OCRmyPDF vs Pixtral
Pick OCRmyPDF to make scanned PDFs searchable and keep them as PDF/A archives. Pick Pixtral only if you already run it on the Mistral API and need question answering over charts and documents, since Mistral marks it deprecated. The main split is that OCRmyPDF adds a text layer to the PDF, while Pixtral reads images and returns text, Markdown or JSON.
OCRmyPDFocrmypdf/ocrmypdf | Pixtralmistral/pixtral | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 1.0 s / page | 3.0 s / page |
| Best for | Searchable PDFs from scans | Questions about document images |
| Inputs | PDF, images | images |
| Languages | 100+ languages (via Tesseract) | Multilingual |
| Max pages per request | 1,000 | 500 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose OCRmyPDF if
- You need validated searchable PDF/A output for archiving, with the OCR layer inserted losslessly where possible.
- You want a free, CPU-only tool under MPL-2.0 that spreads work across all cores and covers 100+ languages through Tesseract language packs.
- You run an office scanner pipeline and only need a text layer, not layout, tables or Markdown.
Choose Pixtral if
- You need Markdown or JSON output, or question answering over charts and documents (DocVQA 90.7 ANLS, ChartQA 81.8, as reported by Mistral).
- You already have an integration on the Mistral API, where launch pricing was $0.15 per million input and output tokens.
- You want Apache-2.0 open weights, and a 128K token context that allows many images per request.
Key differences
| OCRmyPDF | Pixtral | |
|---|---|---|
| What it is | Command-line tool that adds a Tesseract OCR text layer to scanned PDFs | 12.4B vision language model (12B decoder plus 400M vision encoder) from Mistral AI |
| Licence | MPL-2.0 | Apache-2.0 |
| How you run it | Local library, CPU only, uses all CPU cores | Mistral API (pixtral-12b-2409) or self-hosted open weights |
| Price | Free, self-hosted (you pay for compute) | $0.15 per million input and output tokens at launch on the Mistral API; free to self-host (you pay for compute) |
| Output formats | Searchable PDF (PDF/A by default), plain text | Plain text, Markdown, JSON |
| Benchmarks | Not published | DocVQA 90.7 ANLS, ChartQA 81.8 (CoT), MMMU 52.5 (CoT), all from Mistral |
| Known failure | --skip-text with default PDF/A output removes form fields (issue #1790); --deskew --clean-final can double or quadruple file size (issue #948); hangs on PDFs whose forms share one Resources dictionary (issue #1763) | Deprecated and no longer maintained; an HN launch thread user said it doesn't always get OCR anywhere near correct; reported accuracy drop on handwriting, small fonts and non-Latin scripts |
Sources
- OCRmyPDF GitHub README
- Issue #1790 form fields
- Issue #948 file size
- Mistral announcement
- Mistral Sept 2024 pricing
- HN launch thread
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsPixtral
Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.
Pixtral detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "ocrmypdf/ocrmypdf","fallbacks": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
OCRmyPDF alternativesPixtral alternativesBest OCR models in 2026