Mistral AI · OCR
Mistral OCR 2512
Mistral OCR 3 is a document understanding model that extracts text and embedded images from PDFs and images with high fidelity, producing markdown output with HTML-based table reconstruction. Fully backward compatible with Mistral OCR 2.
- Maker's price
- $0.002 /page
- Max context
- 16K
- Listings
- 10
- Providers
- 5
Evidence and sources
Maker HQ: FR (according to Mistral AI's own website)
Advantages and trade-offs
Compared with 10 representative OCR models
Advantages
Input & output
as stated by the model's providersText
Images
Text
Also known as: azure_ai/mistral-ocr-2512, mistral-ocr-3, mistral-ocr-3-0, mistral/mistral-ocr-2512, mistral/mistral-ocr-3, mistral/mistral-ocr-3-0
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works