minimax-m3 · MiniMax · vision
Official MiniMax model; specifications and prices verified against official documentation on 2026-10-07. Language reasoning and tool calling.
Input / output / endpoint: `text, image, video` → `text`. context_window=1,000,000 tokens; OpenAI Chat Completions / Anthropic Messages; streaming; function tools. thinking.type: adaptive / disabled; image/video understanding. Output length is controlled with max_completion_tokens; the official API schema does not publish one fixed maximum for all models.
Coding assistants, tool-using agents, long-context document Q&A, and writing.
The key must have access to the model. Included subscription usage follows the MiniMax console. Accepts text, images, and video; returns text. Thinking defaults to adaptive and can be disabled with thinking.type=disabled. Official sources: [https://platform.minimax.cn/docs/api-reference/text-openai-api](https://platform.minimax.cn/docs/api-reference/text-openai-api) · [https://platform.minimax.cn/docs/guides/pricing-paygo](https://platform.minimax.cn/docs/guides/pricing-paygo) · [https://platform.minimax.io/docs/guides/pricing-paygo](https://platform.minimax.io/docs/guides/pricing-paygo) · [https://platform.minimax.cn/docs/guides/pricing-token-plan](https://platform.minimax.cn/docs/guides/pricing-token-plan)
Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="minimax-m3"
claude