Reading · by Mistral AI
Mistral OCR
Turn PDFs into neat text, keeping tables and images.
document, image, link → text, data, image · document, data → data
- Way in
- Official APISign up yourself, api key
- To start
- $Mistral free/experiment tier (not checked)
- Runs
- In the cloud
- Checked
- Nov 3, 2026Prices as of that day
What it can do 2
Convert PDF or image to markdown with layout, tables and imagesdocument, image, link → text, data, image$4/1k pages (OCR 4.1, mistral-ocr-4-1 / -latest); $2/1k (OCR 3, mistral-ocr-2512); batch ~50% off
Extract structured fields to a JSON schema (annotations)document, data → data$5/1k annotated pages (OCR 4.1); $3/1k (OCR 3)
Prices and limits as of Nov 3, 2026, from Mistral AI’s own pages. They change; check before you rely on them.Not affiliated with Mistral AI. Not advice.Something wrong?