Kraken vs Chunkr
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 Chunkr for parsing PDFs, slides and Word files into Markdown, HTML or JSON chunks for RAG. The main split is the job: Kraken transcribes hard historical material, Chunkr turns modern documents into structured output.
Krakenkraken/kraken | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 1 credit / page | 14 credits / page |
| Per 1,000 pages | $1.00 | $14.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Historical documents and manuscripts | Layout-aware chunks for RAG |
| Inputs | images | PDF, images, DOCX |
| Languages | Many scripts, incl. right-to-left | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | No | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| 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 Kraken if
- Your material is historical manuscripts or early prints, or non-Latin scripts with right-to-left, BiDi or top-to-bottom support.
- You need ALTO, PageXML, abbyyXML or hOCR output for digital humanities tools.
- You want to train layout analysis, reading order and character recognition yourself, and can start from community models on Zenodo.
Choose Chunkr if
- You are chunking PDFs, PPT, Word files or images for RAG and want Markdown, HTML or JSON with bounding boxes.
- You want a hosted cloud API, or a self-hosted version you run with Docker on GPU, CPU-only or Mac ARM.
- You run on Windows-based or mixed teams' infrastructure via Docker, or already have an OpenAI-compatible LLM endpoint to plug in.
Key differences
| Kraken | Chunkr | |
|---|---|---|
| Best for | Historical manuscripts, early prints, Arabic, Hebrew and other RTL scripts | RAG chunking of PDFs and slides, self-hosted layout parsing |
| Licence | Apache-2.0 | AGPL-3.0 or commercial licence; closed-source use needs the commercial one |
| How you run it | Python library installed with pip, run locally | Cloud API, or self-host via Docker with an external OpenAI-compatible LLM endpoint |
| Price | Free, self-hosted (you pay for compute) | Hosted credit-based plans, prices not verified; open-source version free (you pay for compute and an LLM endpoint) |
| Output formats | ALTO, PageXML, hOCR, plain text, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Platform and input | Linux or macOS, x64 or ARM, Python 3.10 to 3.13; no Windows support | Accepts PDF, PPT, Word and images; Excel not supported in the open-source version |
| Known issues | Install dependency conflict (issue #816); learned line order lost in segmentation and text output (issue #820); usually needs training for good accuracy | Open-source version uses community models, less accurate than the cloud's in-house models |
Sources
What each one is
Kraken
OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.
Kraken detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Kraken alternativesChunkr alternativesBest OCR models in 2026