Mathpix Convert vs Kraken
Pick Kraken if you transcribe historical manuscripts, early prints or right-to-left scripts and are ready to train a model on your own material. Pick Mathpix Convert if you need math-heavy PDFs turned into LaTeX or DOCX through a hosted API with no setup. The main split is the target material: Kraken is built for historical and non-Latin scripts, Mathpix Convert for STEM content.
Mathpix Convertmathpix/convert | Krakenkraken/kraken | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 7 credits / page | 1 credit / page |
| Per 1,000 pages | $7.00 | $1.00 |
| Typical speed | 1.5 s / page | 1.5 s / page |
| Best for | Math and scientific papers | Historical documents and manuscripts |
| Inputs | PDF, images | images |
| Languages | 30+ languages | Many scripts, incl. right-to-left |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | No | ✓ 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 Mathpix Convert if
- It converts math, tables and chemistry to LaTeX, Markdown, DOCX and HTML.
- It exports whole PDFs straight to DOCX or LaTeX, and it handles handwritten equations.
- It is a hosted API at $0.005 per PDF page, so you need no local install or training.
Choose Kraken if
- It is built for historical documents and non-Latin scripts, with right-to-left, BiDi and top-to-bottom support.
- It is Apache-2.0 and free to self-host, so you pay only for compute.
- Layout analysis, reading order and character recognition are all trainable, and a public Zenodo repository holds community-trained models.
Key differences
| Mathpix Convert | Kraken | |
|---|---|---|
| Target material | STEM content: math, tables and chemistry | Historical manuscripts, early prints and non-Latin scripts |
| How you run it | Hosted API | Python library run locally on Linux or macOS (x64 or ARM, Python 3.10 to 3.13); no Windows support |
| Licence | Proprietary | Apache-2.0 |
| Price | PDF $0.005 per page (0-1M), $0.0035 above 1M; images $0.002 each; one-time $19.99 API key activation fee | Free, self-hosted (you pay for compute) |
| Output formats | LaTeX, Markdown, DOCX, HTML, JSON | ALTO, PageXML, hOCR, plain text, bounding boxes |
| Setup effort | Get an API key and call the API | Usually needs training on your own material for good accuracy |
| Known issues | Images with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrears; the $19.99 fee is non-refundable | Install can fail with a dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820) |
Sources
What each one is
Mathpix Convert
Specialist for math, science papers and handwritten formulas. Outputs LaTeX.
Mathpix Convert 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.
Use one, fall back to the other
{"model": "mathpix/convert","fallbacks": ["kraken/kraken"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mathpix Convert alternativesKraken alternativesBest OCR models in 2026