OCRRouter

Kraken vs Chandra

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 and need ALTO or PageXML output. Pick Chandra for multilingual scanned documents, PDF to Markdown for RAG, and pages with tables, forms and math. Kraken is a trainable toolkit for archives; Chandra is a ready-made model that converts pages to Markdown, HTML or JSON.

Krakenkraken/krakenChandradatalab/chandra
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page2.0 s / page
Best forHistorical documents and manuscriptsComplex layouts and handwriting
InputsimagesPDF, images
LanguagesMany scripts, incl. right-to-left40+ languages
Max pages per request500500
TablesNo✓ Yes
Handwriting✓ Yes✓ Yes
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNo✓ Yes
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 are transcribing historical manuscripts or early prints and want to train layout analysis, reading order and recognition on your own material.
  • You work with Arabic, Hebrew or other right-to-left, BiDi or top-to-bottom scripts.
  • You need ALTO, PageXML, abbyyXML or hOCR output for digital humanities tools, with community-trained models on Zenodo.

Choose Chandra if

  • You need PDF to Markdown, HTML or JSON for RAG pipelines, with bounding boxes and labels per block.
  • You process multilingual scans, where Chandra 2 averages 77.8% across 43 languages in the authors' benchmark.
  • You want a hosted option: the Datalab API costs $1, $3 or $7.50 per 1,000 pages, and the free tier gives $20 a month.

Key differences

KrakenChandra
LicenceApache-2.0Code Apache-2.0; weights modified OpenRAIL-M, free for research, personal use and companies under $2M funding or revenue
How you run itPython library via pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13). No Windows support.Self-host with vLLM or Hugging Face on an NVIDIA GPU, or use the hosted Datalab API
PriceFree, self-hosted (you pay for compute)Self-hosted free within licence terms. Hosted API $1, $3 or $7.50 per 1,000 pages.
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesMarkdown, HTML, JSON, bounding boxes
BenchmarksNot publishedolmOCR-bench overall 85.8 (Chandra 2, authors' table); 72.7% average on a 90-language benchmark
Setup effortUsually needs training on your own material for good accuracyWorks as a model with no training step; about 1.44 pages/s on one H100 with vLLM
Known failureInstall fails with a dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820)Token-loop hallucinations on some Russian and Kazakh scans (issue #51); weak on Urdu (43.2%) and Sanskrit (51.1%); Old Scans only 51.1 on olmOCR-bench

Sources

What each one is

Kraken

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

Kraken details

Chandra

Datalab's OCR model that keeps layout and handles forms, tables and handwriting.

Chandra 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": ["datalab/chandra"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Kraken alternativesChandra alternativesBest OCR models in 2026