{"id":"minimaxai/minimax-m3","aliases":["hf:minimaxai/minimax-m3","minimax/minimax-m3","minimax/minimax-m3-20260531","minimax/minimax-m3:batch","minimax/minimax-m3:free","openrouter:minimax/minimax-m3","openrouter:minimax/minimax-m3:batch","openrouter:minimax/minimax-m3:free"],"displayName":"MiniMax: MiniMax M3","author":"minimaxai","createdAt":"2026-05-31T16:36:14.000Z","updatedAt":"2026-09-08T15:44:27.512Z","popularityRank":31,"metadata":{"modalities":["image","text","video"],"inputModalities":["text","image","video"],"outputModalities":["text"],"contextLength":1048576,"maxOutputTokens":512000,"family":"minimax","modelsDev":{"provider":"openrouter","sourceUrl":"https://models.dev/api.json","description":"MiniMax multimodal model for long-context coding, perception, and agent planning","lastUpdated":"2026-06-01","releaseDate":"2026-06-01","capabilities":{"reasoning":true,"tool_call":true,"attachment":true,"temperature":true,"open_weights":true,"structured_output":true}},"tokenizer":"Other","licenseStatus":"unknown","weightsAvailable":false,"hostedInferenceAllowed":false,"gated":false,"supportedParameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"providerNames":[],"designArenaCategories":["agenticgamedev","androidnative","fullstack","htmlslides","mobileapps","python-pptxslides","webapps","3d","asciiart","codecategories","dataviz","gamedev","svg","uicomponent","website"],"isModerated":false},"availability":"unknown","externalBest":null,"multivibeNetwork":null,"description":"MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...","runtimes":[],"protocols":[],"harnesses":[]}