-3.1-70B","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.7,"output":0.7,"cache_read":null,"cache_write":null},"org":"nous","zdr":true},{"id":"nousresearch/hermes-4-405b","name":"Nous: Hermes 4 405B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":1,"output":3,"cache_read":0.1,"cache_write":1.25},"org":"nous","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"NousResearch/Hermes-4-405B","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-30","knowledge_cutoff":"2025-11","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"nousresearch/hermes-4-70b","name":"Nous: Hermes 4 70B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.13,"output":0.39999999999999997,"cache_read":0.013,"cache_write":0.16},"org":"nous","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"NousResearch/Hermes-4-70B","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-30","knowledge_cutoff":"2025-11","description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"nvidia/Nemotron-3-Nano-30B-A3B","name":"nvidia/Nemotron-3-Nano-30B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.05,"output":0.2,"cache_read":0.025,"cache_write":null},"org":"nvidia","zdr":true,"benchmarks":{"intelligence_index":14.2,"coding_index":14.4,"agentic_index":2,"design_arena_best":null}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":0.03,"cache_write":null},"org":"nvidia","zdr":true,"benchmarks":{"intelligence_index":14.2,"coding_index":14.4,"agentic_index":2,"design_arena_best":null}},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"NVIDIA: Nemotron 3 Nano 30B A3B","provider":"novita","provider_display":"Novita","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"benchmarks":{"intelligence_index":14.2,"coding_index":14.4,"agentic_index":2,"design_arena_best":null}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"deepinfra","provider_display":"DeepInfra","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":97.22536806342016,"pricing":{"input":0.08499999999999999,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-11","knowledge_cutoff":"2026-02","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7,"design_arena_best":null}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":null,"uptime_30m":99.84423676012462,"pricing":{"input":0.21,"output":0.45499999999999996,"cache_read":0.06,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-11","knowledge_cutoff":"2026-02","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7,"design_arena_best":null}},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"NVIDIA: Nemotron 3 Super","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":null,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"nvidia/nemotron-3-super-120b-a12b","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-03-11","knowledge_cutoff":"2026-02","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7,"design_arena_best":null}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":93.76299376299376,"pricing":{"input":0.5,"output":2.2,"cache_read":0.09999999999999999,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-04","knowledge_cutoff":null,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.together.ai/docs/serverless-models"},"benchmarks":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4,"design_arena_best":{"category":"3d","elo":1189,"win_rate":41.6,"rank":50}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":202800,"max_completion_tokens":202800,"uptime_30m":100,"pricing":{"input":0.6,"output":2.4,"cache_read":0.12,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"medium","source":"models.dev","release_date":"2026-06-04","knowledge_cutoff":null,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4,"design_arena_best":{"category":"3d","elo":1189,"win_rate":41.6,"rank":50}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":512288,"max_completion_tokens":512300,"uptime_30m":99,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":0.19999999999999998,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":null,"model_id":"nvidia/nemotron-3-ultra-550b-a55b","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-04","knowledge_cutoff":null,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4,"design_arena_best":{"category":"3d","elo":1189,"win_rate":41.6,"rank":50}}},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"NVIDIA: Nemotron 3 Ultra","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":32768,"uptime_30m":81.56028368794325,"pricing":{"input":0.625,"output":3.125,"cache_read":0.1875,"cache_write":null},"org":"nvidia","zdr":true,"modelsdev":{"base_url":null,"model_id":"nvidia-nemotron-3-ultra-550b-a55b","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-06-04","knowledge_cutoff":null,"description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4,"design_arena_best":{"category":"3d","elo":1189,"win_rate":41.6,"rank":50}}},{"id":"nvidia/Nemotron-Content-Safety-3.5","name":"nvidia/Nemotron-Content-Safety-3.5","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.2,"output":0.2,"cache_read":null,"cache_write":null},"org":"nvidia"},{"id":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","name":"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.08499999999999999,"output":0.4,"cache_read":null,"cache_write":null},"org":"nvidia","benchmarks":{"intelligence_index":25.4,"coding_index":37.7,"agentic_index":8.7,"design_arena_best":null}},{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.5,"output":2.2,"cache_read":0.1,"cache_write":null},"org":"nvidia","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-04","knowledge_cutoff":null,"description":"Nemotron 3 Ultra is a powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.8,"coding_index":49.3,"agentic_index":27.4,"design_arena_best":{"category":"3d","elo":1189,"win_rate":41.6,"rank":50}}},{"id":"openai/gpt-3.5-turbo","name":"OpenAI: GPT-3.5 Turbo","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":16385,"max_completion_tokens":4096,"uptime_30m":100,"pricing":{"input":0.5,"output":1.5,"cache_read":0,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-3.5-turbo","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2023-03-01","knowledge_cutoff":"2021-09-01","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":10.7,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-3.5-turbo-0613","name":"OpenAI: GPT-3.5 Turbo (older v0613)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":4095,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":1,"output":2,"cache_read":null,"cache_write":null},"org":"openai","zdr":true},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":16385,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":3,"output":4,"cache_read":null,"cache_write":null},"org":"openai"},{"id":"openai/gpt-3.5-turbo-16k","name":"OpenAI: GPT-3.5 Turbo 16k","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":16385,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":3,"output":4,"cache_read":null,"cache_write":null},"org":"openai","zdr":true},{"id":"openai/gpt-3.5-turbo-instruct","name":"OpenAI: GPT-3.5 Turbo Instruct","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":4095,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":1.5,"output":2,"cache_read":null,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2023-09-21","knowledge_cutoff":"2021-08","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":8191,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":30,"output":60,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2023-11-06","knowledge_cutoff":"2023-11","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-4","name":"OpenAI: GPT-4","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":8191,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":30,"output":60,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2023-11-06","knowledge_cutoff":"2023-11","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://platform.openai.com/docs/models"},"benchmarks":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-4-turbo","name":"OpenAI: GPT-4 Turbo","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":10,"output":30,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4-turbo","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2023-11-06","knowledge_cutoff":"2023-12","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":21.5,"agentic_index":null,"design_arena_best":null}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-4.1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1136,"win_rate":59.1,"rank":72}}},{"id":"openai/gpt-4.1","name":"OpenAI: GPT-4.1","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":99.74869419532867,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1136,"win_rate":59.1,"rank":72}}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":99.48190049092051,"pricing":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":14.8,"coding_index":20.2,"agentic_index":1.7,"design_arena_best":{"category":"gamedev","elo":1127,"win_rate":58.5,"rank":78}}},{"id":"openai/gpt-4.1-mini","name":"OpenAI: GPT-4.1 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.39999999999999997,"output":1.5999999999999999,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-4.1-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":14.8,"coding_index":20.2,"agentic_index":1.7,"design_arena_best":{"category":"gamedev","elo":1127,"win_rate":58.5,"rank":78}}},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":99.2796134932275,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.024999999999999998,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4.1-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":9.6,"coding_index":11.1,"agentic_index":1.2,"design_arena_best":{"category":"gamedev","elo":1027,"win_rate":49.6,"rank":97}}},{"id":"openai/gpt-4.1-nano","name":"OpenAI: GPT-4.1 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1047576,"max_completion_tokens":32768,"uptime_30m":99.61538461538461,"pricing":{"input":0.09999999999999999,"output":0.39999999999999997,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-4.1-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-04-14","knowledge_cutoff":"2024-04","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":9.6,"coding_index":11.1,"agentic_index":1.2,"design_arena_best":{"category":"gamedev","elo":1027,"win_rate":49.6,"rank":97}}},{"id":"openai/gpt-4o-2024-08-06","name":"OpenAI: GPT-4o (2024-08-06)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-4o","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2024-05-13","knowledge_cutoff":"2023-09","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":962,"win_rate":42.3,"rank":104}}},{"id":"openai/gpt-4o-2024-11-20","name":"OpenAI: GPT-4o (2024-11-20)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":2.5,"output":10,"cache_read":1.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-05-13","knowledge_cutoff":"2023-09","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":962,"win_rate":42.3,"rank":104}}},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":99.97483191313414,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-4o-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2023-09","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1,"design_arena_best":null}},{"id":"openai/gpt-4o-mini","name":"OpenAI: GPT-4o-mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":99.97123176013682,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-4o-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-07-18","knowledge_cutoff":"2023-09","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":11.4,"agentic_index":1,"design_arena_best":null}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":34.7,"coding_index":37.8,"agentic_index":25.7,"design_arena_best":{"category":"dataviz","elo":1267,"win_rate":63.3,"rank":23}}},{"id":"openai/gpt-5","name":"OpenAI: GPT-5","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.85777777777778,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":34.7,"coding_index":37.8,"agentic_index":25.7,"design_arena_best":{"category":"dataviz","elo":1267,"win_rate":63.3,"rank":23}}},{"id":"openai/gpt-5-codex","name":"OpenAI: GPT-5 Codex","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-15","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"webapps","elo":1138,"win_rate":52.4,"rank":27}}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":96.19930766057432,"pricing":{"input":0.25,"output":2,"cache_read":0.024999999999999998,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.3,"coding_index":15.6,"agentic_index":19.4,"design_arena_best":{"category":"gamedev","elo":1185,"win_rate":46.5,"rank":59}}},{"id":"openai/gpt-5-mini","name":"OpenAI: GPT-5 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.25,"output":2,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.3,"coding_index":15.6,"agentic_index":19.4,"design_arena_best":{"category":"gamedev","elo":1185,"win_rate":46.5,"rank":59}}},{"id":"openai/gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":96.19930766057432,"pricing":{"input":0.25,"output":2,"cache_read":0.024999999999999998,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.3,"coding_index":15.6,"agentic_index":19.4,"design_arena_best":{"category":"gamedev","elo":1185,"win_rate":46.5,"rank":59}}},{"id":"openai/gpt-5-mini:batch","name":"OpenAI: GPT-5 Mini (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.25,"output":2,"cache_read":0.03,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":25.3,"coding_index":15.6,"agentic_index":19.4,"design_arena_best":{"category":"gamedev","elo":1185,"win_rate":46.5,"rank":59}}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":97.52243829468961,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.005,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1126,"win_rate":48.9,"rank":83}}},{"id":"openai/gpt-5-nano","name":"OpenAI: GPT-5 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.01,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1126,"win_rate":48.9,"rank":83}}},{"id":"openai/gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":97.52243829468961,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.005,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1126,"win_rate":48.9,"rank":83}}},{"id":"openai/gpt-5-nano:batch","name":"OpenAI: GPT-5 Nano (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.39999999999999997,"cache_read":0.01,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-05-30","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1126,"win_rate":48.9,"rank":83}}},{"id":"openai/gpt-5-pro","name":"OpenAI: GPT-5 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":15,"output":120,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-10-06","knowledge_cutoff":"2024-09-30","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.70320905212391,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":36.9,"coding_index":49.4,"agentic_index":21,"design_arena_best":{"category":"gamedev","elo":1235,"win_rate":55.9,"rank":37}}},{"id":"openai/gpt-5.1","name":"OpenAI: GPT-5.1","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Speech generation model for controllable voice, narration, and audio delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false},"benchmarks":{"intelligence_index":36.9,"coding_index":49.4,"agentic_index":21,"design_arena_best":{"category":"gamedev","elo":1235,"win_rate":55.9,"rank":37}}},{"id":"openai/gpt-5.1-chat","name":"OpenAI: GPT-5.1 Chat","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","zdr":true,"benchmarks":{"intelligence_index":36.9,"coding_index":49.4,"agentic_index":21,"design_arena_best":{"category":"gamedev","elo":1235,"win_rate":55.9,"rank":37}}},{"id":"openai/gpt-5.1-codex","name":"OpenAI: GPT-5.1-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Speech generation model for controllable voice, narration, and audio delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1202,"win_rate":50.7,"rank":47}}},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"openai/gpt-5.1-codex-max","name":"OpenAI: GPT-5.1-Codex-Max","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex-max","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.1-codex-mini","name":"OpenAI: GPT-5.1-Codex-Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":0.25,"output":2,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.1-codex-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1149,"win_rate":43.4,"rank":69}}},{"id":"openai/gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.70320905212391,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-11-13","knowledge_cutoff":"2024-09-30","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":36.9,"coding_index":49.4,"agentic_index":21,"design_arena_best":{"category":"gamedev","elo":1235,"win_rate":55.9,"rank":37}}},{"id":"openai/gpt-5.1:batch","name":"OpenAI: GPT-5.1 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.25,"output":10,"cache_read":0.13,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.1","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2025-11-14","knowledge_cutoff":"2024-09-30","description":"Speech generation model for controllable voice, narration, and audio delivery","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","audio"],"output":["text","image","audio"]},"open_weights":false},"benchmarks":{"intelligence_index":36.9,"coding_index":49.4,"agentic_index":21,"design_arena_best":{"category":"gamedev","elo":1235,"win_rate":55.9,"rank":37}}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.88121634463097,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.2","name":"OpenAI: GPT-5.2","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2-chat-latest","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.2-chat","name":"OpenAI: GPT-5.2 Chat","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-14","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"androidnative","elo":1176,"win_rate":47.5,"rank":17}}},{"id":"openai/gpt-5.2-codex","name":"OpenAI: GPT-5.2-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.2-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-01-14","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"androidnative","elo":1176,"win_rate":47.5,"rank":17}}},{"id":"openai/gpt-5.2-pro","name":"OpenAI: GPT-5.2 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":21,"output":168,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.88121634463097,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.2:batch","name":"OpenAI: GPT-5.2 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.2","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2025-12-11","knowledge_cutoff":"2025-08-31","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1252,"win_rate":56.1,"rank":34}}},{"id":"openai/gpt-5.3-chat","name":"OpenAI: GPT-5.3 Chat","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true},{"id":"openai/gpt-5.3-chat","name":"OpenAI: GPT-5.3 Chat","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.3-chat-latest","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":"2025-08-31","description":"Chat-tuned GPT model for conversational assistance, writing, and tool workflows","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.80707395498392,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.3-codex","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-02-05","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1218,"win_rate":51.3,"rank":44}}},{"id":"openai/gpt-5.3-codex","name":"OpenAI: GPT-5.3-Codex","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.75,"output":14,"cache_read":0.175,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.3-codex","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-02-24","knowledge_cutoff":"2025-08-31","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1218,"win_rate":51.3,"rank":44}}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":98.60893652896543,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.4,"coding_index":71.1,"agentic_index":41.1,"design_arena_best":{"category":"gamedev","elo":1295,"win_rate":57.6,"rank":19}}},{"id":"openai/gpt-5.4","name":"OpenAI: GPT-5.4","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.4,"coding_index":71.1,"agentic_index":41.1,"design_arena_best":{"category":"gamedev","elo":1295,"win_rate":57.6,"rank":19}}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":60.74436479598789,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":40,"coding_index":56.1,"agentic_index":30.2,"design_arena_best":null}},{"id":"openai/gpt-5.4-mini","name":"OpenAI: GPT-5.4 Mini","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.99717729415417,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":40,"coding_index":56.1,"agentic_index":30.2,"design_arena_best":null}},{"id":"openai/gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":60.74436479598789,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":40,"coding_index":56.1,"agentic_index":30.2,"design_arena_best":null}},{"id":"openai/gpt-5.4-mini:batch","name":"OpenAI: GPT-5.4 Mini (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.99717729415417,"pricing":{"input":0.75,"output":4.5,"cache_read":0.075,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-mini","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":40,"coding_index":56.1,"agentic_index":30.2,"design_arena_best":null}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.99221305092665,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":38.2,"coding_index":56.1,"agentic_index":27.5,"design_arena_best":null}},{"id":"openai/gpt-5.4-nano","name":"OpenAI: GPT-5.4 Nano","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":96.82155967409794,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":38.2,"coding_index":56.1,"agentic_index":27.5,"design_arena_best":null}},{"id":"openai/gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.99221305092665,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":38.2,"coding_index":56.1,"agentic_index":27.5,"design_arena_best":null}},{"id":"openai/gpt-5.4-nano:batch","name":"OpenAI: GPT-5.4 Nano (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":96.82155967409794,"pricing":{"input":0.19999999999999998,"output":1.25,"cache_read":0.02,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-nano","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-17","knowledge_cutoff":"2025-08-31","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":38.2,"coding_index":56.1,"agentic_index":27.5,"design_arena_best":null}},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.4-pro","name":"OpenAI: GPT-5.4 Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.4-pro","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":98.60893652896543,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.4,"coding_index":71.1,"agentic_index":41.1,"design_arena_best":{"category":"gamedev","elo":1295,"win_rate":57.6,"rank":19}}},{"id":"openai/gpt-5.4:batch","name":"OpenAI: GPT-5.4 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.4","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-03-05","knowledge_cutoff":"2025-08-31","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.4,"coding_index":71.1,"agentic_index":41.1,"design_arena_best":{"category":"gamedev","elo":1295,"win_rate":57.6,"rank":19}}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":97.73131432882471,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":54.8,"coding_index":74.9,"agentic_index":44.9,"design_arena_best":{"category":"gamedev","elo":1345,"win_rate":61.3,"rank":4}}},{"id":"openai/gpt-5.5","name":"OpenAI: GPT-5.5","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":54.8,"coding_index":74.9,"agentic_index":44.9,"design_arena_best":{"category":"gamedev","elo":1345,"win_rate":61.3,"rank":4}}},{"id":"openai/gpt-5.5-pro","name":"OpenAI: GPT-5.5 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":30,"output":180,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false}},{"id":"openai/gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":97.73131432882471,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-04-23","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":54.8,"coding_index":74.9,"agentic_index":44.9,"design_arena_best":{"category":"gamedev","elo":1345,"win_rate":61.3,"rank":4}}},{"id":"openai/gpt-5.5:batch","name":"OpenAI: GPT-5.5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2026-04-24","knowledge_cutoff":"2025-12-01","description":"Default frontier GPT for coding, computer use, research, and knowledge work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":54.8,"coding_index":74.9,"agentic_index":44.9,"design_arena_best":{"category":"gamedev","elo":1345,"win_rate":61.3,"rank":4}}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0.5,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":99.52398255813954,"pricing":{"input":0.5,"output":3,"cache_read":0.049999999999999996,"cache_write":0.625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.2,"coding_index":71.4,"agentic_index":45.6,"design_arena_best":null}},{"id":"openai/gpt-5.6-luna","name":"OpenAI: GPT-5.6 Luna","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.6-luna","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":51.2,"coding_index":71.4,"agentic_index":45.6,"design_arena_best":null}},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0.5,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":99.46483180428135,"pricing":{"input":0.5,"output":3,"cache_read":0.049999999999999996,"cache_write":0.625},"org":"openai"},{"id":"openai/gpt-5.6-luna-pro","name":"OpenAI: GPT-5.6 Luna Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1,"output":6,"cache_read":0.09999999999999999,"cache_write":1.25},"org":"openai","zdr":true},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":99.85273402484313,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":58.9,"coding_index":77.4,"agentic_index":54,"design_arena_best":null}},{"id":"openai/gpt-5.6-sol","name":"OpenAI: GPT-5.6 Sol","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":99.84152139461173,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.6-sol","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":58.9,"coding_index":77.4,"agentic_index":54,"design_arena_best":null}},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"org":"openai","zdr":true},{"id":"openai/gpt-5.6-sol-pro","name":"OpenAI: GPT-5.6 Sol Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":99.47643979057592,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":6.25},"org":"openai"},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0.5,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":89.24335979613839,"pricing":{"input":1.25,"output":7.5,"cache_read":0.125,"cache_write":1.5625},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":55,"coding_index":76.7,"agentic_index":47.4,"design_arena_best":null}},{"id":"openai/gpt-5.6-terra","name":"OpenAI: GPT-5.6 Terra","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-5.6-terra","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"high","source":"models.dev","release_date":"2026-07-09","knowledge_cutoff":"2026-02-16","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":55,"coding_index":76.7,"agentic_index":47.4,"design_arena_best":null}},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0.5,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":98.75,"pricing":{"input":1.25,"output":7.5,"cache_read":0.125,"cache_write":1.5625},"org":"openai"},{"id":"openai/gpt-5.6-terra-pro","name":"OpenAI: GPT-5.6 Terra Pro","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":1050000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":2.5,"output":15,"cache_read":0.25,"cache_write":3.125},"org":"openai","zdr":true},{"id":"openai/gpt-5:batch","name":"OpenAI: GPT-5 (batch)","provider":"azure","provider_display":"Azure","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":34.7,"coding_index":37.8,"agentic_index":25.7,"design_arena_best":{"category":"dataviz","elo":1267,"win_rate":63.3,"rank":23}}},{"id":"openai/gpt-5:batch","name":"OpenAI: GPT-5 (batch)","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":99.85777777777778,"pricing":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"gpt-5","doc_url":"https://platform.openai.com/docs/models","confidence":"medium","source":"models.dev","release_date":"2025-08-07","knowledge_cutoff":"2024-09-30","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":34.7,"coding_index":37.8,"agentic_index":25.7,"design_arena_best":{"category":"dataviz","elo":1267,"win_rate":63.3,"rank":23}}},{"id":"openai/gpt-chat-latest","name":"OpenAI: GPT Chat Latest","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":400000,"max_completion_tokens":128000,"uptime_30m":100,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-05","knowledge_cutoff":"2025-12-01","description":"Compact GPT model for low-latency assistance and high-volume workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false,"doc_url":"https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/models"}},{"id":"openai/gpt-oss-120b","name":"openai/gpt-oss-120b","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.037,"output":0.16999999999999998,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":98.26831935836675,"pricing":{"input":0.03,"output":0.16999999999999998,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"novita","provider_display":"Novita","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.17208752217623,"pricing":{"input":0.049999999999999996,"output":0.25,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"openai/gpt-oss-120b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-08-06","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":68.95220588235294,"pricing":{"input":0.049999999999999996,"output":0.44999999999999996,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":45.058930190389844,"pricing":{"input":0.06,"output":0.5,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":131072,"uptime_30m":99.92814543364231,"pricing":{"input":0.07,"output":0.49,"cache_read":0.02,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"openai-gpt-oss-120b","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"medium","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2024-06","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.89183342347215,"pricing":{"input":0.09,"output":0.36,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"baseten","provider_display":"BaseTen","quantization":"fp4","discount":0,"context_length":128072,"max_completion_tokens":128072,"uptime_30m":99.1260721799644,"pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.09999999999999999,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2025-08","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":92.68116523553486,"pricing":{"input":0.09999999999999999,"output":0.75,"cache_read":0.055,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai.gpt-oss-120b","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":94.10161090458489,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":"2025-08","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"nebius","provider_display":"Nebius","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":0.18},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"openai/gpt-oss-120b","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-10","knowledge_cutoff":"2025-09","description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":99.98930938635878,"pricing":{"input":0.15,"output":0.6,"cache_read":0.075,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-120b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"mara","provider_display":"Mara","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":69.76516634050881,"pricing":{"input":0.15,"output":0.75,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b","name":"OpenAI: gpt-oss-120b","provider":"cerebras","provider_display":"Cerebras","quantization":"fp16","discount":0,"context_length":131072,"max_completion_tokens":40960,"uptime_30m":99.99587645870274,"pricing":{"input":0.35,"output":0.75,"cache_read":0.35,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"gpt-oss-120b","doc_url":"https://inference-docs.cerebras.ai/models/overview","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open GPT reasoning model for self-hosted agents and controllable deployments","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b-Turbo","name":"openai/gpt-oss-120b-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"openai","benchmarks":{"intelligence_index":23.8,"coding_index":30.4,"agentic_index":13.2,"design_arena_best":{"category":"gamedev","elo":1049,"win_rate":40.6,"rank":92}}},{"id":"openai/gpt-oss-120b-Ultra","name":"openai/gpt-oss-120b-Ultra","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.2,"output":0.95,"cache_read":null,"cache_write":null},"org":"openai"},{"id":"openai/gpt-oss-20b","name":"openai/gpt-oss-20b","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.030000000000000002,"output":0.14,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.6006221885904,"pricing":{"input":0.03,"output":0.13,"cache_read":0.03,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":88.14538043478261,"pricing":{"input":0.03,"output":0.15,"cache_read":0.02,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"novita","provider_display":"Novita","quantization":"fp4","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.93269015032533,"pricing":{"input":0.04,"output":0.15,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"openai/gpt-oss-20b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-08-06","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":94.28571428571428,"pricing":{"input":0.04,"output":0.15,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":99.87962684321397,"pricing":{"input":0.04,"output":0.18,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":null,"pricing":{"input":0.049999999999999996,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-20b","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.07,"output":0.15,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai.gpt-oss-20b","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":89.48069241011984,"pricing":{"input":0.07,"output":0.25,"cache_read":null,"cache_write":null},"org":"openai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":97.57602468047598,"pricing":{"input":0.07,"output":0.3,"cache_read":0.035,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/gpt-oss-20b","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-20b","name":"OpenAI: gpt-oss-20b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":99.70151190707935,"pricing":{"input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-20b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-08-05","knowledge_cutoff":null,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":14.9,"coding_index":20.7,"agentic_index":3.1,"design_arena_best":{"category":"dataviz","elo":963,"win_rate":39.7,"rank":100}}},{"id":"openai/gpt-oss-safeguard-20b","name":"OpenAI: gpt-oss-safeguard-20b","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.075,"output":0.3,"cache_read":0.0375,"cache_write":null},"org":"openai","zdr":true,"modelsdev":{"base_url":null,"model_id":"openai/gpt-oss-safeguard-20b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-10-29","knowledge_cutoff":null,"description":"Safety model for policy screening, moderation, and risk-aware routing workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"openai/o1","name":"OpenAI: o1","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":15,"output":60,"cache_read":7.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o1","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-12-05","knowledge_cutoff":"2023-09","description":"O-series reasoning model for hard analysis, math, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":39.7,"agentic_index":null,"design_arena_best":null}},{"id":"openai/o1-pro","name":"OpenAI: o1-pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":150,"output":600,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o1-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-03-19","knowledge_cutoff":"2023-09","description":"O-series reasoning model for hard analysis, math, coding, and planning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/o3","name":"OpenAI: o3","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":100,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-16","knowledge_cutoff":"2024-05","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1200,"win_rate":48.1,"rank":49}}},{"id":"openai/o3-deep-research","name":"OpenAI: o3 Deep Research","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":10,"output":40,"cache_read":2.5,"cache_write":null},"org":"openai"},{"id":"openai/o3-mini","name":"OpenAI: o3 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":1.1,"output":4.4,"cache_read":0.55,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2024-12-20","knowledge_cutoff":"2024-05","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"openai/o3-mini-high","name":"OpenAI: o3 Mini High","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":1.1,"output":4.4,"cache_read":0.55,"cache_write":null},"org":"openai","benchmarks":{"intelligence_index":15.6,"coding_index":16.3,"agentic_index":1.7,"design_arena_best":null}},{"id":"openai/o3-pro","name":"OpenAI: o3 Pro","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":20,"output":80,"cache_read":null,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o3-pro","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-10","knowledge_cutoff":"2024-05","description":"High-effort o3 tier for difficult technical reasoning and careful answers","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"openai/o4-mini","name":"OpenAI: o4 Mini","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":100,"pricing":{"input":1.1,"output":4.4,"cache_read":0.275,"cache_write":null},"org":"openai","modelsdev":{"base_url":null,"model_id":"o4-mini","doc_url":"https://platform.openai.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-04-16","knowledge_cutoff":"2024-05","description":"Fast o-series model for compact reasoning, coding, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1059,"win_rate":50,"rank":89}}},{"id":"openai/o4-mini-deep-research","name":"OpenAI: o4 Mini Deep Research","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":2,"output":8,"cache_read":0.5,"cache_write":null},"org":"openai"},{"id":"openai/o4-mini-high","name":"OpenAI: o4 Mini High","provider":"openai","provider_display":"OpenAI","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":100000,"uptime_30m":null,"pricing":{"input":1.1,"output":4.4,"cache_read":0.275,"cache_write":null},"org":"openai"},{"id":"perceptron/perceptron-mk1","name":"Perceptron: Perceptron Mk1","provider":"perceptron","provider_display":"Perceptron","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.15,"output":1.5,"cache_read":null,"cache_write":null},"org":"perceptron","zdr":true},{"id":"perplexity/sonar","name":"Perplexity: Sonar","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":127072,"max_completion_tokens":4096,"uptime_30m":100,"pricing":{"input":1,"output":1,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"modelsdev":{"base_url":null,"model_id":"sonar","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Fast web-grounded Sonar for current answers, citations, and lightweight retrieval","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"perplexity/sonar-deep-research","name":"Perplexity: Sonar Deep Research","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":2,"output":8,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"modelsdev":{"base_url":null,"model_id":"sonar-deep-research","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2025-02-01","knowledge_cutoff":"2025-01","description":"Sonar search model for current answers, retrieval, and citation-backed chat","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"perplexity/sonar-pro","name":"Perplexity: Sonar Pro","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":8000,"uptime_30m":100,"pricing":{"input":3,"output":15,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"modelsdev":{"base_url":null,"model_id":"sonar-pro","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Deeper Sonar search model with broader retrieval and stronger synthesis","capabilities":{"reasoning":false,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"perplexity/sonar-pro-search","name":"Perplexity: Sonar Pro Search","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":8000,"uptime_30m":100,"pricing":{"input":3,"output":15,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true},{"id":"perplexity/sonar-reasoning-pro","name":"Perplexity: Sonar Reasoning Pro","provider":"perplexity","provider_display":"Perplexity","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":4096,"uptime_30m":100,"pricing":{"input":2,"output":8,"cache_read":null,"cache_write":null},"org":"perplexity","zdr":true,"modelsdev":{"base_url":null,"model_id":"sonar-reasoning-pro","doc_url":"https://docs.perplexity.ai","confidence":"high","source":"models.dev","release_date":"2024-01-01","knowledge_cutoff":"2025-09-01","description":"Web-grounded Sonar for multi-step research questions that need cited reasoning","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"poolside/laguna-s-2.1","name":"Poolside: Laguna S 2.1","provider":"poolside","provider_display":"Poolside","quantization":"bf16","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":0.01,"cache_write":0},"org":"poolside","modelsdev":{"base_url":"https://inference.poolside.ai/v1","model_id":"poolside/laguna-s-2.1","doc_url":"https://platform.poolside.ai","confidence":"high","source":"models.dev","release_date":"2026-07-21","knowledge_cutoff":null,"description":"Agentic coding model from Poolside in the XS size class for local deployment","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"poolside/laguna-xs-2.1","name":"Poolside: Laguna XS 2.1","provider":"poolside","provider_display":"Poolside","quantization":"fp8","discount":0.4,"context_length":262144,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.06,"output":0.12,"cache_read":0.03,"cache_write":0},"org":"poolside","modelsdev":{"base_url":"https://inference.poolside.ai/v1","model_id":"poolside/laguna-xs-2.1","doc_url":"https://platform.poolside.ai","confidence":"high","source":"models.dev","release_date":"2026-07-02","knowledge_cutoff":null,"description":"Agentic coding model from Poolside in the XS size class for local deployment","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":16384,"uptime_30m":99.5878606219558,"pricing":{"input":0.36,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-10-15","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen-2.5-72b-instruct","name":"Qwen2.5 72B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":32000,"max_completion_tokens":8192,"uptime_30m":null,"pricing":{"input":0.38,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen-2.5-72b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2024-10-15","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":99.9207413730033,"pricing":{"input":0.04,"output":0.09999999999999999,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true},{"id":"qwen/qwen-2.5-7b-instruct","name":"Qwen: Qwen2.5 7B Instruct","provider":"together","provider_display":"Together","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":2048,"uptime_30m":100,"pricing":{"input":0.3,"output":0.3,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true},{"id":"qwen/qwen-2.5-coder-32b-instruct","name":"Qwen2.5 Coder 32B Instruct","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.66,"output":1,"cache_read":null,"cache_write":null},"org":"qwen"},{"id":"qwen/qwen-plus-2025-07-28","name":"Qwen: Qwen Plus 0728","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.26,"output":0.78,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2024-01-25","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"Qwen/Qwen2.5-72B-Instruct","name":"Qwen/Qwen2.5-72B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":32768,"pricing":{"input":0.36,"output":0.4,"cache_read":null,"cache_write":null},"org":"qwen"},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":32000,"max_completion_tokens":8192,"uptime_30m":99.87608426270135,"pricing":{"input":0.25,"output":0.75,"cache_read":0.025,"cache_write":0.31},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"Qwen/Qwen2.5-VL-72B-Instruct","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2025-01-20","knowledge_cutoff":"2024-12","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen2.5-vl-72b-instruct","name":"Qwen: Qwen2.5 VL 72B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":128000,"uptime_30m":99.71550497866288,"pricing":{"input":0.7999999999999999,"output":1,"cache_read":0.39999999999999997,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-20","knowledge_cutoff":"2024-12","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"}},{"id":"Qwen/Qwen3-14B","name":"Qwen/Qwen3-14B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.12000000000000001,"output":0.24000000000000002,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","provider":"nextbit","provider_display":"NextBit","quantization":"int4","discount":0,"context_length":40960,"max_completion_tokens":40960,"uptime_30m":98.80861463265617,"pricing":{"input":0.09999999999999999,"output":0.24,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-14b","name":"Qwen: Qwen3 14B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":91.33603238866397,"pricing":{"input":0.22749999999999998,"output":0.9099999999999999,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-14b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":10.4,"coding_index":13.8,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-235b-a22b","name":"Qwen: Qwen3 235B A22B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.45499999999999996,"output":1.8199999999999998,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-235b-a22b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1055,"win_rate":40.5,"rank":98}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":92.01293340671435,"pricing":{"input":0.09,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":90.65158291677629,"pricing":{"input":0.09,"output":0.58,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.81565275682924,"pricing":{"input":0.14,"output":0.7999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.98384230085637,"pricing":{"input":0.14950000000000002,"output":0.5980000000000001,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":86.94649446494465,"pricing":{"input":0.15,"output":0.75,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":71.75936435868331,"pricing":{"input":0.19999999999999998,"output":0.6,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.11623246492987,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"Qwen/Qwen3-235B-A22B-Instruct-2507","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"medium","source":"models.dev","release_date":"2025-07-29","knowledge_cutoff":"2025-04","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.84164687252573,"pricing":{"input":0.19999999999999998,"output":0.88,"cache_read":0.19999999999999998,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.4,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":99.97072599531616,"pricing":{"input":0.21,"output":0.84,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"crusoe","provider_display":"Crusoe","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.22,"output":0.7999999999999999,"cache_read":0.11,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"qwen/qwen3-235b-a22b-2507","name":"Qwen: Qwen3 235B A22B Instruct 2507","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":16384,"uptime_30m":99.72096267875828,"pricing":{"input":0.22,"output":0.88,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-18","knowledge_cutoff":"2024-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1087,"win_rate":47.7,"rank":85}}},{"id":"Qwen/Qwen3-235B-A22B-Instruct-2507","name":"Qwen/Qwen3-235B-A22B-Instruct-2507","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-22","knowledge_cutoff":"2025-04","description":"Efficient multilingual, Mixture-of-Experts, instruction-tuned model, optimized for logical reasoning.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"Qwen/Qwen3-235B-A22B-Thinking-2507","name":"Qwen/Qwen3-235B-A22B-Thinking-2507","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.22999999999999998,"output":2.3,"cache_read":0.20000000059999998,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-25","knowledge_cutoff":"2025-04","description":"High-performance Mixture-of-Experts model optimized for structured reasoning, math, and long-form generation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":19.6,"coding_index":22.1,"agentic_index":3.8,"design_arena_best":{"category":"website","elo":1077,"win_rate":42.1,"rank":92}}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.22999999999999998,"output":2.3,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-25","knowledge_cutoff":"2025-04","description":"High-performance Mixture-of-Experts model optimized for structured reasoning, math, and long-form generation.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":19.6,"coding_index":22.1,"agentic_index":3.8,"design_arena_best":{"category":"website","elo":1077,"win_rate":42.1,"rank":92}}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.3,"output":3,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-235b-a22b-thinking-2507","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-07-25","knowledge_cutoff":"2025-04","description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":19.6,"coding_index":22.1,"agentic_index":3.8,"design_arena_best":{"category":"website","elo":1077,"win_rate":42.1,"rank":92}}},{"id":"qwen/qwen3-235b-a22b-thinking-2507","name":"Qwen: Qwen3 235B A22B Thinking 2507","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.44999999999999996,"output":3.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"qwen3-235b-a22b-thinking-2507","doc_url":"https://docs.venice.ai","confidence":"high","source":"models.dev","release_date":"2025-04-29","knowledge_cutoff":null,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":19.6,"coding_index":22.1,"agentic_index":3.8,"design_arena_best":{"category":"website","elo":1077,"win_rate":42.1,"rank":92}}},{"id":"Qwen/Qwen3-30B-A3B","name":"Qwen/Qwen3-30B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.12000000000000001,"output":0.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":997,"win_rate":39,"rank":97}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.13,"output":0.52,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":997,"win_rate":39,"rank":97}}},{"id":"qwen/qwen3-30b-a3b","name":"Qwen: Qwen3 30B A3B","provider":"nextbit","provider_display":"NextBit","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.14,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":997,"win_rate":39,"rank":97}}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.55,"context_length":128000,"max_completion_tokens":32000,"uptime_30m":99.6353973550859,"pricing":{"input":0.04815,"output":0.19305,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-29","knowledge_cutoff":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.18419423619231,"pricing":{"input":0.09,"output":0.3,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-29","knowledge_cutoff":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":8192,"uptime_30m":96.02854483400559,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":0.125},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"Qwen/Qwen3-30B-A3B-Instruct-2507","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.58806926539019,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-29","knowledge_cutoff":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.96282988477265,"pricing":{"input":0.13,"output":0.52,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-29","knowledge_cutoff":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3-30b-a3b-instruct-2507","name":"Qwen: Qwen3 30B A3B Instruct 2507","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":32000,"uptime_30m":null,"pricing":{"input":0.15,"output":0.55,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-29","knowledge_cutoff":null,"description":"Qwen3-30B-A3B-Instruct-2507 is a 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding.","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3-30b-a3b-thinking-2507","name":"Qwen: Qwen3 30B A3B Thinking 2507","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":81920,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-31","knowledge_cutoff":null,"description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.clarifai.com/compute/inference/"},"benchmarks":{"intelligence_index":14.4,"coding_index":12.1,"agentic_index":1.8,"design_arena_best":{"category":"dataviz","elo":955,"win_rate":33.3,"rank":102}}},{"id":"Qwen/Qwen3-32B","name":"Qwen/Qwen3-32B","provider":"deepinfra","quantization":null,"discount":0,"context_length":40960,"pricing":{"input":0.08,"output":0.28,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":40960,"max_completion_tokens":8192,"uptime_30m":99.55297273133661,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":0.01,"cache_write":0.125},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"Qwen/Qwen3-32B","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":0,"pricing":{"input":0.10400000000000001,"output":0.41600000000000004,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-32b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.81472904122278,"pricing":{"input":0.14,"output":0.5700000000000001,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-32b","name":"Qwen: Qwen3 32B","provider":"groq","provider_display":"Groq","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":40960,"uptime_30m":100,"pricing":{"input":0.29,"output":0.59,"cache_read":0.145,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"qwen/qwen3-32b","doc_url":"https://console.groq.com/docs/models","confidence":"high","source":"models.dev","release_date":"2025-06-11","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":11.5,"coding_index":15.3,"agentic_index":1.8,"design_arena_best":null}},{"id":"qwen/qwen3-8b","name":"Qwen: Qwen3 8B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.117,"output":0.45499999999999996,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-8b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":8.3,"coding_index":9,"agentic_index":1.5,"design_arena_best":null}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.22,"output":1.7999999999999998,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.47871416159862,"pricing":{"input":0.3,"output":1,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":92.96375266524521,"pricing":{"input":0.35,"output":1.5,"cache_read":0.04,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"qwen3-coder-480b-a35b-instruct-turbo","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2026-01-27","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.37578027465668,"pricing":{"input":0.38,"output":1.55,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.975,"output":4.875,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder","name":"Qwen: Qwen3 Coder 480B A35B","provider":"coreweave","provider_display":"CoreWeave","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":96.0553633217993,"pricing":{"input":1,"output":1.5,"cache_read":1,"cache_write":null},"org":"qwen","zdr":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"website","elo":1183,"win_rate":61.7,"rank":63}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":160000,"max_completion_tokens":32768,"uptime_30m":86.34466308884913,"pricing":{"input":0.07,"output":0.27,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-coder-30b-a3b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-10-09","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1113,"win_rate":54.7,"rank":82}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.30641985033478,"pricing":{"input":0.07,"output":0.28,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-31","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.clarifai.com/compute/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1113,"win_rate":54.7,"rank":82}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":0,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-31","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.clarifai.com/compute/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1113,"win_rate":54.7,"rank":82}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.2925,"output":1.4625,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-coder-30b-a3b-instruct","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-04","knowledge_cutoff":"2025-04","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1113,"win_rate":54.7,"rank":82}}},{"id":"qwen/qwen3-coder-30b-a3b-instruct","name":"Qwen: Qwen3 Coder 30B A3B Instruct","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":99.61685823754789,"pricing":{"input":0.44999999999999996,"output":1.7,"cache_read":0.09,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-31","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.clarifai.com/compute/inference/"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1113,"win_rate":54.7,"rank":82}}},{"id":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","name":"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.3,"output":1,"cache_read":0.09999999899999999,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-27","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.venice.ai"}},{"id":"qwen/qwen3-coder-flash","name":"Qwen: Qwen3 Coder Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.195,"output":0.975,"cache_read":0.039,"cache_write":0.24375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-coder-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"ionstream","provider_display":"Ionstream","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":97.61904761904762,"pricing":{"input":0.11,"output":0.7999999999999999,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.12,"output":0.7999999999999999,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0.4,"context_length":256000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":0.18,"output":0.8999999999999999,"cache_read":0.036,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.19999999999999998,"output":1.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-coder-next","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-03","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen/qwen3-coder-next","name":"Qwen: Qwen3 Coder Next","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.3,"output":1.5,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen/qwen3-coder-plus","name":"Qwen: Qwen3 Coder Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.65,"output":3.25,"cache_read":0.13,"cache_write":0.8125},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-coder-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-07-23","knowledge_cutoff":"2025-04","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"Qwen/Qwen3-Max","name":"Qwen/Qwen3-Max","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":1.2,"output":5.999999999999999,"cache_read":0.24,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-23","knowledge_cutoff":"2025-04","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"asciiart","elo":1166,"win_rate":47.2,"rank":38}}},{"id":"qwen/qwen3-max","name":"Qwen: Qwen3 Max","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.78,"output":3.9,"cache_read":0.156,"cache_write":0.975},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-max","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-09-23","knowledge_cutoff":"2025-04","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"asciiart","elo":1166,"win_rate":47.2,"rank":38}}},{"id":"Qwen/Qwen3-Max-Thinking","name":"Qwen/Qwen3-Max-Thinking","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":1.2,"output":5.999999999999999,"cache_read":0.24,"cache_write":null},"org":"qwen","benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"asciiart","elo":1166,"win_rate":47.2,"rank":38}}},{"id":"qwen/qwen3-max-thinking","name":"Qwen: Qwen3 Max Thinking","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.78,"output":3.9,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"asciiart","elo":1166,"win_rate":47.2,"rank":38}}},{"id":"Qwen/Qwen3-Next-80B-A3B-Instruct","name":"Qwen/Qwen3-Next-80B-A3B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.09,"output":1.1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-10","knowledge_cutoff":"2024-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.0975,"output":0.78,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-next-80b-a3b-instruct","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.95719178082192,"pricing":{"input":0.09999999999999999,"output":1.1,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-10","knowledge_cutoff":"2024-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.15,"output":1.2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-10","knowledge_cutoff":"2024-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-instruct","name":"Qwen: Qwen3 Next 80B A3B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":95.1923076923077,"pricing":{"input":0.15,"output":1.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-next-80b-a3b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-10","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.15,"output":1.2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.15,"output":1.2,"cache_read":0.015,"cache_write":0.18},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.tokenfactory.nebius.com/v1","model_id":"Qwen/Qwen3-Next-80B-A3B-Thinking","doc_url":"https://docs.tokenfactory.nebius.com/","confidence":"high","source":"models.dev","release_date":"2026-01-28","knowledge_cutoff":"2025-12","description":"Qwen reasoning model for deliberate problem solving, math, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen/qwen3-next-80b-a3b-thinking","name":"Qwen: Qwen3 Next 80B A3B Thinking","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.15,"output":1.2,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3-next-80b-a3b-thinking","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2025-09","knowledge_cutoff":"2025-04","description":"Efficient Qwen thinking model for local reasoning, math, and coding agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"Qwen/Qwen3-VL-235B-A22B-Instruct","name":"Qwen/Qwen3-VL-235B-A22B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":0.8799999999999999,"cache_read":0.11000000000000001,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":95.8219800181653,"pricing":{"input":0.21,"output":1.9,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":95.49316586627262,"pricing":{"input":0.21,"output":1.9,"cache_read":0.09999999999999999,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.26,"output":1.04,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-235b-a22b-instruct","name":"Qwen: Qwen3 VL 235B A22B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":93.25236167341431,"pricing":{"input":0.3,"output":1.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-vl-235b-a22b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.39999999999999997,"output":4,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-235b-a22b-thinking","name":"Qwen: Qwen3 VL 235B A22B Thinking","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.98,"output":3.95,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-vl-235b-a22b-thinking","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-24","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":false,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen/Qwen3-VL-30B-A3B-Instruct","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.15,"output":0.6,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"Qwen/Qwen3-VL-30B-A3B-Instruct","name":"Qwen3-VL 30B A3B Instruct","provider":"sference","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.4,"output":2,"cache_read":0.1,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.13,"output":0.52,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":98.762233736327,"pricing":{"input":0.19999999999999998,"output":0.7,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3-vl-30b-a3b-instruct","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen3-vl-30b-a3b-instruct","name":"Qwen: Qwen3 VL 30B A3B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":89.96372430471584,"pricing":{"input":0.29,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-30b-a3b-thinking","name":"Qwen: Qwen3 VL 30B A3B Thinking","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.29,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-11","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-32b-instruct","name":"Qwen: Qwen3 VL 32B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.9950768018905,"pricing":{"input":0.10400000000000001,"output":0.41600000000000004,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.987013549197,"pricing":{"input":0.117,"output":0.45499999999999996,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-17","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen: Qwen3 VL 8B Instruct","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.52807928268051,"pricing":{"input":0.25,"output":0.75,"cache_read":0.12,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-17","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":false,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"}},{"id":"qwen/qwen3-vl-8b-thinking","name":"Qwen: Qwen3 VL 8B Thinking","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.18,"output":2.0999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true},{"id":"Qwen/Qwen3.5-122B-A10B","name":"Qwen/Qwen3.5-122B-A10B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.29,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7,"design_arena_best":null}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.26,"output":2.08,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7,"design_arena_best":null}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.26,"output":2.08,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-122b-a10b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7,"design_arena_best":null}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":98.98989898989899,"pricing":{"input":0.3,"output":2.4,"cache_read":0.3,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"},"benchmarks":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7,"design_arena_best":null}},{"id":"qwen/qwen3.5-122b-a10b","name":"Qwen: Qwen3.5-122B-A10B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.82898674647285,"pricing":{"input":0.39999999999999997,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-122b-a10b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-26","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":32.3,"coding_index":45.7,"agentic_index":20.7,"design_arena_best":null}},{"id":"Qwen/Qwen3.5-27B","name":"Qwen/Qwen3.5-27B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.26,"output":2.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.8989388580091,"pricing":{"input":0.195,"output":1.56,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-27b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":98.09688581314879,"pricing":{"input":0.25,"output":2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.8158379373849,"pricing":{"input":0.27,"output":2.16,"cache_read":0.27,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.52267303102626,"pricing":{"input":0.3,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-27b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-26","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"qwen/qwen3.5-27b","name":"Qwen: Qwen3.5-27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":98.11320754716981,"pricing":{"input":0.3,"output":2.4,"cache_read":0.15,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"}},{"id":"Qwen/Qwen3.5-35B-A3B","name":"Qwen/Qwen3.5-35B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.14,"output":1,"cache_read":0.05000000040000001,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.25314465408806,"pricing":{"input":0.14,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":66.9172932330827,"pricing":{"input":0.15,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.1625,"output":1.3,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-35b-a3b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-23","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.22499999999999998,"output":1.7999999999999998,"cache_read":0.22499999999999998,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"nextbit","provider_display":"NextBit","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.22999999999999998,"output":1.5999999999999999,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":null,"pricing":{"input":0.24,"output":1.7999999999999998,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.25,"output":1.25,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"qwen/qwen3.5-35b-a3b","name":"Qwen: Qwen3.5-35B-A3B","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.3125,"output":1.25,"cache_read":0.15625,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-24","knowledge_cutoff":null,"description":"Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":24,"coding_index":37,"agentic_index":11.8,"design_arena_best":null}},{"id":"Qwen/Qwen3.5-397B-A17B","name":"Qwen/Qwen3.5-397B-A17B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.45,"output":2.9999999999999996,"cache_read":0.22000000050000001,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":81920,"uptime_30m":null,"pricing":{"input":0.385,"output":2.4499999999999997,"cache_read":0.111,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"qwen3.5-397b-a17b","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.39,"output":2.34,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-397b-a17b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":98.92739273927393,"pricing":{"input":0.44999999999999996,"output":3,"cache_read":0.22499999999999998,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"Qwen/Qwen3.5-397B-A17B-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.39595288432498,"pricing":{"input":0.5,"output":3.5999999999999996,"cache_read":0.3,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.43820224719101,"pricing":{"input":0.55,"output":3.5,"cache_read":0.55,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.62154942119324,"pricing":{"input":0.55,"output":3.5,"cache_read":0.22499999999999998,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"qwen/qwen3.5-397b-a17b","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-17","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"streamlake","provider_display":"StreamLake","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":64000,"uptime_30m":null,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":0.12,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":null,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen/qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"venice","provider_display":"Venice","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":32768,"uptime_30m":96.89119170984456,"pricing":{"input":0.75,"output":4.5,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-07-15","knowledge_cutoff":"2025-07","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.tokenfactory.nebius.com/"},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"Qwen/Qwen3.5-9B","name":"Qwen/Qwen3.5-9B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.15,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-13","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":96.56160458452722,"pricing":{"input":0.09999999999999999,"output":0.15,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-13","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":32768,"uptime_30m":99.97262523952915,"pricing":{"input":0.09999999999999999,"output":0.15,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-13","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-03-13","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen/qwen3.5-9b","name":"Qwen: Qwen3.5-9B","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.93714644877436,"pricing":{"input":0.16999999999999998,"output":0.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev":{"base_url":null,"model_id":"Qwen/Qwen3.5-9B","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-03-03","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen/qwen3.5-flash-02-23","name":"Qwen: Qwen3.5-Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.065,"output":0.26,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true},{"id":"qwen/qwen3.5-plus-02-15","name":"Qwen: Qwen3.5 Plus 2026-02-15","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.26,"output":1.56,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1214,"win_rate":52.2,"rank":42}}},{"id":"qwen/qwen3.5-plus-20260420","name":"Qwen: Qwen3.5 Plus 2026-04-20","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.3,"output":1.7999999999999998,"cache_read":null,"cache_write":0.375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.5-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-02-16","knowledge_cutoff":"2025-04","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false}},{"id":"Qwen/Qwen3.6-27B","name":"Qwen/Qwen3.6-27B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.32,"output":3.2,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":0.28,"output":1.99,"cache_read":0.14,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":98.67416633186018,"pricing":{"input":0.28900000000000003,"output":2.4,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.24558587479936,"pricing":{"input":0.3,"output":2,"cache_read":0.15,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"Qwen/Qwen3.6-27B-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":91.47794994040524,"pricing":{"input":0.3,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262140,"uptime_30m":98.79581151832461,"pricing":{"input":0.32,"output":2.7,"cache_read":0.15,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":99.46091644204851,"pricing":{"input":0.325,"output":3.25,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":99.4768962510898,"pricing":{"input":0.44999999999999996,"output":2.7,"cache_read":null,"cache_write":null},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-27b","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen/qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.6,"output":3.5999999999999996,"cache_read":0.12,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen/Qwen3.6-35B-A3B","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1,"output":0.95,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"Qwen/Qwen3.6-35B-A3B","name":"Qwen3.6 35B","provider":"sference","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":1.25,"cache_read":0.05,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":65536,"uptime_30m":99.38574938574939,"pricing":{"input":0.09999999999999999,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.69205160216397,"pricing":{"input":0.14,"output":1,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.56008146639512,"pricing":{"input":0.15,"output":1,"cache_read":0.049999999999999996,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":98.7012987012987,"pricing":{"input":0.186,"output":1.11375,"cache_read":0.186,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.63235294117648,"pricing":{"input":0.19999999999999998,"output":1.27,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":97.54738015607582,"pricing":{"input":0.19999999999999998,"output":1.5999999999999999,"cache_read":null,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":0.25,"output":1.25,"cache_read":0.25,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-35b-a3b","name":"Qwen: Qwen3.6 35B A3B","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":262140,"max_completion_tokens":262140,"uptime_30m":100,"pricing":{"input":0.28500000000000003,"output":2.4,"cache_read":0.14250000000000002,"cache_write":null},"org":"qwen","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-15","knowledge_cutoff":null,"description":"Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":31.6,"coding_index":41.9,"agentic_index":21.4,"design_arena_best":null}},{"id":"qwen/qwen3.6-flash","name":"Qwen: Qwen3.6 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.1875,"output":1.125,"cache_read":null,"cache_write":0.234375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-flash","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-27","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false}},{"id":"qwen/qwen3.6-max-preview","name":"Qwen: Qwen3.6 Max Preview","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":1.0270000000000001,"output":6.162,"cache_read":0.13,"cache_write":1.28375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-max-preview","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-20","knowledge_cutoff":"2025-04","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"qwen/qwen3.6-plus","name":"Qwen: Qwen3.6 Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.325,"output":1.95,"cache_read":0.05,"cache_write":0.40625},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.6-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-04","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":39.6,"coding_index":54.5,"agentic_index":27.6,"design_arena_best":{"category":"uicomponent","elo":1273,"win_rate":52.7,"rank":27}}},{"id":"qwen/qwen3.7-flash","name":"Qwen: Qwen3.7 Flash","provider":"alibaba","provider_display":"Alibaba","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":99.98339835643729,"pricing":{"input":0.03,"output":0.13,"cache_read":0.006,"cache_write":0.038000000000000006},"org":"qwen","subscription":true},{"id":"Qwen/Qwen3.7-Max","name":"Qwen/Qwen3.7-Max","provider":"deepinfra","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":46,"coding_index":66,"agentic_index":30.6,"design_arena_best":{"category":"gamedev","elo":1323,"win_rate":59.1,"rank":11}}},{"id":"qwen/qwen3.7-max","name":"Qwen: Qwen3.7 Max","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":1.475,"output":4.425,"cache_read":0.295,"cache_write":1.84375},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-max","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":46,"coding_index":66,"agentic_index":30.6,"design_arena_best":{"category":"gamedev","elo":1323,"win_rate":59.1,"rank":11}}},{"id":"qwen/qwen3.7-plus","name":"Qwen: Qwen3.7 Plus","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":99.99800820619049,"pricing":{"input":0.32,"output":1.28,"cache_read":0.064,"cache_write":0.39999999999999997},"org":"qwen","subscription":true,"modelsdev":{"base_url":"https://dashscope-intl.aliyuncs.com/compatible-mode/v1","model_id":"qwen3.7-plus","doc_url":"https://www.alibabacloud.com/help/en/model-studio/models","confidence":"high","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":"2025-04","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":39,"coding_index":55.9,"agentic_index":20.8,"design_arena_best":{"category":"website","elo":1299,"win_rate":53.2,"rank":15}}},{"id":"qwen3-coder-480b-a35b-instruct-int4-mixed-ar","name":"Qwen3 Coder 480B A35B Instruct INT4 Mixed AR","provider":"hyper","quantization":null,"discount":0,"context_length":106000,"pricing":{"input":0.569,"output":2.135,"cache_read":0,"cache_write":0.2845},"org":"hyper","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-15","knowledge_cutoff":"2024-12","description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"}},{"id":"qwen3-coder-next","name":"Qwen3 Coder Next","provider":"ember","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.108,"output":0.675,"cache_read":0.06,"cache_write":null},"org":"qwen","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-06","knowledge_cutoff":null,"description":"Qwen coding model for software agents, repository edits, and code reasoning","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html"},"benchmarks":{"intelligence_index":21.1,"coding_index":36.2,"agentic_index":8.8,"design_arena_best":null}},{"id":"qwen3-next-80b-a3b-instruct","name":"Qwen3 Next 80B A3B Instruct","provider":"hyper","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.1175,"output":1.136,"cache_read":0,"cache_write":0.05875},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-01-10","knowledge_cutoff":"2024-12","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":16.7,"coding_index":17.4,"agentic_index":2.1,"design_arena_best":null}},{"id":"qwen3.5-397b-a17b","name":"Qwen: Qwen3.5 397B A17B","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.35,"output":1.75,"cache_read":0.07,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"qwen3.5-397b-a17b","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-02-15","knowledge_cutoff":null,"description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":48.2,"agentic_index":19.8,"design_arena_best":{"category":"3d","elo":1218,"win_rate":56.7,"rank":41}}},{"id":"qwen3.5-9b","name":"Qwen: Qwen3.5 9B","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.04,"output":0.15,"cache_read":0.008,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"qwen3.5-9b","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-03-13","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":21.4,"coding_index":28.7,"agentic_index":7.4,"design_arena_best":null}},{"id":"qwen3.6-27b","name":"Qwen: Qwen3.6 27B","provider":"crof","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":1.5,"cache_read":0.04,"cache_write":null},"org":"qwen","zdr":true,"max_completion_tokens":262144,"modelsdev":{"base_url":"https://crof.ai/v1","model_id":"qwen3.6-27b","doc_url":"https://crof.ai/docs","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.1,"coding_index":53.7,"agentic_index":27,"design_arena_best":null}},{"id":"qwen3.6-flash","name":"Qwen3.6-Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1,"output":4,"cache_read":0.1,"cache_write":1.25},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-27","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"}},{"id":"qwen3.6-max","name":"Qwen3.6-Max","provider":"hyper","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":2,"output":12,"cache_read":0.2,"cache_write":2.5},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-20","knowledge_cutoff":"2025-04","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://www.alibabacloud.com/help/en/model-studio/models"}},{"id":"qwen3.6-plus","name":"Qwen3.6-Plus","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":6,"cache_read":0.2,"cache_write":2.5},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-02","knowledge_cutoff":"2025-04","description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":39.6,"coding_index":54.5,"agentic_index":27.6,"design_arena_best":{"category":"uicomponent","elo":1273,"win_rate":52.7,"rank":27}}},{"id":"qwen3.6-plus","name":"Qwen3.6 Plus (≤256K)","provider":"opencode","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.5,"output":3,"cache_read":0.05,"cache_write":0.625},"org":"qwen","subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"qwen3.6-plus","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-04-02","knowledge_cutoff":"2025-04","description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":39.6,"coding_index":54.5,"agentic_index":27.6,"design_arena_best":{"category":"uicomponent","elo":1273,"win_rate":52.7,"rank":27}}},{"id":"qwen3.6-plus-long","name":"Qwen3.6 Plus (>256K)","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2,"output":6,"cache_read":0.2,"cache_write":null},"org":"qwen","subscription":true},{"id":"qwen3.7-flash","name":"Qwen3.7-Flash","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":0.2,"output":0.8,"cache_read":0.04,"cache_write":0},"org":"qwen","subscription":true},{"id":"qwen3.7-max","name":"Qwen3.7-Max","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":0},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":46,"coding_index":66,"agentic_index":30.6,"design_arena_best":{"category":"gamedev","elo":1323,"win_rate":59.1,"rank":11}}},{"id":"qwen3.7-max","name":"Qwen3.7 Max","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":2.5,"output":7.5,"cache_read":0.5,"cache_write":3.125},"org":"qwen","subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"qwen3.7-max","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-05-21","knowledge_cutoff":null,"description":"Flagship model for demanding analysis, coding, and production agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":46,"coding_index":66,"agentic_index":30.6,"design_arena_best":{"category":"gamedev","elo":1323,"win_rate":59.1,"rank":11}}},{"id":"qwen3.7-plus","name":"Qwen3.7-Plus","provider":"hyper","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.2,"output":4.8,"cache_read":0.24,"cache_write":0},"org":"qwen","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-12","knowledge_cutoff":null,"description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":39,"coding_index":55.9,"agentic_index":20.8,"design_arena_best":{"category":"website","elo":1299,"win_rate":53.2,"rank":15}}},{"id":"qwen3.7-plus","name":"Qwen3.7 Plus (≤256K)","provider":"opencode","quantization":null,"discount":0,"context_length":256000,"pricing":{"input":0.4,"output":1.6,"cache_read":0.04,"cache_write":0.5},"org":"qwen","subscription":true,"max_completion_tokens":65536,"modelsdev":{"base_url":"https://opencode.ai/zen/go/v1","model_id":"qwen3.7-plus","doc_url":"https://opencode.ai/docs/zen","confidence":"high","source":"models.dev","release_date":"2026-06-02","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":39,"coding_index":55.9,"agentic_index":20.8,"design_arena_best":{"category":"website","elo":1299,"win_rate":53.2,"rank":15}}},{"id":"qwen3.7-plus-long","name":"Qwen3.7 Plus (>256K)","provider":"opencode","quantization":null,"discount":0,"context_length":1000000,"pricing":{"input":1.2,"output":4.8,"cache_read":0.12,"cache_write":null},"org":"qwen","subscription":true},{"id":"rekaai/reka-edge","name":"Reka Edge","provider":"reka","provider_display":"Reka","quantization":"bf16","discount":0,"context_length":16384,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.09999999999999999,"output":0.09999999999999999,"cache_read":null,"cache_write":null},"org":"rekaai","zdr":true},{"id":"rekaai/reka-flash-3","name":"Reka Flash 3","provider":"reka","provider_display":"Reka","quantization":"fp8","discount":0,"context_length":65536,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":0.09999999999999999,"output":0.19999999999999998,"cache_read":null,"cache_write":null},"org":"rekaai","zdr":true},{"id":"relace/relace-apply-3","name":"Relace: Relace Apply 3","provider":"relace","provider_display":"Relace","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":0.85,"output":1.25,"cache_read":null,"cache_write":null},"org":"relace","zdr":true},{"id":"relace/relace-search","name":"Relace: Relace Search","provider":"relace","provider_display":"Relace","quantization":"bf16","discount":0,"context_length":256000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":1,"output":3,"cache_read":null,"cache_write":null},"org":"relace","zdr":true},{"id":"sakana/fugu-ultra","name":"Sakana: Fugu Ultra","provider":"sakana","provider_display":"Sakana AI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":128000,"uptime_30m":null,"pricing":{"input":5,"output":30,"cache_read":0.5,"cache_write":null},"org":"sakana","modelsdev":{"base_url":"https://api.sakana.ai/v1","model_id":"fugu-ultra-20260615","doc_url":"https://console.sakana.ai/models","confidence":"high","source":"models.dev","release_date":"2026-06-15","knowledge_cutoff":null,"description":"Quality-first multi-agent model for hard research, analysis, and competitions","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":false},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":false}},{"id":"Sao10K/L3-8B-Lunaris-v1-Turbo","name":"Sao10K/L3-8B-Lunaris-v1-Turbo","provider":"deepinfra","quantization":null,"discount":0,"context_length":8192,"pricing":{"input":0.04,"output":0.05,"cache_read":null,"cache_write":null},"org":"sao10k"},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":8192,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":0.04,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true},{"id":"sao10k/l3-lunaris-8b","name":"Sao10K: Llama 3 8B Lunaris","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":8192,"max_completion_tokens":8192,"uptime_30m":100,"pricing":{"input":0.049999999999999996,"output":0.049999999999999996,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"sao10K/l3-8b-lunaris","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2024-11-28","knowledge_cutoff":null,"description":"Open-weight instruction model for adaptable chat and self-hosted production workloads","capabilities":{"reasoning":false,"tool_call":false,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true}},{"id":"Sao10K/L3.1-70B-Euryale-v2.2","name":"Sao10K/L3.1-70B-Euryale-v2.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":131072,"pricing":{"input":0.85,"output":0.85,"cache_read":null,"cache_write":null},"org":"sao10k"},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","provider":"deepinfra","provider_display":"DeepInfra","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":100,"pricing":{"input":0.85,"output":0.85,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true},{"id":"sao10k/l3.1-euryale-70b","name":"Sao10K: Llama 3.1 Euryale 70B v2.2","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.02,"context_length":8192,"max_completion_tokens":8192,"uptime_30m":null,"pricing":{"input":1.4504,"output":1.4504,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true},{"id":"sao10k/l3.3-euryale-70b","name":"Sao10K: Llama 3.3 Euryale 70B","provider":"nextbit","provider_display":"NextBit","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":16384,"uptime_30m":98.67674858223062,"pricing":{"input":0.65,"output":0.75,"cache_read":null,"cache_write":null},"org":"sao10k","zdr":true},{"id":"stepfun-ai/Step-3.7-Flash","name":"stepfun-ai/Step-3.7-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.2,"output":1.15,"cache_read":0.04000000000000001,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-29","knowledge_cutoff":"2026-03-01","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://platform.stepfun.com/docs/zh/overview/concept"},"benchmarks":{"intelligence_index":30.3,"coding_index":39.6,"agentic_index":21.5,"design_arena_best":{"category":"website","elo":1213,"win_rate":46.3,"rank":46}}},{"id":"stepfun/step-3.5-flash","name":"StepFun: Step 3.5 Flash","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.09999999999999999,"output":0.3,"cache_read":null,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-29","knowledge_cutoff":"2025-01","description":"StepFun flash lane for quick multimodal reasoning and coding assistance","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://platform.stepfun.com/docs/zh/overview/concept"}},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","provider":"stepfun","provider_display":"StepFun","quantization":"fp8","discount":0,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":99.89440337909187,"pricing":{"input":0.19999999999999998,"output":1.15,"cache_read":0.04,"cache_write":null},"org":"stepfun","modelsdev":{"base_url":"https://api.stepfun.com/v1","model_id":"step-3.7-flash","doc_url":"https://platform.stepfun.com/docs/zh/overview/concept","confidence":"high","source":"models.dev","release_date":"2026-05-29","knowledge_cutoff":"2026-03-01","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":30.3,"coding_index":39.6,"agentic_index":21.5,"design_arena_best":{"category":"website","elo":1213,"win_rate":46.3,"rank":46}}},{"id":"stepfun/step-3.7-flash","name":"StepFun: Step 3.7 Flash","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":256000,"uptime_30m":99.29824561403508,"pricing":{"input":0.19999999999999998,"output":1.15,"cache_read":0.04,"cache_write":null},"org":"stepfun","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-05-29","knowledge_cutoff":"2026-03-01","description":"Newer StepFun flash model for faster agents, coding, and multimodal prompts","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true,"doc_url":"https://platform.stepfun.com/docs/zh/overview/concept"},"benchmarks":{"intelligence_index":30.3,"coding_index":39.6,"agentic_index":21.5,"design_arena_best":{"category":"website","elo":1213,"win_rate":46.3,"rank":46}}},{"id":"syn:large:text","name":"syn:large:text","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"z-ai","pricing":{"input":1,"output":3,"cache_read":0.2,"cache_write":null},"zdr":true,"subscription":true},{"id":"syn:large:vision","name":"syn:large:vision","provider":"synthetic","quantization":null,"discount":0,"context_length":524288,"org":"moonshot","pricing":{"input":3,"output":15,"cache_read":0.6000000000000001,"cache_write":null},"zdr":true,"subscription":true},{"id":"syn:small:text","name":"syn:small:text","provider":"synthetic","quantization":null,"discount":0,"context_length":196608,"org":"z-ai","pricing":{"input":0.09999999999999999,"output":0.5,"cache_read":0.02,"cache_write":null},"zdr":true,"subscription":true},{"id":"syn:small:vision","name":"syn:small:vision","provider":"synthetic","quantization":null,"discount":0,"context_length":262144,"org":"qwen","pricing":{"input":0.44999999999999996,"output":3.5999999999999996,"cache_read":0.09,"cache_write":null},"zdr":true,"subscription":true},{"id":"tencent/hunyuan-a13b-instruct","name":"Tencent: Hunyuan A13B Instruct","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":null,"pricing":{"input":0.14,"output":0.5700000000000001,"cache_read":null,"cache_write":null},"org":"tencent","zdr":true},{"id":"tencent/Hy3","name":"tencent/Hy3","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.14,"output":0.58,"cache_read":0.035,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":41.2,"coding_index":58.8,"agentic_index":30.7,"design_arena_best":null}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0.08,"context_length":262144,"max_completion_tokens":null,"uptime_30m":95.97457627118644,"pricing":{"input":0.1288,"output":0.5336,"cache_read":0.0322,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":41.2,"coding_index":58.8,"agentic_index":30.7,"design_arena_best":null}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"tencent","provider_display":"Tencent","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":128000,"uptime_30m":99.90900818926298,"pricing":{"input":0.13199999999999998,"output":0.5279999999999999,"cache_read":0.032999999999999995,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":41.2,"coding_index":58.8,"agentic_index":30.7,"design_arena_best":null}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.50124688279301,"pricing":{"input":0.14,"output":0.58,"cache_read":0.035,"cache_write":null},"org":"tencent","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":41.2,"coding_index":58.8,"agentic_index":30.7,"design_arena_best":null}},{"id":"tencent/hy3","name":"Tencent: Hy3","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":0.19999999999999998,"output":0.7999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"tencent","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-06","knowledge_cutoff":null,"description":"Tencent Hy reasoning model for coding, instruction following, and agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":41.2,"coding_index":58.8,"agentic_index":30.7,"design_arena_best":null}},{"id":"thedrummer/cydonia-24b-v4.1","name":"TheDrummer: Cydonia 24B V4.1","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.90671641791045,"pricing":{"input":0.3,"output":0.5,"cache_read":0.15,"cache_write":null},"org":"thedrummer","zdr":true},{"id":"thedrummer/rocinante-12b","name":"TheDrummer: Rocinante 12B","provider":"parasail","provider_display":"Parasail","quantization":"bf16","discount":0,"context_length":65536,"max_completion_tokens":65536,"uptime_30m":100,"pricing":{"input":0.25,"output":0.5,"cache_read":null,"cache_write":null},"org":"thedrummer","zdr":true},{"id":"thedrummer/skyfall-36b-v2","name":"TheDrummer: Skyfall 36B V2","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.55,"output":0.7999999999999999,"cache_read":0.25,"cache_write":null},"org":"thedrummer","zdr":true},{"id":"thedrummer/unslopnemo-12b","name":"TheDrummer: UnslopNemo 12B","provider":"nextbit","provider_display":"NextBit","quantization":"fp8","discount":0,"context_length":32768,"max_completion_tokens":32768,"uptime_30m":null,"pricing":{"input":0.39999999999999997,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"thedrummer","zdr":true},{"id":"thinkingmachines/Inkling","name":"thinkingmachines/Inkling","provider":"deepinfra","quantization":null,"discount":0,"context_length":524288,"pricing":{"input":1,"output":4.05,"cache_read":0.17,"cache_write":null},"org":"thinkingmachines","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":40.7,"coding_index":52.1,"agentic_index":32.3,"design_arena_best":null}},{"id":"thinkingmachines/inkling","name":"Thinking Machines: Inkling","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":32768,"uptime_30m":100,"pricing":{"input":1,"output":4.05,"cache_read":0.16999999999999998,"cache_write":null},"org":"thinkingmachines","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"thinkingmachines/inkling","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Multimodal reasoning model for visual analysis, planning, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.7,"coding_index":52.1,"agentic_index":32.3,"design_arena_best":null}},{"id":"thinkingmachines/inkling","name":"Thinking Machines: Inkling","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":524288,"max_completion_tokens":131072,"uptime_30m":98.05060141020323,"pricing":{"input":1,"output":4.05,"cache_read":0.16999999999999998,"cache_write":null},"org":"thinkingmachines","zdr":true,"modelsdev":{"base_url":null,"model_id":"thinkingmachines/Inkling","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-07-15","knowledge_cutoff":null,"description":"Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.7,"coding_index":52.1,"agentic_index":32.3,"design_arena_best":null}},{"id":"umans-flash","name":"Umans Flash","provider":"umans","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.15,"output":1,"cache_read":0.05,"cache_write":null},"org":"umans","zdr":true},{"id":"umans-glm-5.2","name":"Umans GLM 5.2","provider":"umans","quantization":null,"discount":0,"context_length":405504,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"umans","zdr":true,"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"umans-kimi-k2.7","name":"Umans Kimi K2.7 Code","provider":"umans","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.95,"output":4,"cache_read":0.19,"cache_write":null},"org":"umans","zdr":true},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"mancer-2","provider_display":"Mancer 2","quantization":"fp8","discount":0,"context_length":6144,"max_completion_tokens":2048,"uptime_30m":null,"pricing":{"input":0.44999999999999996,"output":0.65,"cache_read":null,"cache_write":null},"org":"undi95","zdr":true},{"id":"undi95/remm-slerp-l2-13b","name":"ReMM SLERP 13B","provider":"nextbit","provider_display":"NextBit","quantization":"bf16","discount":0,"context_length":6144,"max_completion_tokens":4096,"uptime_30m":null,"pricing":{"input":0.44999999999999996,"output":0.65,"cache_read":null,"cache_write":null},"org":"undi95","zdr":true},{"id":"upstage/solar-pro-3","name":"Upstage: Solar Pro 3","provider":"upstage","provider_display":"Upstage","quantization":"unknown","discount":0,"context_length":128000,"max_completion_tokens":null,"uptime_30m":null,"pricing":{"input":0.15,"output":0.6,"cache_read":0.015,"cache_write":null},"org":"upstage","benchmarks":{"intelligence_index":14.1,"coding_index":16.2,"agentic_index":2.7,"design_arena_best":null}},{"id":"writer/palmyra-x5","name":"Writer: Palmyra X5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":1040000,"max_completion_tokens":8192,"uptime_30m":null,"pricing":{"input":0.6,"output":6,"cache_read":null,"cache_write":null},"org":"writer","zdr":true,"modelsdev":{"base_url":null,"model_id":"writer.palmyra-x5-v1:0","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2025-04-28","knowledge_cutoff":null,"description":"Reasoning model for deliberate analysis, multi-step problem solving, and tool use","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false}},{"id":"x-ai/grok-4.20","name":"xAI: Grok 4.20","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":null,"uptime_30m":99.99036237471087,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1253,"win_rate":53.5,"rank":33}}},{"id":"x-ai/grok-4.20-multi-agent","name":"xAI: Grok 4.20 Multi-Agent","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":2000000,"max_completion_tokens":30000,"uptime_30m":86.4406779661017,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.20-multi-agent-0309","doc_url":"https://docs.x.ai/docs/models","confidence":"medium","source":"models.dev","release_date":"2026-03-09","knowledge_cutoff":null,"description":"Grok model for agentic tool use, reasoning, coding, and live assistance","capabilities":{"reasoning":true,"tool_call":false,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false}},{"id":"x-ai/grok-4.3","name":"xAI: Grok 4.3","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":1000000,"max_completion_tokens":30000,"uptime_30m":100,"pricing":{"input":1.25,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.3","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-17","knowledge_cutoff":null,"description":"xAI's Grok for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":37.6,"coding_index":42.2,"agentic_index":24.1,"design_arena_best":{"category":"gamedev","elo":1233,"win_rate":49.4,"rank":38}}},{"id":"x-ai/grok-4.5","name":"xAI: Grok 4.5","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":500000,"max_completion_tokens":500000,"uptime_30m":99.85898014440433,"pricing":{"input":2,"output":6,"cache_read":0.3,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-4.5","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-07-08","knowledge_cutoff":null,"description":"xAI's latest Grok for chat, coding, agentic tools, and lower hallucination risk","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":53.8,"coding_index":72.4,"agentic_index":45.7,"design_arena_best":{"category":"gamedev","elo":1330,"win_rate":54.2,"rank":8}}},{"id":"x-ai/grok-build-0.1","name":"xAI: Grok Build 0.1","provider":"xai","provider_display":"xAI","quantization":"unknown","discount":0,"context_length":256000,"max_completion_tokens":256000,"uptime_30m":100,"pricing":{"input":1,"output":2,"cache_read":0.19999999999999998,"cache_write":null},"org":"xai","zdr":true,"subscription":true,"modelsdev":{"base_url":null,"model_id":"grok-build-0.1","doc_url":"https://docs.x.ai/docs/models","confidence":"high","source":"models.dev","release_date":"2026-04-16","knowledge_cutoff":null,"description":"Fast Grok coding model tuned for agentic engineering and iterative edits","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","image","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":39.8,"coding_index":51.5,"agentic_index":28,"design_arena_best":null}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.2,"context_length":1050000,"max_completion_tokens":null,"uptime_30m":85.57046979865773,"pricing":{"input":0.112,"output":0.224,"cache_read":0.0024,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":90.1595744680851,"pricing":{"input":0.13,"output":0.26,"cache_read":0.065,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"xiaomi","provider_display":"Xiaomi","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.07949137998284,"pricing":{"input":0.14,"output":0.28,"cache_read":0.0028,"cache_write":null},"org":"xiaomi","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":94.45544554455445,"pricing":{"input":0.14,"output":0.28,"cache_read":0.049999999999999996,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":65536,"uptime_30m":95.60615779345734,"pricing":{"input":0.14,"output":0.28,"cache_read":0.049999999999999996,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5","name":"Xiaomi: MiMo-V2.5","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":98.24598478444632,"pricing":{"input":0.16799999999999998,"output":0.33599999999999997,"cache_read":0.0034,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"xiaomimimo/mimo-v2.5-pro","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"medium","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"gmicloud","provider_display":"GMICloud","quantization":"bf16","discount":0.2,"context_length":1050000,"max_completion_tokens":null,"uptime_30m":95.35864978902954,"pricing":{"input":0.348,"output":0.696,"cache_read":0.0032,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"xiaomi","provider_display":"Xiaomi","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.93903678114205,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":1024000,"max_completion_tokens":131072,"uptime_30m":99.16943521594685,"pricing":{"input":0.435,"output":0.87,"cache_read":0.0036,"cache_write":null},"org":"xiaomi","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"novita","provider_display":"Novita","quantization":"unknown","discount":0.08,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.9723909442297,"pricing":{"input":0.48024,"output":0.96048,"cache_read":0.003956,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"xiaomimimo/mimo-v2.5-pro","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"xiaomi/mimo-v2.5-pro","name":"Xiaomi: MiMo-V2.5-Pro","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":0.6,"output":3,"cache_read":0.16,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"XiaomiMiMo/MiMo-V2.5","name":"XiaomiMiMo/MiMo-V2.5","provider":"deepinfra","quantization":null,"discount":0,"context_length":262144,"pricing":{"input":0.4,"output":2,"cache_read":0.08000000000000002,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo omni model for text, image, video, audio, and agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","audio","video"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":37.2,"coding_index":56.8,"agentic_index":23.7,"design_arena_best":{"category":"gamedev","elo":1299,"win_rate":56.5,"rank":18}}},{"id":"XiaomiMiMo/MiMo-V2.5-Pro","name":"XiaomiMiMo/MiMo-V2.5-Pro","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1,"output":2.9999999999999996,"cache_read":0.2,"cache_write":null},"org":"xiaomi","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-22","knowledge_cutoff":"2024-12","description":"MiMo pro model for strong multimodal reasoning and agent execution","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":42.2,"coding_index":60.2,"agentic_index":29.1,"design_arena_best":{"category":"gamedev","elo":1339,"win_rate":62,"rank":5}}},{"id":"z-ai/glm-4.5","name":"Z.ai: GLM 4.5","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":100,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"3d","elo":1227,"win_rate":59.7,"rank":38}}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":96.91489361702128,"pricing":{"input":0.13,"output":0.85,"cache_read":0.024999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.5-air","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-10-13","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":59.4,"rank":42}}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.39577039274926,"pricing":{"input":0.14,"output":0.86,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-10-13","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://novita.ai/docs/guides/introduction"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":59.4,"rank":42}}},{"id":"z-ai/glm-4.5-air","name":"Z.ai: GLM 4.5 Air","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":98304,"uptime_30m":93.5103244837758,"pricing":{"input":0.19999999999999998,"output":1.1,"cache_read":0.03,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5-air","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-07-28","knowledge_cutoff":"2025-04","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"dataviz","elo":1222,"win_rate":59.4,"rank":42}}},{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":65536,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.5v","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-08-11","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true}},{"id":"z-ai/glm-4.5v","name":"Z.ai: GLM 4.5V","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":65536,"max_completion_tokens":16384,"uptime_30m":null,"pricing":{"input":0.6,"output":1.7999999999999998,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.5v","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-08-11","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0,"context_length":198000,"max_completion_tokens":16384,"uptime_30m":99.26739926739927,"pricing":{"input":0.43,"output":1.75,"cache_read":0.08,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org-glm-4.6","doc_url":"https://docs.venice.ai","confidence":"medium","source":"models.dev","release_date":"2024-04-01","knowledge_cutoff":"2025-04","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":97.43589743589743,"pricing":{"input":0.55,"output":2.2,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.6","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"z-ai","provider_display":"Z.AI","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":94.75982532751091,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.6","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-09-30","knowledge_cutoff":"2025-04","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"z-ai/glm-4.6","name":"Z.ai: GLM 4.6","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":99.38271604938271,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-11-15","knowledge_cutoff":"2024-10","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":99.72183588317107,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.055,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.6v","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-08","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":true,"temperature":true},"modalities":{"input":["text","video","image"],"output":["text"]},"open_weights":true}},{"id":"z-ai/glm-4.6v","name":"Z.ai: GLM 4.6V","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":131072,"max_completion_tokens":32768,"uptime_30m":98.63713798977854,"pricing":{"input":0.3,"output":0.8999999999999999,"cache_read":0.049999999999999996,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.6v","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-12-08","knowledge_cutoff":"2025-04","description":"GLM vision model for visual reasoning, documents, and multimodal agents","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video"],"output":["text"]},"open_weights":true}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.2,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":80.18433179723502,"pricing":{"input":0.48,"output":1.76,"cache_read":null,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":92.36453201970444,"pricing":{"input":0.52,"output":1.85,"cache_read":0.12,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.1,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":81.12206216830933,"pricing":{"input":0.54,"output":1.9800000000000002,"cache_read":0.099,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.7","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"venice","provider_display":"Venice","quantization":"fp4","discount":0,"context_length":198000,"max_completion_tokens":16384,"uptime_30m":99.14529914529915,"pricing":{"input":0.55,"output":2.65,"cache_read":0.11,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"z-ai","provider_display":"Z.AI","quantization":"fp4","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":62.23698781838317,"pricing":{"input":0.6,"output":2.2,"cache_read":0.11,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-4.7","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"google","provider_display":"Google","quantization":"unknown","discount":0,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":94.68574348492591,"pricing":{"input":0.6,"output":2.2,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":null,"pricing":{"input":0.85,"output":3.3000000000000003,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7","name":"Z.ai: GLM 4.7","provider":"cerebras","provider_display":"Cerebras","quantization":"fp16","discount":0,"context_length":131072,"max_completion_tokens":40960,"uptime_30m":100,"pricing":{"input":2.25,"output":2.75,"cache_read":2.25,"cache_write":0},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-glm-4.7","doc_url":"https://inference-docs.cerebras.ai/models/overview","confidence":"medium","source":"models.dev","release_date":"2026-01-07","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":131072,"max_completion_tokens":131072,"uptime_30m":99.85412107950401,"pricing":{"input":0.060500000000000005,"output":0.39999999999999997,"cache_read":null,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"@cf/zai-org/glm-4.7-flash","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"novita","provider_display":"Novita","quantization":"bf16","discount":0,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":66.88839615668883,"pricing":{"input":0.07,"output":0.39999999999999997,"cache_read":0.01,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-4.7-flash","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"z-ai/glm-4.7-flash","name":"Z.ai: GLM 4.7 Flash","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":128000,"max_completion_tokens":16384,"uptime_30m":83.49705304518665,"pricing":{"input":0.125,"output":0.5,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.4,"context_length":198000,"max_completion_tokens":128000,"uptime_30m":99.72260748959778,"pricing":{"input":0.6,"output":1.92,"cache_read":0.12,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.4,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":98.89813907933399,"pricing":{"input":0.6,"output":1.92,"cache_read":0.12,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":99.38650306748467,"pricing":{"input":0.7,"output":2.24,"cache_read":0.14,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":64000,"max_completion_tokens":128000,"uptime_30m":99.4475138121547,"pricing":{"input":0.75,"output":2.4,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-02-11","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":false},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":99.25925925925925,"pricing":{"input":0.95,"output":2.5500000000000003,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":65535,"uptime_30m":null,"pricing":{"input":0.95,"output":2.5500000000000003,"cache_read":0.475,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"zai-org/GLM-5-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":99.48979591836735,"pricing":{"input":0.95,"output":3.15,"cache_read":0.19,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"amazon","provider_display":"Amazon Bedrock","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":95.16393442622952,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai.glm-5","doc_url":"https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html","confidence":"high","source":"models.dev","release_date":"2026-03-18","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":202800,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-02-11","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":95.91836734693877,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-02-12","knowledge_cutoff":null,"description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":99.57081545064378,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":198000,"max_completion_tokens":32000,"uptime_30m":99.57627118644068,"pricing":{"input":1,"output":3.1999999999999997,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5","name":"Z.ai: GLM 5","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":null,"pricing":{"input":1.2,"output":3.5,"cache_read":0.475,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5-turbo","name":"Z.ai: GLM 5 Turbo","provider":"z-ai","provider_display":"Z.AI","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5-turbo","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-03-16","knowledge_cutoff":null,"description":"Faster GLM-5 lane for coding agents that need lower latency","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.32,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":99.92260061919505,"pricing":{"input":0.952,"output":2.992,"cache_read":0.17679999999999998,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.31,"context_length":200000,"max_completion_tokens":128000,"uptime_30m":99.94008388256441,"pricing":{"input":0.966,"output":3.036,"cache_read":0.1794,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":163840,"max_completion_tokens":131072,"uptime_30m":93.5064935064935,"pricing":{"input":0.975,"output":4.300000000000001,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5.1","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"chutes","provider_display":"Chutes","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":65535,"uptime_30m":91.44050104384134,"pricing":{"input":0.98,"output":3.08,"cache_read":0.49,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"zai-org/GLM-5.1-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.3,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":98.29867674858222,"pricing":{"input":0.98,"output":3.08,"cache_read":0.182,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5.1-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":1.19,"output":3.74,"cache_read":0.6,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"crusoe","provider_display":"Crusoe","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":null,"uptime_30m":99.73154362416108,"pricing":{"input":1.2,"output":4.4,"cache_read":0.25,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":128000,"uptime_30m":93.79084967320262,"pricing":{"input":1.21,"output":4.199999999999999,"cache_read":0.6,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":100,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0,"context_length":204800,"max_completion_tokens":131072,"uptime_30m":99.63235294117648,"pricing":{"input":1.38,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.1","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-03-27","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"nebius","provider_display":"Nebius","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":null,"uptime_30m":100,"pricing":{"input":1.4,"output":4.4,"cache_read":null,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"parasail","provider_display":"Parasail","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":95.21739130434783,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":null,"uptime_30m":0,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":202752,"max_completion_tokens":202752,"uptime_30m":99.90800367985281,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.1","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":99.8997995991984,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.1","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.1","name":"Z.ai: GLM 5.1","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":200000,"max_completion_tokens":80000,"uptime_30m":100,"pricing":{"input":1.54,"output":4.84,"cache_read":0.286,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"streamlake","provider_display":"StreamLake","quantization":"fp8","discount":0.4645,"context_length":1024000,"max_completion_tokens":128000,"uptime_30m":99.70303750212116,"pricing":{"input":0.7497,"output":2.3562,"cache_read":0.13923000000000002,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"novita","provider_display":"Novita","quantization":"fp8","discount":0.464,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.88618665388762,"pricing":{"input":0.7504000000000001,"output":2.3584,"cache_read":0.13936,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.novita.ai/openai","model_id":"zai-org/glm-5.2","doc_url":"https://novita.ai/docs/guides/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"coreweave","provider_display":"CoreWeave","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.13242756588639,"pricing":{"input":0.76,"output":2.42,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"baidu","provider_display":"Baidu","quantization":"fp8","discount":0.45,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.51550387596899,"pricing":{"input":0.77,"output":2.42,"cache_read":0.143,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"akashml","provider_display":"AkashML","quantization":"fp8","discount":0.45,"context_length":96890,"max_completion_tokens":96890,"uptime_30m":97.17114568599717,"pricing":{"input":0.77,"output":2.42,"cache_read":0.143,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"alibaba","provider_display":"Alibaba","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.02391933926847,"pricing":{"input":0.826,"output":2.5959999999999996,"cache_read":0.16519999999999999,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"gmicloud","provider_display":"GMICloud","quantization":"fp8","discount":0.34,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.32465821116784,"pricing":{"input":0.9239999999999999,"output":2.904,"cache_read":0.1716,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.gmi-serving.com/v1","model_id":"zai-org/GLM-5.2-FP8","doc_url":"https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"inceptron","provider_display":"Inceptron","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":93.76049916006718,"pricing":{"input":0.94,"output":2.9000000000000004,"cache_read":0.16999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"sail-research","provider_display":"Sail Research","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.82713915298184,"pricing":{"input":1,"output":3.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"digitalocean","provider_display":"DigitalOcean","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":131072,"uptime_30m":96.8944099378882,"pricing":{"input":1.0499999999999998,"output":4.4,"cache_read":0.21,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.do-ai.run/v1","model_id":"glm-5.2","doc_url":"https://docs.digitalocean.com/products/gradient-ai-platform/details/models/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"ambient","provider_display":"Ambient","quantization":"fp8","discount":0,"context_length":101376,"max_completion_tokens":101376,"uptime_30m":83.37950138504155,"pricing":{"input":1.0499999999999998,"output":4.4,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"morph","provider_display":"Morph","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":94.42724458204334,"pricing":{"input":1.1,"output":4.1,"cache_read":0.22,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"decart","provider_display":"Decart","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":99.51980792316927,"pricing":{"input":1.2,"output":2.5,"cache_read":0.19999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"chutes","provider_display":"Chutes","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":65535,"uptime_30m":99.13232104121475,"pricing":{"input":1.25,"output":3.95,"cache_read":0.625,"cache_write":null},"org":"z-ai","subscription":true,"modelsdev":{"base_url":"https://llm.chutes.ai/v1","model_id":"zai-org/GLM-5.2-TEE","doc_url":"https://llm.chutes.ai/v1/models","confidence":"medium","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"atlascloud","provider_display":"AtlasCloud","quantization":"fp8","discount":0.1,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.87662241523961,"pricing":{"input":1.26,"output":3.9600000000000004,"cache_read":0.234,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"siliconflow","provider_display":"SiliconFlow","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":99.68152866242038,"pricing":{"input":1.302,"output":4.092,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.594451628071,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5.2","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"fireworks","provider_display":"Fireworks","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":99.2843201040989,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://api.fireworks.ai/inference/v1/","model_id":"accounts/fireworks/models/glm-5p2","doc_url":"https://fireworks.ai/docs/","confidence":"high","source":"models.dev","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"cloudflare","provider_display":"Cloudflare","quantization":"unknown","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":100,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":null,"model_id":"@cf/zai-org/glm-5.2","doc_url":"https://developers.cloudflare.com/workers-ai/models/","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"friendli","provider_display":"Friendli","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":1048576,"uptime_30m":99.02130109383995,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev":{"base_url":"https://api.friendli.ai/serverless/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://friendli.ai/docs/guides/serverless_endpoints/introduction","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"parasail","provider_display":"Parasail","quantization":"fp4","discount":0,"context_length":262144,"max_completion_tokens":262144,"uptime_30m":99.81343283582089,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"venice","provider_display":"Venice","quantization":"fp8","discount":0,"context_length":1000000,"max_completion_tokens":131072,"uptime_30m":99.08759124087592,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"together","provider_display":"Together","quantization":"unknown","discount":0,"context_length":512000,"max_completion_tokens":164000,"uptime_30m":58.753297237262245,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":null,"model_id":"zai-org/GLM-5.2","doc_url":"https://docs.together.ai/docs/serverless-models","confidence":"high","source":"models.dev","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"ionstream","provider_display":"Ionstream","quantization":"fp4","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":98.63680623174295,"pricing":{"input":1.4,"output":4.4,"cache_read":0.26,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"phala","provider_display":"Phala","quantization":"unknown","discount":0,"context_length":1048576,"max_completion_tokens":131072,"uptime_30m":98.47328244274809,"pricing":{"input":1.4,"output":4.4,"cache_read":0.7,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"baseten","provider_display":"BaseTen","quantization":"fp8","discount":0,"context_length":1048576,"max_completion_tokens":262144,"uptime_30m":98.66962305986696,"pricing":{"input":1.4,"output":4.4,"cache_read":0.14,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev":{"base_url":"https://inference.baseten.co/v1","model_id":"zai-org/GLM-5.2","doc_url":"https://docs.baseten.co/inference/model-apis/overview","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5.2","name":"Z.ai: GLM 5.2","provider":"io-net","provider_display":"Io Net","quantization":"fp8","discount":0,"context_length":262144,"max_completion_tokens":65536,"uptime_30m":null,"pricing":{"input":3.3278760000000003,"output":7.279730000000001,"cache_read":1.6639380000000001,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"z-ai/glm-5v-turbo","name":"Z.ai: GLM 5V Turbo","provider":"z-ai","provider_display":"Z.AI","quantization":"fp8","discount":0,"context_length":202752,"max_completion_tokens":131072,"uptime_30m":100,"pricing":{"input":1.2,"output":4,"cache_read":0.24,"cache_write":0},"org":"z-ai","zdr":true,"subscription":true,"modelsdev":{"base_url":"https://api.z.ai/api/paas/v4","model_id":"glm-5v-turbo","doc_url":"https://docs.z.ai/guides/overview/pricing","confidence":"high","source":"models.dev","release_date":"2026-04-01","knowledge_cutoff":null,"description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":true,"temperature":true},"modalities":{"input":["text","image","video","pdf"],"output":["text"]},"open_weights":false},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1276,"win_rate":54.1,"rank":25}}},{"id":"zai-org/GLM-4.6","name":"zai-org/GLM-4.6","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.5,"output":2,"cache_read":0.1,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2024-11-15","knowledge_cutoff":"2024-10","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":false,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":false,"doc_url":"https://io.net/docs/guides/intelligence/io-intelligence"},"benchmarks":{"intelligence_index":28.7,"coding_index":45.8,"agentic_index":17.7,"design_arena_best":{"category":"gamedev","elo":1206,"win_rate":54.6,"rank":45}}},{"id":"zai-org/GLM-4.7","name":"zai-org/GLM-4.7","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.4,"output":1.75,"cache_read":0.08000000000000002,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2025-12-22","knowledge_cutoff":"2025-04","description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.baseten.co/inference/model-apis/overview"},"benchmarks":{"intelligence_index":33.7,"coding_index":45.3,"agentic_index":25.4,"design_arena_best":{"category":"website","elo":1251,"win_rate":55.3,"rank":34}}},{"id":"zai-org/GLM-4.7-Flash","name":"zai-org/GLM-4.7-Flash","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.060000000000000005,"output":0.4,"cache_read":0.0100000002,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-01-19","knowledge_cutoff":"2025-04","description":"Budget GLM lane for fast coding help, routing, and everyday automation","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://crof.ai/docs"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"uicomponent","elo":1244,"win_rate":57.6,"rank":35}}},{"id":"zai-org/GLM-5","name":"zai-org/GLM-5","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":0.6,"output":2.08,"cache_read":0.12,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-02-11","knowledge_cutoff":"2025-04","description":"Legacy model retained for compatibility with older integrations","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://opencode.ai/docs/zen"},"benchmarks":{"intelligence_index":null,"coding_index":null,"agentic_index":null,"design_arena_best":{"category":"gamedev","elo":1314,"win_rate":59.1,"rank":14}}},{"id":"zai-org/GLM-5.1","name":"zai-org/GLM-5.1","provider":"deepinfra","quantization":null,"discount":0,"context_length":202752,"pricing":{"input":1.05,"output":3.5,"cache_read":0.205000005,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-04-07","knowledge_cutoff":null,"description":"Powerful MoE model for long-horizon agentic engineering and advanced reasoning.","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://docs.wandb.ai/guides/integrations/inference/"},"benchmarks":{"intelligence_index":40.2,"coding_index":55.8,"agentic_index":29.9,"design_arena_best":{"category":"dataviz","elo":1366,"win_rate":67,"rank":3}}},{"id":"zai-org/GLM-5.2","name":"zai-org/GLM-5.2","provider":"deepinfra","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":0.9299999999999999,"output":2.9999999999999996,"cache_read":0.18000000269999997,"cache_write":null},"org":"z-ai","zdr":true,"modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"zai-org/glm-5.2","name":"GLM 5.2","provider":"lilac","quantization":null,"discount":0,"context_length":524288,"pricing":{"input":0.8999999999999999,"output":3,"cache_read":0.16999999999999998,"cache_write":null},"org":"z-ai","zdr":true,"subscription":true,"max_completion_tokens":524288,"modelsdev":{"base_url":"https://api.getlilac.com/v1","model_id":"zai-org/glm-5.2","doc_url":"https://docs.getlilac.com/inference/models","confidence":"high","source":"models.dev","release_date":"2026-06-13","knowledge_cutoff":null,"description":"Open flagship GLM for long-horizon coding agents and million-token context work","capabilities":{"reasoning":true,"tool_call":true,"structured_output":true,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}},{"id":"zai-org/GLM-5.2","name":"GLM 5.2","provider":"sference","quantization":null,"discount":0,"context_length":1048576,"pricing":{"input":1.2,"output":4.2,"cache_read":0.26,"cache_write":null},"org":"z-ai","modelsdev_model":{"source":"models.dev (model-level fallback)","release_date":"2026-06-16","knowledge_cutoff":null,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","capabilities":{"reasoning":true,"tool_call":true,"structured_output":false,"attachment":false,"temperature":true},"modalities":{"input":["text"],"output":["text"]},"open_weights":true,"doc_url":"https://fireworks.ai/docs/"},"benchmarks":{"intelligence_index":51.1,"coding_index":68.8,"agentic_index":43.1,"design_arena_best":{"category":"3d","elo":1367,"win_rate":59.9,"rank":4}}}]}