{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/minimax-m3/","md":"https://postcutoff.com/m/minimax-m3/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-m3","name":"MiniMax-M3","org":"MiniMax","family":"MiniMax-M","released":"2026-06-01","status":"current","type":"reasoning-llm","modality_in":["text","image","video"],"modality_out":["text"],"open_weights":true,"model_license":"minimax-community","context_window":1000000,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":0.3,"output":1.2,"cache_read":0.06,"unit":"per 1M tokens (USD), standard tier, input <=512K (after permanent 50% discount); >512K input: 0.60/2.40/0.12. Priority tier 1.5x","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-M3","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-M3","endpoint":"https://api.minimax.io/v1","docs":"https://platform.minimax.io/docs/api-reference/text-openai-api"},{"provider":"OpenRouter","model_id":"minimax/minimax-m3","url":"https://openrouter.ai/minimax/minimax-m3"},{"provider":"Hugging Face","url":"https://huggingface.co/MiniMaxAI/MiniMax-M3"}],"capabilities":[{"name":"MiniMax Sparse Attention (MSA)","detail":"New sparse attention for million-token contexts: 9x prefill and 15x decode speed-up vs M2 at 1M context, ~1/20 per-token compute.","first":false,"discovered":"launch","source":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"name":"Native multimodality from step one","detail":"Mixed text/image/video training from the start of pre-training (~428B total / ~23B active).","first":false,"discovered":"launch","source":"https://huggingface.co/MiniMaxAI/MiniMax-M3"},{"name":"Three reasoning modes","detail":"thinking parameter selects among three reasoning modes; interleaved thinking with tool use.","first":false,"discovered":"launch","source":"https://huggingface.co/MiniMaxAI/MiniMax-M3"}],"entry":null,"notes":"MiniMax flagship LLM. OpenAI-format responses include <think> content that must be preserved across turns. MiniMax-M3.1-Flash-Preview (1M, tunable thinking) exists but only via Token Plan/MiniMax Code. Max output and knowledge cutoff not verified.","verified":"2026-09-29","body_md":"Low-cost 1M-context multimodal coding/agent model; Anthropic-SDK-first API, open weights.\n\n```bash\ncurl https://api.minimax.io/anthropic/v1/messages \\\n -H \"x-api-key: $MINIMAX_API_KEY\" -H \"anthropic-version: 2023-06-01\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"MiniMax-M3\",\"max_tokens\":4096,\"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-M3","page_url":"https://postcutoff.com/m/minimax-m3/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1826,"you_url":"https://postcutoff.com/you/minimax-m3/","briefings":null}