OCRRouter

Kraken vs Nougat

Pick Kraken for historical manuscripts, early prints and non-Latin or right-to-left scripts, especially when you can train it on your own material. Pick Nougat for English scientific papers where you need LaTeX math and tables in Markdown, but only for non-commercial work. The main split is document type: Kraken targets historical and non-Latin material, Nougat targets arXiv-style papers.

Krakenkraken/krakenNougatmeta/nougat
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forHistorical documents and manuscriptsarXiv-style papers
InputsimagesPDF, images
LanguagesMany scripts, incl. right-to-leftMainly English
Max pages per request500200
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose Kraken if

  • Your material is historical manuscripts or early prints, which is what Kraken is built for.
  • You need Arabic, Hebrew or other right-to-left scripts, with BiDi and top-to-bottom support.
  • You want ALTO, PageXML or hOCR output for digital humanities tools, and you can train layout analysis, reading order and recognition on your own data.

Choose Nougat if

  • Your input is English scientific papers, since Nougat was trained on arXiv and PubMed Central documents.
  • You need equations and tables as LaTeX inside Mathpix-compatible Markdown.
  • You want a small or base checkpoint with a simple CLI and API, and your use is non-commercial.

Key differences

KrakenNougat
LicenceApache-2.0Code MIT; weights CC-BY-NC, so no commercial use
How you run itPython library, installed via pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13). No Windows support.Self-hosted Python package with a CLI and API; small and base checkpoints
PriceFree, self-hosted (you pay for compute)Free for non-commercial use, self-hosted (you pay for compute)
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesMarkdown (.mmd) and LaTeX
Target documentsHistorical manuscripts, early prints, non-Latin scriptsEnglish arXiv-style scientific papers, math-heavy PDFs
LanguagesRight-to-left, BiDi and top-to-bottom scripts supportedWorks best on English; Chinese, Russian and Japanese do not work
Known failureUsually needs training on your own material; install dependency conflict (issue #816); learned line order lost in segmentation and text output (issue #820)Repetition loops on 1.5% of test pages, more on out-of-domain documents; repetition detection can drop pages as MISSING_PAGE (issue #11)

Sources

What each one is

Kraken

OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.

Kraken details

Nougat

Meta's model that converts academic PDFs to Markdown with LaTeX math.

Nougat details

Try 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": "kraken/kraken","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Kraken alternativesNougat alternativesBest OCR models in 2026