# Pixtral 12B API Pricing

As of October 10, 2026, Pixtral 12B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens from Vercel AI Gateway, the lowest of 3 providers. It has a 128,000-token context window and returns up to 4,000 tokens per response.

- Page: https://models.litellm.ai/models/pixtral-12b
- Lab: Mistral AI
- LiteLLM model name: `vercel_ai_gateway/mistral/pixtral-12b`
- Context window: 128,000 tokens
- Max output: 4,000 tokens
- Added to LiteLLM: October 2024
- 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 |
|---|---|---|---|---|---|---|---|
| Vercel AI Gateway | `vercel_ai_gateway/mistral/pixtral-12b` | $0.15 | $0.15 | – | – | – | 128K |
| IBM watsonx.ai (snapshot 2409) | `watsonx/mistralai/pixtral-12b-2409` | $0.35 | $0.35 | – | – | – | 128K |
| Scaleway (snapshot 2409) | `scaleway/mistralai/pixtral-12b-2409` | $0.20 | $0.20 | – | – | – | 128K |

## Cost examples

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

- Vercel AI Gateway: $0.375
- Scaleway: $0.50
- IBM watsonx.ai: $0.875

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

- Vercel AI Gateway: $1.53
- Scaleway: $2.04
- IBM watsonx.ai: $3.57

## Features

Supported: Function calling, Structured output, Image input.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="vercel_ai_gateway/mistral/pixtral-12b",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Pixtral 12B cost?

Pixtral 12B costs $0.15 per 1M input tokens and $0.15 per 1M output tokens from Vercel AI Gateway, the lowest of 3 providers.

### What is the context window of Pixtral 12B?

Pixtral 12B has a 128,000-token context window and returns up to 4,000 tokens per response.

### Which providers offer Pixtral 12B?

Pixtral 12B is available from 3 providers through LiteLLM: Vercel AI Gateway, IBM watsonx.ai and Scaleway. The lowest price is on Vercel AI Gateway.

### How do I call Pixtral 12B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="vercel_ai_gateway/mistral/pixtral-12b", 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 Pixtral 12B support?

Pixtral 12B supports function calling, structured output and image input.

### When did LiteLLM add Pixtral 12B?

Pixtral 12B was added to LiteLLM's model price file in October 2024.

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