UTC

MiniMax-M2.7

MiniMax · open weights · served by 44 providers · tool calling, reasoning

minimax/MiniMax-M2.7

Weights
Open
Released
2026-03-18
Knowledge cutoff
2025-01
Context window
205K
Deprecation dates

When each platform deprecates MiniMax-M2.7, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Together AIdeprecated 2026-07-28together_ai/MiniMaxAI/MiniMax-M2.7successor: together_ai/MiniMaxAI/MiniMax-M3.1-Flash
Every upcoming deprecation →
Hugging Face repository

MiniMaxAI/MiniMax-M2.7 at commit 0a6536713b, last changed 2026-10-26

Licence
other
Access
Open download
Library
transformers
Formats
.safetensors
  • Loading it runs code from the repository (trust_remote_code). Read that code, and pin the commit.
  • No model signature file is published with the weights.

What the Hub's scanners report

27 weight files, 27 with a scan result. No scanner reports an issue with them.

The model at this commit, its 27 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • 302.AIMiniMax-M2.7
  • AbacusMiniMaxAI/MiniMax-M2.7
  • AIHubMixcoding-minimax-m2.7
  • AIHubMixcoding-minimax-m2.7-free
  • AIHubMixminimax-m2.7
  • Aurikominimax-m2-7
  • CommandCodeMiniMaxAI/MiniMax-M2.7
  • CrossModelminimax/minimax-m2.7
  • Deep InfraMiniMaxAI/MiniMax-M2.7deprecated
  • Eden AIminimax/MiniMax-M2.7
  • FastRouterminimax/minimax-m2.7
  • FrogBotminimax-m2-7deprecated
  • GMI CloudMiniMaxAI/MiniMax-M2.7
  • Hugging FaceMiniMaxAI/MiniMax-M2.7
  • IteraComputeminimax/minimax-m2.7
  • JoinGonkaMiniMaxAI/MiniMax-M2.7
  • Kenariminimax-m2-7
  • Kilo Gatewayminimax/minimax-m2.7
  • DevPass (LLM Gateway)minimax-m2.7
  • LLM Gatewayminimax/minimax-m2.7
  • LLM Gatewaynovita/minimax-m2.7
  • LLM Gatewayscx-ai/minimax-m2.7
  • LLM Gatewaytencent/minimax-m2.7
  • Merge Gatewayminimax/minimax-m2.7
20 more providers

Moark (MiniMax-M2.7), Moneo (MiniMax-M2.7:web), NanoGPT (minimax/minimax-m2.7), Novita AI (minimax/minimax-m2.7), Ofox (minimax/minimax-m2.7), Ollama Cloud (minimax-m2.7), OpenCode (minimax-m2.7), OpenCode Go (minimax-m2.7), OpenRouter (minimax/minimax-m2.7), Opper (minimax-m2.7), OrcaRouter (minimax/minimax-m2.7), Requesty (minimax-m2.7), SCNet Token Plan (MiniMax-M2.7), SCX.ai (MiniMax-M2.7), Together AI (MiniMaxAI/MiniMax-M2.7), UnoRouter (minimax-m2.7), UnoRouter (minimax-m2.7:free), Venice AI (minimax-m27), Vercel AI Gateway (minimax/minimax-m2.7), ZenMux (minimax/minimax-m2.7)

Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.