{"id":"minimax/minimax-m3","name":"MiniMax M3","vendor":"MiniMax","kind":"text","description":"M3 can reason over up to one million tokens in one request, enough to compare lengthy specifications or trace dependencies across a large codebase.","useCases":["Trace a behavior across several parts of a codebase","Compare requirements across lengthy specifications"],"technical":[{"label":"API model ID","value":"minimax/minimax-m3"},{"label":"Provider","value":"MiniMax"},{"label":"Modality","value":"Text"},{"label":"Input","value":"Chat messages"},{"label":"Output","value":"Text"},{"label":"Endpoint","value":"POST /v1/chat/completions"}],"parameters":[{"name":"messages","type":"object[]","description":"The conversation, in OpenAI's format.","required":true,"options":"OpenAI chat messages (system, user, assistant, tool)"},{"name":"max_completion_tokens","type":"integer","description":"Thinking tokens count toward it: too small a cap ends with finish_reason: length and an empty answer.","required":false,"default":"the model's","options":"1 up to the model's output limit"},{"name":"max_tokens","type":"integer","description":"The older name for the same cap; MiniMax marks it deprecated.","required":false,"options":"as above"},{"name":"stream","type":"boolean","description":"Server-sent events, as in OpenAI's API.","required":false,"default":"false","options":"true · false"},{"name":"stream_options","type":"object","description":"Adds a final chunk with token usage.","required":false,"options":"{\"include_usage\": true}"},{"name":"temperature","type":"number","description":"MiniMax documents it as having no effect on M3 (fixed at 1).","required":false,"default":"1","options":"(0, 1]"},{"name":"top_p","type":"number","description":"MiniMax documents it as having no effect on M3 (fixed at 0.95).","required":false,"default":"0.95","options":"(0, 1]"},{"name":"tools","type":"object[]","description":"Function calling, in OpenAI's format.","required":false,"options":"OpenAI function tools"},{"name":"tool_choice","type":"string","description":"Whether the model may, must, or must not call a tool, as MiniMax documents for M3.","required":false,"default":"auto","options":"none · auto · required"},{"name":"thinking","type":"object","description":"The model reasons before answering by default; disabled turns it off.","required":false,"default":"on","options":"{\"type\": \"adaptive\"} · {\"type\": \"disabled\"}"},{"name":"reasoning_split","type":"boolean","description":"true returns the reasoning in reasoning_content; false leaves it inside the answer between think tags.","required":false,"default":"the vendor's","options":"true · false"},{"name":"service_tier","type":"string","description":"MiniMax's priority tier, on M3 only, billed at 1.5× the standard rates.","required":false,"default":"standard","options":"priority"}],"pricing":{"currency":"USD","generated":"2026-11-21T02:23:44Z","notes":["A prompt over 512,000 tokens bills the whole request at the long-context rates."],"rates":[{"charge":"per 1M input tokens","options":"","price":0.36,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"prompts over 512,000 tokens","price":0.72,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M input tokens","options":"priority (service_tier: priority)","price":0.54,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"","price":1.44,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"prompts over 512,000 tokens","price":2.88,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M output tokens","options":"priority (service_tier: priority)","price":2.16,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"","price":0.072,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"prompts over 512,000 tokens","price":0.144,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cached input tokens","options":"priority (service_tier: priority)","price":0.108,"from":null,"until":null,"note":null,"status":"active"},{"charge":"per 1M cache-write tokens","options":"","price":0,"from":null,"until":null,"note":"free","status":"active"},{"charge":"per 1M cache-write tokens","options":"priority (service_tier: priority)","price":0,"from":null,"until":null,"note":"free","status":"active"}]},"links":{"page":"https://sociaro.com/models/minimax/minimax-m3","markdown":"https://sociaro.com/models/minimax/minimax-m3.md","json":"https://sociaro.com/models/minimax/minimax-m3.json","pricing":"https://sociaro.com/pricing?model=minimax%2Fminimax-m3","docs":"https://docs.sociaro.com/models/minimax-minimax-m3/","playground":null},"examples":[]}