{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/minimax-m2-7/","md":"https://postcutoff.com/m/minimax-m2-7/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"minimax-m2-7","name":"MiniMax-M2.7","org":"MiniMax","family":"MiniMax-M","released":"2026-03-18","status":"current","type":"reasoning-llm","modality_in":["text"],"modality_out":["text"],"open_weights":true,"model_license":"other (MiniMax license, see HF)","context_window":204800,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"cache_write":0.375,"unit":"per 1M tokens (USD); MiniMax-M2.7-highspeed: 0.6 / 2.4","source":"https://platform.minimax.io/docs/guides/pricing-paygo"},"price_line":"$0.30 in, $1.20 out per 1M tokens","access":[{"provider":"MiniMax API (Anthropic format)","model_id":"MiniMax-M2.7","endpoint":"https://api.minimax.io/anthropic","docs":"https://platform.minimax.io/docs/api-reference/text-anthropic-api"},{"provider":"MiniMax API (OpenAI format)","model_id":"MiniMax-M2.7","endpoint":"https://api.minimax.io/v1","docs":"https://platform.minimax.io/docs/api-reference/text-openai-api"},{"provider":"MiniMax API (fast)","model_id":"MiniMax-M2.7-highspeed","endpoint":"https://api.minimax.io/v1","docs":"https://platform.minimax.io/docs/api-reference/text-openai-api"},{"provider":"OpenRouter","model_id":"minimax/minimax-m2.7","url":"https://openrouter.ai/minimax/minimax-m2.7"},{"provider":"Hugging Face","url":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"}],"capabilities":[{"name":"Participates in its own evolution","detail":"MiniMax calls it its first model deeply participating in its own development ('recursive self-improvement').","first":false,"discovered":"launch","source":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"},{"name":"Agent harness building","detail":"Builds complex agent harnesses using Agent Teams, Skills and dynamic tool search; aimed at professional office delivery.","first":false,"discovered":"launch","source":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7"}],"entry":null,"notes":"Text-only predecessor of M3, still a current API model; highspeed variant ~100 tok/s vs ~60. M2.5/M2.1/M2 are legacy (same $0.3/$1.2 price).","verified":"2026-09-29","body_md":"Budget agentic coding model with 204.8K context; good for self-hosting (SGLang) or cheap API use.\n\n```bash\ncurl https://api.minimax.io/v1/chat/completions \\\n -H \"Authorization: Bearer $MINIMAX_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"MiniMax-M2.7\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://platform.minimax.io/docs/guides/models-intro · https://platform.minimax.io/docs/guides/pricing-paygo · https://huggingface.co/MiniMaxAI/MiniMax-M2.7","page_url":"https://postcutoff.com/m/minimax-m2-7/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1905,"you_url":"https://postcutoff.com/you/minimax-m2-7/","briefings":null}