# MiniMax-M2

> MiniMax-M2 is an open-weight language model from MiniMax, released on 27 Oct 2025. It accepts text and generates text, with a 205K-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.30 per million input tokens and $1.20 per million output tokens (MiniMax API), across 6 providers we track.

Source page: https://www.aimodel.directory/models/minimax-m2
Last verified: 4 Oct 2026

## Specifications

- **Developer:** MiniMax
- **Release date:** 27 Oct 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M2)
- **License:** modified-mit (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M2)
- **Parameters:** 229B (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M2)
- **Context window:** 205K (204,800 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Knowledge cutoff:** 1 Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M2.toml)
- **Hugging Face:** MiniMaxAI/MiniMax-M2 (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M2)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| MiniMax API | $0.30 | $1.20 | – | 205K |
| Amazon Bedrock | $0.30 | $1.20 | – | 205K |
| Novita AI | $0.30 | $1.20 | $0.03 | 205K |
| Hugging Face Inference Providers | $0.30 | $1.20 | – | 205K |
| Vercel AI Gateway | $0.30 | $1.20 | $0.03 | 205K |
| OpenRouter | $0.30 | $1.20 | – | 197K |

## FAQ

### What is the context window of MiniMax-M2?

MiniMax-M2 has a context window of 204,800 tokens (205K) and can generate up to 131,072 tokens in a single response, according to models.dev.

### How much does the MiniMax-M2 API cost?

Through MiniMax API, MiniMax-M2 costs $0.30 per million input tokens and $1.20 per million output tokens. Prices last verified 4 Oct 2026.

### Is MiniMax-M2 open source?

MiniMax-M2 is an open-weight model: its weights are published on Hugging Face as MiniMaxAI/MiniMax-M2 under the modified-mit license. Check the license terms before commercial use.

### When was MiniMax-M2 released?

MiniMax released MiniMax-M2 on 27 Oct 2025, according to models.dev.

### Which providers offer MiniMax-M2?

We track MiniMax-M2 on 6 providers: MiniMax API, Amazon Bedrock, Novita AI, Hugging Face Inference Providers, Vercel AI Gateway, OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "MiniMax-M2", https://www.aimodel.directory/models/minimax-m2