# Mistral OCR

> Mistral document OCR model (Pixtral OCR) for PDF and image text recognition.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `mistral/mistral-ocr-latest`
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/mistral/mistral-ocr-latest
- Released: 2025-03-01
- Context: 1K tokens
- Input: image, pdf; output: text

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| OCR | $0.0044 | per page |

## Providers

Without a prefix each request goes to the best-priced healthy provider. To pin one, send the model as `<provider>:mistral/mistral-ocr-latest`.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| Mistral AI | `mistral:mistral/mistral-ocr-latest` | France | — | — | no |

Web page: https://www.ohmygpt.com/models/mistral/mistral-ocr-latest