Mistral OCR vs Kraken
Pick Mistral OCR for high-volume PDF to Markdown and batch scanning of modern business documents through a hosted API. Pick Kraken for historical manuscripts, early prints and non-Latin scripts such as Arabic and Hebrew, where you can train your own models and run everything locally.
Mistral OCRmistral/mistral-ocr | Krakenkraken/kraken | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 1 credit / page |
| Per 1,000 pages | $25.00 | $1.00 |
| Typical speed | 0.9 s / page | 1.5 s / page |
| Best for | High-volume PDF to Markdown | Historical documents and manuscripts |
| Inputs | PDF, images | images |
| Languages | 100+ languages | Many scripts, incl. right-to-left |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| 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 Mistral OCR if
- It is a hosted API at $2 per 1,000 pages, or $1 per 1,000 through the Batch API, so there is nothing to train or host.
- OCR 3 rebuilds tables as HTML with rowspan and colspan, and returns Markdown, HTML, JSON and extracted images.
- It suits RAG pipelines and batches of scanned business documents, with no setup beyond an API call.
Choose Kraken if
- It is built for historical documents and non-Latin scripts, with right-to-left, BiDi and top-to-bottom support.
- Layout analysis, reading order and character recognition are all trainable, and a public Zenodo repository holds community-trained models.
- It is Apache-2.0 and free to self-host, and it outputs ALTO, PageXML, abbyyXML and hOCR, which digital humanities tools use.
Key differences
| Mistral OCR | Kraken | |
|---|---|---|
| How you run it | Hosted API from Mistral AI (current version mistral-ocr-2512, OCR 3) | Python library installed with pip, run locally |
| Licence | Proprietary | Apache-2.0 |
| Price | $2 per 1,000 pages; $3 with structured annotations; $1 per 1,000 via Batch API | Free; you pay for your own compute |
| Output formats | Markdown, HTML, JSON, images | ALTO, PageXML, hOCR, plain text, bounding boxes |
| Best document types | PDFs for RAG, scanned business documents in batch | Historical manuscripts, early prints, Arabic, Hebrew and other RTL scripts |
| Benchmark | OmniDocBench v1.5: 78.83 (first version); v1.6: 85.66 | Not published |
| Known failure | Hallucinated text on unreadable handwriting; changed checkbox states and misread characters on a dense financial table page | No Windows support; install dependency conflict (issue #816); learned line order lost in text output (issue #820) |
Sources
- Mistral OCR 3 announcement
- OmniDocBench v1.6 leaderboard
- Reducto test of Mistral OCR
- Kraken GitHub README
- Zenodo OCR models
- Issue #820
What each one is
Mistral OCR
Fast document OCR that returns clean Markdown with tables and embedded images.
Mistral OCR detailsKraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "mistral/mistral-ocr","fallbacks": ["kraken/kraken"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral OCR vs TrOCRMistral OCR vs docTRGemini Flash vs KrakenKraken vs ERNIE 4.5 VLKraken vs MiniCPM-V 4.5Unlimited OCR vs KrakenMistral OCR vs RapidOCRMistral OCR vs DeepSeek-OCR
Mistral OCR alternativesKraken alternativesBest OCR models in 2026