# Mistral AI: Mistral OCR 4.1

> Extracts text and tables from documents and images as Markdown. Available through the OCR endpoint and as the PDF parser's OCR model; billed per processed page.

- Model ID: `mistralai/mistral-ocr-4.1`
- Maker: Mistral AI (`mistralai`)
- Context length: -
- Input: files and images
- Output: OCR
- Capabilities: -
- Page: https://tokenlane.de/models/mistralai/mistral-ocr-4.1

## Providers

| Providers | Data centers | Sovereign EU | Zero data retention |
|---|---|---|---|
| Mistral AI | FR, SE, NO, NL, BE | no | no |

## Usage

- Base URL: `https://api.tokenlane.de/v1` (OpenAI- and OpenRouter-compatible)
- Authentication: `Authorization: Bearer $TOKENLANE_API_KEY`
- Guide: https://tokenlane.de/docs/guides/ocr.md?lang=en
- Machine-readable catalogue: `GET https://api.tokenlane.de/v1/models?output_modalities=all` (public, no key)
- Documentation index for agents: https://tokenlane.de/llms.txt

_Catalogue snapshot: 2026-11-19T13:10:34.963Z_
