MiniMax-M2.7
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).
- Context window
- 204,800 tokens
- Input
- text
- Output
- text
- License
- other (MiniMax license, see HF)
- Pricing
- input: $0.3 · output: $1.2 · cache read: $0.06 · cache write: $0.375 (per 1M tokens (USD); MiniMax-M2.7-highspeed: 0.6 / 2.4) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| MiniMax API (Anthropic format) | MiniMax-M2.7 | https://api.minimax.io/anthropic | docs |
| MiniMax API (OpenAI format) | MiniMax-M2.7 | https://api.minimax.io/v1 | docs |
| MiniMax API (fast) | MiniMax-M2.7-highspeed | https://api.minimax.io/v1 | docs |
| OpenRouter | minimax/minimax-m2.7 | openrouter.ai/minimax/minimax-m2.7 | — |
| Hugging Face | — | huggingface.co/MiniMaxAI/MiniMax-M2.7 | — |
Notable capabilities (2)
- Participates in its own evolution: MiniMax calls it its first model deeply participating in its own development ('recursive self-improvement'). source
- Agent harness building: Builds complex agent harnesses using Agent Teams, Skills and dynamic tool search; aimed at professional office delivery. source
Budget agentic coding model with 204.8K context; good for self-hosting (SGLang) or cheap API use.
curl https://api.minimax.io/v1/chat/completions \
-H "Authorization: Bearer $MINIMAX_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"MiniMax-M2.7","messages":[{"role":"user","content":"Hello"}]}'
Sources: https://platform.minimax.io/docs/guides/models-intro · https://platform.minimax.io/docs/guides/pricing-paygo · https://huggingface.co/MiniMaxAI/MiniMax-M2.7
Other MiniMax models
MiniMax H3 · MiniMax Music 3.0 · MiniMax-M3 · MiniMax Speech 2.8 (HD / Turbo)