# Fw MiniMax M2.5 API Pricing

As of October 10, 2026, Fw MiniMax M2.5 costs $0.33 per 1M input tokens and $1.32 per 1M output tokens on Azure AI Foundry, with cache reads at $0.033 per 1M tokens. It has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

- Page: https://models.litellm.ai/models/fw-minimax-m2.5
- LiteLLM model name: `azure_ai/FW-MiniMax-M2.5`
- Context window: 1,000,000 tokens
- Max output: 1,000,000 tokens
- Added to LiteLLM: August 14, 2026
- Deprecation date: July 1, 2027
- 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 |
|---|---|---|---|---|---|---|---|
| Azure AI Foundry | `azure_ai/FW-MiniMax-M2.5` | $0.33 | $1.32 | $0.033 | – | – | 1M |

## Cost examples

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

- Azure AI Foundry: $1.32

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

- Azure AI Foundry: $3.564

## Features

Supported: Function calling, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="azure_ai/FW-MiniMax-M2.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Fw MiniMax M2.5 cost?

Fw MiniMax M2.5 costs $0.33 per 1M input tokens and $1.32 per 1M output tokens on Azure AI Foundry, with cache reads at $0.033 per 1M tokens.

### What is the context window of Fw MiniMax M2.5?

Fw MiniMax M2.5 has a 1,000,000-token context window and returns up to 1,000,000 tokens per response.

### Which providers offer Fw MiniMax M2.5?

Fw MiniMax M2.5 is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/FW-MiniMax-M2.5.

### How do I call Fw MiniMax M2.5 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/FW-MiniMax-M2.5", 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 Fw MiniMax M2.5 support?

Fw MiniMax M2.5 supports function calling, reasoning and prompt caching.

### When did LiteLLM add Fw MiniMax M2.5?

Fw MiniMax M2.5 was added to LiteLLM's model price file on August 14, 2026.

### Is Fw MiniMax M2.5 being deprecated?

Azure AI Foundry lists a deprecation date of July 1, 2027 for azure_ai/FW-MiniMax-M2.5.

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