OCRRouter

Kraken vs Unstructured

Pick Kraken for historical manuscripts, early prints and right-to-left scripts such as Arabic and Hebrew, where you can train layout and recognition on your own material. Pick Unstructured for ingesting mixed file types such as PDFs, Word, PowerPoint, HTML, emails and images into a RAG pipeline. The main split is the job: Kraken is a trainable recogniser for hard scripts, while Unstructured is an ingestion tool for modern files.

Krakenkraken/krakenUnstructuredunstructured/unstructured
TypeOpen sourceOCR API
Price1 credit / page20 credits / page
Per 1,000 pages$1.00$20.00
Typical speed1.5 s / page3.0 s / page
Best forHistorical documents and manuscriptsMixed file types into RAG
InputsimagesPDF, images, DOCX
LanguagesMany scripts, incl. right-to-leftMultilingual
Max pages per request5001,000
TablesNo✓ Yes
Handwriting✓ YesNo
MathNoNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
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

  • You work with historical manuscripts or early prints, which is what Kraken is built for.
  • You need Arabic, Hebrew or other right-to-left, BiDi or top-to-bottom scripts.
  • You want ALTO, PageXML, abbyyXML or hOCR output for digital humanities tools, and trainable layout analysis, reading order and character recognition.

Choose Unstructured if

  • You need one library for PDFs, HTML, Word, PowerPoint, emails and images, with many connectors.
  • You want a hosted API with the first 10,000 pages free, then $0.015 per page, or a free Apache-2.0 library to self-host.
  • You process born-digital PDFs and want the Fast strategy, or want to choose between Auto, Fast, High-Res and VLM to trade speed for quality.

Key differences

KrakenUnstructured
LicenceApache-2.0Apache-2.0 for the open-source library; proprietary for the hosted platform
How you run itLocal library installed with pip on Linux or macOS, x64 or ARM, Python 3.10 to 3.13. No Windows support.Self-hosted Python library or hosted API
PriceFree, self-hosted (you pay for compute)Hosted: first 10,000 pages free, then $0.015 per page. Business plan is custom. Library is free.
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesJSON, HTML, plain text, bounding boxes
Best document typesHistorical manuscripts, early prints, non-Latin scriptsMixed file types for RAG, born-digital PDFs
TablesNot publishedOpen-source table cell content scores 0.426 versus 0.866 hosted (vendor's own benchmark). hi_res tables can cut off at edges and drop first letters. Table OCR ignores language settings.
Known failureInstall can fail with a dependency conflict (issue #816). Learned line order is lost in segmentation and text output (issue #820). Usually needs training on your own material.Library sends usage telemetry by default. Extra Tesseract pass on tables adds processing time.

Sources

What each one is

Kraken

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

Kraken details

Unstructured

Document ETL for RAG. Partitions many file types into typed elements; open-source library too.

Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Kraken alternativesUnstructured alternativesBest OCR models in 2026