Jina OCR vs Unstructured
Pick Jina OCR for non-commercial or research work that turns PDF pages into Markdown, HTML or LaTeX. Pick Unstructured for ingesting mixed file types such as Word, PowerPoint, emails and HTML into a RAG pipeline, with the hosted platform if you need accurate tables. The main split is licence and scope: Jina OCR is CC-BY-NC-4.0 and needs a deal for commercial use, while the Unstructured library is Apache-2.0.
Jina OCRjina/jina-ocr | Unstructuredunstructured/unstructured | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 1 credit / page | 20 credits / page |
| Per 1,000 pages | $1.00 | $20.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Clean Markdown at low cost | Mixed file types into 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 | No |
| 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
- It scores 91.14 on OmniDocBench v1.6 (authors) and 83.4 on olmOCR-Bench, 7.4 points above DeepSeek-OCR.
- It has only about 570M active parameters out of 3B MoE and runs at 2.57 pages per second on an A100.
- It outputs Markdown, HTML and LaTeX, which suits page-to-Markdown conversion for research and evaluation.
Choose Unstructured if
- It handles PDFs, HTML, Word, PowerPoint, emails and images in one library, so mixed-format ingestion needs no extra tools.
- The library is Apache-2.0 and has many connectors, and the hosted platform gives 10,000 free pages before $0.015 per page.
- Its Auto, Fast, High-Res and VLM strategies let you trade speed for quality, and Fast suits born-digital PDFs.
Key differences
| Jina OCR | Unstructured | |
|---|---|---|
| Licence | CC-BY-NC-4.0; commercial use needs a license from Jina/Elastic | Apache-2.0 for the open-source library; proprietary for the hosted platform |
| How you run it | Self-host the open weights or call Jina's hosted API | Self-host the Python library or use the hosted API |
| Price | Free self-hosted for non-commercial use, you pay for compute | Library is free; hosted is 10,000 free pages, then $0.015 per page; Business is custom |
| Output formats | Markdown, HTML, LaTeX | JSON, HTML, plain text, bounding boxes |
| Benchmarks | OmniDocBench v1.6 overall 91.14; olmOCR-Bench overall 83.4 (authors) | Table cell content 0.426 open-source vs 0.866 hosted (vendor's own benchmark) |
| Hardware | GPU recommended (A100 and L4 benchmarked); vLLM 0.21+ for FastMTP; falls back to CPU in Transformers | Not published |
| Known failure | Hosted API returns HTTP 503 on cold start; retry after 30 to 60 seconds | hi_res tables cut off at edges and drop first letters; table OCR ignores language settings |
Sources
- jina-ocr-v1 model card
- Jina model page
- Unstructured pricing
- Unstructured GitHub README
- Unstructured issue #3262
- Unstructured issue #1694
What each one is
Jina OCR
Compact page-to-Markdown model from Jina AI, built on the DeepSeek-OCR encoder.
Jina OCR detailsUnstructured
Document ETL for RAG. Partitions many file types into typed elements; open-source library too.
Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Jina OCR alternativesUnstructured alternativesBest OCR models in 2026