# Mistral Ocr API Pricing

As of October 10, 2026, Mistral Ocr costs $2.00 per 1K pages on Mistral AI. Across 3 providers on LiteLLM, the price ranges from $0.50 to $4.00.

- Page: https://models.litellm.ai/models/mistral-ocr
- Lab: Mistral AI
- LiteLLM model name: `mistral/mistral-ocr-2512`
- Added to LiteLLM: October 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 |
|---|---|---|---|---|---|---|---|
| Mistral AI (snapshot 2512) | `mistral/mistral-ocr-2512` | – | – | – | – | – | – |
| Mistral AI (latest alias) | `mistral/mistral-ocr-latest` | – | – | – | – | – | – |
| Azure AI Foundry (snapshot 2505) | `azure_ai/mistral-ocr-2505` | – | – | – | – | – | – |
| Azure AI Foundry (snapshot 2512) | `azure_ai/mistral-ocr-2512` | – | – | – | – | – | – |
| Google Vertex AI (snapshot 2505) | `vertex_ai/mistral-ocr-2505` | – | – | – | – | – | – |

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="mistral/mistral-ocr-2512",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Mistral Ocr cost?

Mistral Ocr costs $2.00 per 1K pages on Mistral AI. Across 3 providers on LiteLLM, the price ranges from $0.50 to $4.00.

### Which providers offer Mistral Ocr?

Mistral Ocr is available from 3 providers through LiteLLM: Mistral AI, Azure AI Foundry and Google Vertex AI. The lowest price is on Google Vertex AI.

### How do I call Mistral Ocr with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="mistral/mistral-ocr-2512", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/ocr from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### When did LiteLLM add Mistral Ocr?

Mistral Ocr was added to LiteLLM's model price file in October 2025.

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