OCRRouter

Kraken vs dots.ocr

Pick Kraken for historical manuscripts, early prints and right-to-left or other non-Latin scripts, where you can train layout and recognition on your own material and need ALTO or PageXML. Pick dots.ocr for modern multilingual PDFs, academic and business documents with mixed tables and text, where you want layout, Markdown, HTML tables and LaTeX formulas from one model. The main split is the material: Kraken is built for historical scripts and needs training, while dots.ocr parses contemporary documents but needs a CUDA GPU.

Krakenkraken/krakendots.ocrrednote/dots-ocr
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page1.5 s / page
Best forHistorical documents and manuscriptsMultilingual document parsing
InputsimagesPDF, images
LanguagesMany scripts, incl. right-to-left100+ languages
Max pages per request500500
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
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

  • Your material is historical manuscripts or early prints, which is what Kraken is built for.
  • 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, plus a public Zenodo repository of community-trained models.

Choose dots.ocr if

  • You convert multilingual business or academic PDFs to Markdown, with tables as HTML and formulas as LaTeX.
  • You want one 3B model that returns layout boxes, categories and text in a single pass, without training it first.
  • You need chart or diagram conversion to SVG through the dots.mocr-svg variant.

Key differences

Krakendots.ocr
Best forHistorical manuscripts, early prints, RTL and non-Latin scriptsMultilingual PDFs, academic and business documents with tables
LicenceApache-2.0MIT (the repository also includes a separate dots.ocr license agreement file)
How you run itPython library installed with pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13); no Windows supportSelf-hosted via vLLM or Hugging Face Transformers; single CUDA GPU with vLLM is the documented path, no VRAM figure stated
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesJSON, Markdown, HTML, LaTeX, bounding boxes, SVG
BenchmarksNot publishedolmOCR-bench 79.1 for dots.ocr and 83.9 for dots.mocr (1.5), reported by the authors
Known failureUsually needs training on your own material for good accuracy; install dependency conflict (issue #816); learned line order lost in segmentation and text output (issue #820)Runs of ellipses or underscores can make output repeat endlessly; complex tables and formulas remain difficult; a table above 1000 grid cells drops the whole page in Docling (issue #5146)

Sources

What each one is

Kraken

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

Kraken details

dots.ocr

Single vision model from rednote that does layout detection and content recognition together.

dots.ocr 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": ["rednote/dots-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Kraken alternativesdots.ocr alternativesBest OCR models in 2026