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/kraken | Nanonets-OCRnanonets/nanonets-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 1.5 s / page | 1.8 s / page |
| Best for | Historical documents and manuscripts | Markdown with semantic tags |
| Inputs | images | PDF, images |
| Languages | Many scripts, incl. right-to-left | Multilingual |
| Max pages per request | 500 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | ✓ Yes |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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
| Kraken | Nanonets-OCR | |
|---|---|---|
| Main target | Historical documents and non-Latin scripts | Printed business documents and PDFs to Markdown |
| How you run it | Python library installed with pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13); no Windows support | Self-hosted model weights from Hugging Face, fine-tuned from Qwen2.5-VL-3B |
| Licence | Apache-2.0 | Not stated on the OCR2-3B model card; base model is Qwen2.5-VL-3B |
| Price | Free, self-hosted (you pay for compute) | Free, self-hosted (you pay for compute) |
| Output formats | ALTO, PageXML, hOCR, plain text, bounding boxes | Markdown, HTML, LaTeX, Mermaid |
| Training and prompting | Layout analysis, reading order and recognition are trainable; usually needs training on your own material for good accuracy | Trained on a fixed prompt; the team says hallucination with other prompts is expected |
| Known problems | Install 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
- Kraken GitHub README
- Kraken docs
- Zenodo OCR models
- Issue #820
- Nanonets-OCR2-3B model card
- HF discussion fixed prompt
What each one is
Kraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken detailsNanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-OCR detailsTry both on your own file
Run the file once with each model and compare the output.
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