UTC

MiniMax-M2.1

MiniMax · open weights · served by 21 providers · tool calling, reasoning

minimax/MiniMax-M2.1

Weights
Open
Released
2025-12-23
Knowledge cutoff
2025-01
Context window
205K
Deprecation dates

When each platform deprecates MiniMax-M2.1, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Amazon Bedrockdeprecates 2027-03-30bedrock/ap-northeast-1/minimax.minimax-m2.1successor: bedrock/ap-northeast-1/minimax.minimax-m2.5
Every upcoming deprecation →
Hugging Face repository

MiniMaxAI/MiniMax-M2.1 at commit 917dbb7d07, last changed 2026-10-26

Licence
modified-mit
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

31 weight files, 30 with a scan result. No scanner reports an issue with them.

The model at this commit, its 31 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-M2.1
  • Amazon Bedrockminimax.minimax-m2.1deprecated
  • Cortecsminimax-m2.1
  • Eden AIminimax/MiniMax-M2.1
  • Hugging FaceMiniMaxAI/MiniMax-M2.1
  • Jiekou.AIminimax/minimax-m2.1
  • Kilo Gatewayminimax/minimax-m2.1
  • DevPass (LLM Gateway)minimax-m2.1
  • LLM Gatewayminimax/minimax-m2.1
  • MeganovaMiniMaxAI/MiniMax-M2.1
  • Merge Gatewayminimax/minimax-m2.1
  • MoarkMiniMax-M2.1deprecated
  • NanoGPTminimax/minimax-m2.1
  • Ofoxminimax/minimax-m2.1
  • Ofoxminimax/minimax-m2.1-lightning
  • OpenCodeminimax-m2.1deprecated
  • OpenCodeminimax-m2.1-freedeprecated
  • Poenovita/minimax-m2.1
  • Qiniuminimax/minimax-m2.1deprecated
  • Vercel AI Gatewayminimax/minimax-m2.1
  • ZenMuxminimax/minimax-m2.1
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.