OCRRouter

Kraken vs Nanonets-OCR

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 Nanonets-OCR for modern printed business PDFs that you want as Markdown for an LLM, including signatures, checkboxes and flowcharts. The main split is document type: Kraken is a trainable toolkit for historical and non-Latin material, Nanonets-OCR is a fixed-prompt model for modern documents.

Krakenkraken/krakenNanonets-OCRnanonets/nanonets-ocr
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page1.8 s / page
Best forHistorical documents and manuscriptsMarkdown with semantic tags
InputsimagesPDF, images
LanguagesMany scripts, incl. right-to-leftMultilingual
Max pages per request500500
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ YesNo
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

  • Your material is historical manuscripts or early prints, which is what Kraken is built for.
  • You need right-to-left, BiDi or top-to-bottom scripts such as Arabic and Hebrew.
  • You want ALTO, PageXML or hOCR output for digital humanities tools, plus a Zenodo repository of community-trained models you can start from.

Choose Nanonets-OCR if

  • You have printed business documents with signatures, watermarks and checkboxes, which the model tags or converts to unicode symbols.
  • You want Markdown, HTML or LaTeX out, with flowcharts and org charts extracted as Mermaid code.
  • You want one pretrained 3B model with no training step, with a published DocVQA score of 89.43 for the OCR2-3B model.

Key differences

KrakenNanonets-OCR
Main targetHistorical documents and non-Latin scriptsPrinted business documents and PDFs to Markdown
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 model weights from Hugging Face, fine-tuned from Qwen2.5-VL-3B
LicenceApache-2.0Not stated on the OCR2-3B model card; base model is Qwen2.5-VL-3B
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)
Output formatsALTO, PageXML, hOCR, plain text, bounding boxesMarkdown, HTML, LaTeX, Mermaid
Training and promptingLayout analysis, reading order and recognition are trainable; usually needs training on your own material for good accuracyTrained on a fixed prompt; the team says hallucination with other prompts is expected
Known problemsInstall dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820)olmOCR-bench overall 69.5; not trained on handwriting and can hallucinate; generation loops seen in a handwriting test, with CER up to 2100%

Sources

What each one is

Kraken

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

Kraken details

Nanonets-OCR

Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.

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

Questions

More comparisons

Kraken alternativesNanonets-OCR alternativesBest OCR models in 2026