# MiniMax-M3

> MiniMax-M3 is an open-weight language model from MiniMax, released on 1 Jun 2026. It accepts text, images and video and generates text, with a 1M-token context window and up to 512K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.28 per million input tokens and $1.10 per million output tokens (DeepInfra), across 9 providers we track.

Source page: https://www.aimodel.directory/models/minimax-m3
Last verified: 4 Oct 2026

## Specifications

- **Developer:** MiniMax
- **Release date:** 1 Jun 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M3)
- **License:** minimax-community (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M3)
- **Parameters:** 427B (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M3)
- **Context window:** 1M (1,000,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Max output:** 512K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Knowledge cutoff:** Jan 2025 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Input:** Text, images and video (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/minimax/models/MiniMax-M3.toml)
- **Hugging Face:** MiniMaxAI/Minimax-M3 (source: Hugging Face, https://huggingface.co/MiniMaxAI/MiniMax-M3)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| DeepInfra | $0.28 | $1.10 | $0.06 | 524K |
| MiniMax API | $0.30 | $1.20 | $0.06 | 1M |
| Hugging Face Inference Providers | $0.30 | $1.20 | – | 524K |
| Nebius AI Studio | $0.30 | $1.20 | – | 1M |
| Fireworks AI | $0.30 | $1.20 | $0.06 | 512K |
| Fireworks AI | $0.30 | $1.20 | $0.06 | 512K |
| SiliconFlow | $0.30 | $1.20 | $0.06 | 1M |
| Together AI | $0.30 | $1.20 | $0.06 | 524K |
| OpenRouter | $0.30 | $1.20 | $0.06 | 524K |
| Vercel AI Gateway | $0.30 | $1.20 | $0.06 | 512K |

## FAQ

### What is the context window of MiniMax-M3?

MiniMax-M3 has a context window of 1,000,000 tokens (1M) and can generate up to 512,000 tokens in a single response, according to models.dev.

### How much does the MiniMax-M3 API cost?

Through MiniMax API, MiniMax-M3 costs $0.30 per million input tokens and $1.20 per million output tokens. The lowest listed price is $0.28 input / $1.10 output through DeepInfra. Prices last verified 4 Oct 2026.

### Is MiniMax-M3 open source?

MiniMax-M3 is an open-weight model: its weights are published on Hugging Face as MiniMaxAI/Minimax-M3 under the minimax-community license. Check the license terms before commercial use.

### When was MiniMax-M3 released?

MiniMax released MiniMax-M3 on 1 Jun 2026, according to models.dev.

### Which providers offer MiniMax-M3?

We track MiniMax-M3 on 9 providers: DeepInfra, MiniMax API, Hugging Face Inference Providers, Nebius AI Studio, Fireworks AI, SiliconFlow, Together AI, OpenRouter, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "MiniMax-M3", https://www.aimodel.directory/models/minimax-m3