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?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.