# MiniMax M2.7 Highspeed API Pricing

As of October 10, 2026, MiniMax M2.7 Highspeed costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on Novita AI, with cache reads at $0.06 per 1M tokens. It has a 204,800-token context window and returns up to 131,072 tokens per response.

- Page: https://models.litellm.ai/models/minimax-m2.7-highspeed
- Lab: MiniMax
- LiteLLM model name: `novita/minimax/minimax-m2.7-highspeed`
- Context window: 204,800 tokens
- Max output: 131,072 tokens
- Added to LiteLLM: August 27, 2026
- 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 |
|---|---|---|---|---|---|---|---|
| Novita AI | `novita/minimax/minimax-m2.7-highspeed` | $0.60 | $2.40 | $0.06 | – | – | 200K |

## Cost examples

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

- Novita AI: $2.40

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

- Novita AI: $6.48

## Features

Supported: Function calling, Structured output, Reasoning, Prompt caching.
Not supported: Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="novita/minimax/minimax-m2.7-highspeed",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does MiniMax M2.7 Highspeed cost?

MiniMax M2.7 Highspeed costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on Novita AI, with cache reads at $0.06 per 1M tokens.

### What is the context window of MiniMax M2.7 Highspeed?

MiniMax M2.7 Highspeed has a 204,800-token context window and returns up to 131,072 tokens per response.

### Which providers offer MiniMax M2.7 Highspeed?

MiniMax M2.7 Highspeed is available from Novita AI through LiteLLM, using the model name novita/minimax/minimax-m2.7-highspeed.

### How do I call MiniMax M2.7 Highspeed with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="novita/minimax/minimax-m2.7-highspeed", 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 M2.7 Highspeed support?

MiniMax M2.7 Highspeed supports function calling, structured output, reasoning and prompt caching. It does not support image input.

### When did LiteLLM add MiniMax M2.7 Highspeed?

MiniMax M2.7 Highspeed was added to LiteLLM's model price file on August 27, 2026.

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