# MiniMax M2 API Pricing

As of October 10, 2026, MiniMax M2 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.03 and cache writes at $0.375 per 1M tokens. It has a 200,000-token context window and returns up to 8,192 tokens per response.

- Page: https://models.litellm.ai/models/minimax-m2
- Lab: MiniMax
- LiteLLM model name: `minimax/MiniMax-M2`
- Context window: 200,000 tokens
- Max output: 8,192 tokens
- Added to LiteLLM: November 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| MiniMax | `minimax/MiniMax-M2` | $0.30 | $1.20 | $0.03 | – | – | 200K |
| Amazon Bedrock | `minimax.minimax-m2` | $0.30 | $1.20 | – | – | – | 1M |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/minimax-m2` | $0.30 | $1.20 | – | – | – | 4K |
| Google Vertex AI | `vertex_ai/minimaxai/minimax-m2-maas` | $0.30 | $1.20 | $0.03 | – | – | 192K |
| Novita AI | `novita/minimax/minimax-m2` | $0.30 | $1.20 | $0.03 | – | – | 200K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- MiniMax: $1.20
- Amazon Bedrock: $1.20
- Fireworks AI: $1.20
- Google Vertex AI: $1.20

100 long-document requests with 100,000 input and 2,000 output tokens each:

- MiniMax: $3.24
- Amazon Bedrock: $3.24
- Fireworks AI: $3.24
- Google Vertex AI: $3.24

## Features

Supported: Function calling, Parallel tool calls, Structured output, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="minimax/MiniMax-M2",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does MiniMax M2 cost?

MiniMax M2 costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on MiniMax, with cache reads at $0.03 and cache writes at $0.375 per 1M tokens.

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

MiniMax M2 has a 200,000-token context window and returns up to 8,192 tokens per response.

### Which providers offer MiniMax M2?

MiniMax M2 is available from 5 providers through LiteLLM: MiniMax, Amazon Bedrock, Fireworks AI, Google Vertex AI and Novita AI.

### How do I call MiniMax M2 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="minimax/MiniMax-M2", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does MiniMax M2 support?

MiniMax M2 supports function calling, parallel tool calls, structured output, reasoning and prompt caching.

### When did LiteLLM add MiniMax M2?

MiniMax M2 was added to LiteLLM's model price file in November 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json