OCRRouter

Kraken vs SmolDocling

Pick Kraken for historical manuscripts, early prints and non-Latin or right-to-left scripts, where you can train layout analysis and recognition on your own material. Pick SmolDocling only for experiments with a tiny document VLM on English pages, since it is a preview release and its authors point users to Granite-Docling. The main split is the job: Kraken is a trainable toolkit for historical material, SmolDocling is a 256M model that converts modern-style pages to structured output.

Krakenkraken/krakenSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.5 s / page1.0 s / page
Best forHistorical documents and manuscriptsVery cheap page conversion
InputsimagesPDF, images
LanguagesMany scripts, incl. right-to-leftMainly English
Max pages per request500500
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
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 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, reading order and recognition on your own data.

Choose SmolDocling if

  • You want one 256M-parameter model that handles text, tables (OTSL), code, formulas and charts with location tags.
  • You need DocTags, Markdown, HTML, JSON or LaTeX output from English pages on modest hardware.
  • Speed matters in an experiment: about 0.35 seconds per page on an A100 with vLLM.

Key differences

KrakenSmolDocling
What it isOpen-source OCR system with trainable layout analysis and recognition256M-parameter document conversion VLM from Hugging Face and IBM that outputs DocTags for Docling
LicenceApache-2.0Apache-2.0 per the model summary; the metadata tag says CDLA-Permissive-2.0
How you run itPython library via pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13); no Windows supportSelf-hosted model; you pay for compute
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
LanguagesHistorical and non-Latin scripts, including right-to-left, BiDi and top-to-bottomEnglish only
BenchmarksNot publishedTable TEDS structure 0.82 on FinTabNet 150dpi, full-page OCR F1 0.80, OCRBench 338 (author-reported)
Known failureInstall can fail with a dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820)Endless token repetition and missing closing tags; output loops on some images, making generation very slow (Docling issue #1515)

Sources

What each one is

Kraken

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

Kraken details

SmolDocling

Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.

SmolDocling 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": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Kraken alternativesSmolDocling alternativesBest OCR models in 2026