MiniMax M2
MiniMax· released 23 Oct 2025
minimax/minimax-m2- Input / 1M tokens
- $0.3
- Output / 1M tokens
- $1.2
Longest answer: 177K tokens
About
MiniMax M2 is a text-in, text-out language model from MiniMax, released on 2025-10-23. Its summary describes it as a compact model for end-to-end coding and agentic workflows, with 10 billion activated parameters out of 230 billion total. It supports tools and reasoning, and has a context window of 204,800 tokens. The maximum output is 176,947 tokens. MiniMax lists open weights, with Hugging Face ID MiniMaxAI/MiniMax-M2. Its model ID is minimax/minimax-m2. Input costs USD 0.3 per 1M tokens, while output costs USD 1.2 per 1M tokens. For teams assessing it, the listed emphasis on coding and agentic workflows sits alongside tool support, open weights and a text-only interface. The official page is on OpenRouter.
Who it is for
MiniMax M2 suits builders focused on end-to-end coding or agentic workflows. It may also fit teams looking for open weights, tool support and reasoning in a text-only model.
What is good
- Open weights are listed.
- Supports tools and reasoning.
- Context window is 204,800 tokens.
- Listed for end-to-end coding workflows.
- Maximum output is 176,947 tokens.
What to know first
- Inputs and outputs are text only.
- Output costs USD 1.2 per 1M tokens.
- Released on 2025-10-23.
Verdict
MiniMax M2 pairs open weights and tool support with a stated focus on coding and agentic workflows. Its text-only interface and listed token rates are relevant constraints when assessing fit.
Details
- Lab
- MiniMaxopenrouter.ai · 3 Oct 2026
- Context
- 205Kopenrouter.ai · 3 Oct 2026
- Input price
- $0.3 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $1.2 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 176,947 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- textopenrouter.ai · 3 Oct 2026
- Open weights
- Yesopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Open-Weight Models in 2026178 listed
- MiniMax Models: Pricing per 1M Tokens and Context (2026)8 listed
Sources
- openrouter.ai/minimax/minimax-m2· checked 3 Oct 2026