Unlimited OCR vs Kraken
Pick Unlimited OCR for modern long documents such as reports and books that you want as Markdown or text with bounding boxes, for example bulk PDF to text for RAG. Pick Kraken for historical manuscripts, early prints and non-Latin or right-to-left scripts, where you can train layout and recognition on your own material. The main split is document type: Unlimited OCR parses 40+ pages in one pass on a CUDA GPU, while Kraken is a trainable toolkit for archive and digital humanities work.
Unlimited OCRbaidu/unlimited-ocr | Krakenkraken/kraken | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 1.2 s / page | 1.5 s / page |
| Best for | Books and very long documents | Historical documents and manuscripts |
| Inputs | PDF, images | images |
| Languages | 30+ languages | Many scripts, incl. right-to-left |
| Max pages per request | 1,000 | 500 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| 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 Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go through in one request.
- It is MIT licensed, which allows commercial use with no copyleft, and Baidu Cloud also offers a hosted endpoint.
- It returns Markdown, plain text and bounding boxes, with block types alongside the text.
Choose Kraken if
- It is built for historical documents and non-Latin scripts, with right-to-left, BiDi and top-to-bottom support.
- Layout analysis, reading order and character recognition are all trainable on your own material.
- It outputs ALTO, PageXML, abbyyXML and hOCR used by digital humanities tools, and a public Zenodo repository holds community-trained models.
Key differences
| Unlimited OCR | Kraken | |
|---|---|---|
| Best document types | Long reports and books, bulk PDF to text for RAG | Historical manuscripts, early prints, Arabic, Hebrew and other RTL scripts |
| Licence | MIT | Apache-2.0 |
| How you run it | Self-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud | Python library installed with pip, run locally |
| Hardware and OS | NVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs | Linux or macOS, x64 or ARM, Python 3.10 to 3.13; no Windows support |
| Output formats | Markdown, plain text, bounding boxes | ALTO, PageXML, hOCR, plain text, bounding boxes |
| Benchmarks | ParseBench mean 46.17 (independent); Unlimited OCR 2 scores 84.6 on MPDocBench and 77.1 on MarathonDocBench (authors) | Not published |
| Known failure modes | Text repetition and looping on some pages, reports of hallucinated text, styling such as bold and italic mostly lost, 32,768 token context cap | Install can fail with a dependency conflict, learned line order is lost in segmentation and text output, usually needs training on your own material for good accuracy |
Sources
- Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Issue #55 repetition
- Kraken GitHub README
- Kraken docs
- Issue #820
What each one is
Unlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR detailsKraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken 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": "baidu/unlimited-ocr","fallbacks": ["kraken/kraken"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesKraken alternativesBest OCR models in 2026