Jina OCR vs Chunkr
Pick Jina OCR for non-commercial PDF to Markdown work, research and evaluation, where it has published scores: 91.14 on OmniDocBench v1.6 and 83.4 on olmOCR-Bench. Pick Chunkr when you need layout analysis, bounding boxes and semantic chunking for RAG over PDFs, slides, Word files and images. Licensing is the other big split: Jina OCR is CC-BY-NC-4.0 and needs a license for commercial use, while Chunkr is AGPL-3.0 with a commercial license option.
Jina OCRjina/jina-ocr | 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 | Clean Markdown at low cost | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | About 100 languages | Multilingual |
| Max pages per request | 200 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ 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 Jina OCR if
- You want a model with published benchmark scores: 91.14 on OmniDocBench v1.6 (reported by the authors) and 83.4 on olmOCR-Bench, 7.4 points above DeepSeek-OCR.
- You need Markdown, HTML or LaTeX output from a model with about 570M active parameters, which runs at 2.57 pages per second on an A100.
- Your use is non-commercial or research, so the CC-BY-NC-4.0 licence is not a blocker.
Choose Chunkr if
- You are building RAG and need semantic chunking plus OCR with bounding boxes, not only page-to-Markdown.
- Your inputs include PPT, Word and images as well as PDF, and you want HTML, Markdown or JSON out.
- You want to self-host through Docker with GPU, CPU-only or Mac ARM options and connect any OpenAI-compatible LLM endpoint.
Key differences
| Jina OCR | Chunkr | |
|---|---|---|
| Licence | CC-BY-NC-4.0; commercial use needs a license from Jina/Elastic | AGPL-3.0 or commercial license; closed-source use needs the commercial license |
| How you run it | Self-host the open-weight model or call Jina's hosted API | Cloud API or self-host via Docker (GPU, CPU-only, Mac ARM) |
| What it is | Page-to-Markdown model, 3B MoE (about 570M active parameters) | Document parsing service: layout analysis, OCR with bounding boxes, semantic chunking |
| Output formats | Markdown, HTML, LaTeX | HTML, Markdown, JSON, bounding boxes |
| Benchmarks | OmniDocBench v1.6 overall 91.14 (authors); olmOCR-Bench overall 83.4 | Not published |
| Cost | Free self-hosted for non-commercial use; you pay for compute | Open-source version free self-hosted (you pay for compute and an LLM endpoint); hosted credit-based plans, prices not published |
| Known limits | Hosted API returns HTTP 503 on cold start; retry after 30 to 60 seconds. Reported scores use a stricter prompt than the recommended default. | Open-source version uses community models, less accurate than the cloud's in-house models. No Excel support in the open-source version. Self-host needs an external LLM endpoint. |
Sources
What each one is
Jina OCR
Compact page-to-Markdown model from Jina AI, built on the DeepSeek-OCR encoder.
Jina OCR 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": "jina/jina-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Jina OCR alternativesChunkr alternativesBest OCR models in 2026