# MiniMax-M2 API pricing

The official API price of MiniMax-M2 is $0.3 per 1M input tokens and $1.2 per 1M output tokens (as of 2026-11-12). Context window: 205K tokens, up to 131K output tokens per request. 14 providers sell it. The lowest is DevPass (LLM Gateway): $0.2 input, $1 output. This model is marked as deprecated.

- Type: Text
- Context: 205K
- Max output: 131K
- Released: 2025-10-27
- Open weights: Yes

## Price by provider (USD per 1M tokens)

| Provider | Model id | Input | Output | Cached | Notes |
| --- | --- | --- | --- | --- | --- |
| [MiniMax (minimax.io)](https://platform.minimax.io/docs/guides/quickstart) | MiniMax-M2 | $0.3 | $1.2 | — | Official, Deprecated |
| [DevPass (LLM Gateway)](https://llmgateway.io/docs) | minimax-m2 | $0.2 | $1 | $0.03 | Lowest |
| [LLM Gateway](https://llmgateway.io/docs) | minimax/minimax-m2 | $0.2 | $1 | $0.03 |  |
| [Eden AI](https://docs.edenai.co) | minimax/MiniMax-M2 | $0.3 | $1.2 | — |  |
| [Hugging Face](https://huggingface.co/docs/inference-providers) | MiniMaxAI/MiniMax-M2 | $0.3 | $1.2 | — |  |
| [Merge Gateway](https://docs.merge.dev/merge-gateway) | minimax/minimax-m2 | $0.3 | $1.2 | $0.03 |  |
| [Ofox](https://ofox.ai/docs) | minimax/minimax-m2 | $0.3 | $1.2 | $0.03 |  |
| [Vercel AI Gateway](https://github.com/vercel/ai/tree/5eb85cc45a259553501f535b8ac79a77d0e79223/packages/gateway) | minimax/minimax-m2 | $0.3 | $1.2 | $0.03 |  |
| [ZenMux](https://docs.zenmux.ai) | minimax/minimax-m2 | $0.3 | $1.2 | $0.03 |  |
| [302.AI](https://doc.302.ai) | MiniMax-M2 | $0.33 | $1.32 | — |  |
| [NanoGPT](https://docs.nano-gpt.com) | minimax/minimax-m2 | $0.17 | $1.53 | $0.085 |  |
| [Cortecs](https://api.cortecs.ai/v1/models) | minimax-m2 | $0.349 | $1.405 | — |  |
| [Amazon Bedrock](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) | minimax.minimax-m2 | $0.3 | $1.2 | — | Deprecated |
| [Qiniu](https://developer.qiniu.com/aitokenapi) | minimax/minimax-m2 | $0.304348 | $1.217391 | — | Deprecated |

Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.

Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.

https://apibook.ai/models/minimax/minimax-m2/