Kraken vs Chandra
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 and need ALTO or PageXML output. Pick Chandra for multilingual scanned documents, PDF to Markdown for RAG, and pages with tables, forms and math. Kraken is a trainable toolkit for archives; Chandra is a ready-made model that converts pages to Markdown, HTML or JSON.
Krakenkraken/kraken | Chandradatalab/chandra | |
|---|---|---|
| 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 | 2.0 s / page |
| Best for | Historical documents and manuscripts | Complex layouts and handwriting |
| Inputs | images | PDF, images |
| Languages | Many scripts, incl. right-to-left | 40+ languages |
| Max pages per request | 500 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | ✓ Yes | ✓ Yes |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| 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
- You are transcribing historical manuscripts or early prints and want to train layout analysis, reading order and recognition on your own material.
- 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, with community-trained models on Zenodo.
Choose Chandra if
- You need PDF to Markdown, HTML or JSON for RAG pipelines, with bounding boxes and labels per block.
- You process multilingual scans, where Chandra 2 averages 77.8% across 43 languages in the authors' benchmark.
- You want a hosted option: the Datalab API costs $1, $3 or $7.50 per 1,000 pages, and the free tier gives $20 a month.
Key differences
| Kraken | Chandra | |
|---|---|---|
| Licence | Apache-2.0 | Code Apache-2.0; weights modified OpenRAIL-M, free for research, personal use and companies under $2M funding or revenue |
| How you run it | Python library via pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13). No Windows support. | Self-host with vLLM or Hugging Face on an NVIDIA GPU, or use the hosted Datalab API |
| Price | Free, self-hosted (you pay for compute) | Self-hosted free within licence terms. Hosted API $1, $3 or $7.50 per 1,000 pages. |
| Output formats | ALTO, PageXML, hOCR, plain text, bounding boxes | Markdown, HTML, JSON, bounding boxes |
| Benchmarks | Not published | olmOCR-bench overall 85.8 (Chandra 2, authors' table); 72.7% average on a 90-language benchmark |
| Setup effort | Usually needs training on your own material for good accuracy | Works as a model with no training step; about 1.44 pages/s on one H100 with vLLM |
| Known failure | Install fails with a dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820) | Token-loop hallucinations on some Russian and Kazakh scans (issue #51); weak on Urdu (43.2%) and Sanskrit (51.1%); Old Scans only 51.1 on olmOCR-bench |
Sources
- Kraken GitHub README
- Zenodo OCR models
- Issue #820
- Chandra GitHub README
- Datalab pricing
- GitHub issue #51 token loops
What each one is
Kraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken detailsChandra
Datalab's OCR model that keeps layout and handles forms, tables and handwriting.
Chandra 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": ["datalab/chandra"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Kraken alternativesChandra alternativesBest OCR models in 2026