Unlimited OCR vs Nougat
Pick Unlimited OCR for long multi-page documents, bulk PDF to text for RAG, and anything you ship commercially, because it is MIT licensed and parses 40+ pages in one pass. Pick Nougat only for English arXiv-style papers where you need LaTeX math and tables, and only for non-commercial use, because its weights are CC-BY-NC.
Unlimited OCRbaidu/unlimited-ocr | Nougatmeta/nougat | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 3.0 s / page |
| Best for | Books and very long documents | arXiv-style papers |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | Mainly English |
| Max pages per request | 1,000 | 200 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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
- The MIT licence allows commercial use with no copyleft, while Nougat's weights are CC-BY-NC.
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go through in one request.
- It returns block types and bounding boxes with the text, which helps layout-aware extraction.
Choose Nougat if
- It is trained on arXiv and PubMed Central papers, so it fits English scientific papers.
- It outputs LaTeX for equations and tables in Mathpix-compatible .mmd Markdown, which suits math-heavy PDFs.
- It ships small and base checkpoints with a simple CLI and API.
Key differences
| Unlimited OCR | Nougat | |
|---|---|---|
| Licence | MIT | Code MIT; weights CC-BY-NC |
| Commercial use | Allowed | Not allowed with the weights |
| How you run it | Self-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR product | Self-hosted Python package only |
| Output formats | Markdown, plain text, bounding boxes | Markdown (.mmd) and LaTeX |
| Best document type | Long reports and books, bulk PDF to text for RAG | English arXiv-style scientific papers with heavy math |
| Hardware | NVIDIA GPU with CUDA 12.9 or 13.0; version 2 runs out of memory on 12 GB GPUs under SGLang | Not published |
| Known failure | Repetition and looping on some pages (issue #55), hallucinated text (issue #58), formatting mostly lost | Repetition loops on 1.5% of test pages, more on out-of-domain documents; pages can be dropped as MISSING_PAGE (issue #11); Chinese, Russian and Japanese do not work |
Sources
- Hugging Face model card
- GitHub repo
- Issue #55 repetition
- Nougat GitHub README
- Nougat paper
- Issue #11 repetitions
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 detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "baidu/unlimited-ocr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR vs DonutUnlimited OCR vs MonkeyOCRMinerU vs NougatGLM-OCR vs NougatUnlimited OCR vs dots.ocrUnlimited OCR vs Typhoon OCRUnlimited OCR vs UnstructuredUnlimited OCR vs Tesseract.js
Unlimited OCR alternativesNougat alternativesBest OCR models in 2026