Unlimited OCR vs Unstructured
Pick Unlimited OCR for long PDFs such as reports and books that you want parsed in one request on your own NVIDIA GPU, under an MIT licence. Pick Unstructured when your pipeline ingests mixed file types (PDF, HTML, Word, PowerPoint, email, images) or you want a hosted API with 10,000 free pages. Unstructured's open-source library scores 0.426 on table cell content against 0.866 hosted, so use the hosted platform if tables matter.
Unlimited OCRbaidu/unlimited-ocr | Unstructuredunstructured/unstructured | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 20 credits / page |
| Per 1,000 pages | $2.00 | $20.00 |
| Typical speed | 1.2 s / page | 3.0 s / page |
| Best for | Books and very long documents | Mixed file types into RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 30+ languages | Multilingual |
| Max pages per request | 1,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| 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 in one request.
- It is MIT licensed, which allows commercial use with no copyleft.
- It outputs Markdown, plain text and bounding boxes, with block types alongside the text.
Choose Unstructured if
- It handles PDFs, HTML, Word, PowerPoint, emails and images in one library, with many connectors.
- The hosted platform gives you the first 10,000 pages free, then $0.015 per page, and needs no GPU of your own.
- Its Auto, Fast, High-Res and VLM strategies let you trade speed for quality, and Fast suits born-digital PDFs.
Key differences
| Unlimited OCR | Unstructured | |
|---|---|---|
| Licence | MIT | Apache-2.0 for the open-source library; proprietary for the hosted platform |
| How you run it | Self-host with vLLM, SGLang or transformers on an NVIDIA GPU with CUDA 12.9 or 13.0; also offered hosted in Baidu Cloud | Self-host the Python library or use the hosted API |
| Price | Free to self-host, you pay for compute | Library free; hosted first 10,000 pages free, then $0.015 per page |
| Input types | Multi-page documents, parsed in one pass (40+ pages) | PDFs, HTML, Word, PowerPoint, emails and images |
| Output formats | Markdown, plain text, bounding boxes | JSON, HTML, plain text, bounding boxes |
| Tables | Not published | Table cell content 0.426 in the open-source library vs 0.866 hosted; hi_res tables can cut off at edges and drop first letters; table OCR ignores language settings |
| Known failure | Text repetition and looping on some pages, reports of hallucinated text, and a 32,768 token context cap; version 2 runs out of memory on 12 GB GPUs under SGLang | Extra Tesseract pass on tables adds processing time; the library sends usage telemetry by default |
Sources
- Hugging Face model card
- GitHub repo
- Issue #55 repetition
- Unstructured pricing
- Unstructured GitHub README
- Unstructured issue #3262
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 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": "baidu/unlimited-ocr","fallbacks": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR alternativesUnstructured alternativesBest OCR models in 2026