Kraken vs GOT-OCR 2.0
Pick GOT-OCR 2.0 if you need a model that works on formulas, tables, charts and sheet music for English and Chinese documents. Pick Kraken if your material is historical manuscripts, early prints or right-to-left scripts, and you are willing to train it on your own pages. The main split is purpose: Kraken is a trainable toolkit for the humanities, GOT-OCR 2.0 is a general model with fixed capabilities.
Krakenkraken/kraken | GOT-OCR 2.0stepfun/got-ocr-2 | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 1.5 s / page | 1.5 s / page |
| Best for | Historical documents and manuscripts | Formatted text, formulas and charts |
| Inputs | images | images |
| Languages | Many scripts, incl. right-to-left | Chinese, English |
| Max pages per request | 500 | 100 |
| Tables | No | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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 source is historical manuscripts or early prints, which is what Kraken is built for.
- You need 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, and want to train layout, reading order and recognition on your own material.
Choose GOT-OCR 2.0 if
- You need formulas, tables, charts, sheet music or chemical structures read, with LaTeX, TikZ, SMILES or kern output.
- You want to OCR a specific region of a page by passing box coordinates or color.
- You work with English and Chinese documents and want multi-page OCR through Hugging Face Transformers with batched inference.
Key differences
| Kraken | GOT-OCR 2.0 | |
|---|---|---|
| Main purpose | Historical and non-Latin script material, with trainable layout analysis and recognition | Unified model for text, formulas, tables, charts and sheet music |
| Training needed | Usually needs training on your own material for good accuracy | No training step described; runs as a 580M-parameter model |
| Output formats | ALTO, PageXML, hOCR, plain text, bounding boxes | Plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Platform and hardware | Linux or macOS, x64 or ARM, Python 3.10 to 3.13; no Windows support | CUDA 11.8 and PyTorch 2.0.1 per README; CPU users pointed to a llama.cpp port |
| Licence | Apache-2.0 | Code Apache-2.0; training data CC BY-NC 4.0 |
| Benchmarks | Not published | Not published; README lists no benchmark scores |
| Known failure | Install dependency conflict (issue #816); learned line order lost in segmentation and text output (issue #820) | Output can loop characters midway (issue #226); wrong text on blank images (issue #235); format mode much worse than plain mode (issue #317) |
Sources
What each one is
Kraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken detailsGOT-OCR 2.0
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
GOT-OCR 2.0 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": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Kraken alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026