Nanonets-OCR vs Nougat
Pick Nougat for English arXiv-style papers with heavy math, but only for non-commercial work, because its weights are CC-BY-NC. Pick Nanonets-OCR for business documents with signatures, watermarks and checkboxes, or for flowcharts you want as Mermaid. Neither is built for handwriting or non-Latin scripts, and Nanonets-OCR's licence is not stated on its model card.
Nanonets-OCRnanonets/nanonets-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 | 1.8 s / page | 3.0 s / page |
| Best for | Markdown with semantic tags | arXiv-style papers |
| Inputs | PDF, images | PDF, images |
| Languages | Multilingual | Mainly English |
| Max pages per request | 500 | 200 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | ✓ Yes | 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 Nanonets-OCR if
- Your documents are business PDFs with signatures, watermarks and checkboxes, which it tags or converts to unicode symbols.
- You need flowcharts or org charts extracted as Mermaid code, or output as HTML as well as Markdown and LaTeX.
- You want printed PDFs turned into Markdown for LLMs and can accept a 3B model with an olmOCR-bench overall score of 69.5.
Choose Nougat if
- Your input is English scientific papers, since it was trained on arXiv and PubMed Central documents.
- You need math-heavy pages as LaTeX, with equations and tables in Mathpix-compatible .mmd Markdown.
- You want a simple CLI and API with small and base checkpoints, and your use is non-commercial.
Key differences
| Nanonets-OCR | Nougat | |
|---|---|---|
| Built for | Business documents with signatures, watermarks, checkboxes and flowcharts | Scientific PDF pages from arXiv-style papers |
| Licence | Not stated on the Nanonets-OCR2-3B model card (no licence tag) | Code MIT; weights CC-BY-NC, so no commercial use |
| How you run it | Self-host the weights from Hugging Face, fine-tuned from Qwen2.5-VL-3B | Self-hosted Python package with a CLI and API |
| Output formats | Markdown, HTML, LaTeX, Mermaid | Markdown (.mmd) and LaTeX |
| Benchmarks | olmOCR-bench overall 69.5, DocVQA 89.43, ChartQA 78.56 (OCR2-3B, reported by the authors) | Not published |
| Languages and handwriting | Not trained on handwriting and can hallucinate; handwriting test saw generation loops with CER up to 2100% | Works best on English; the README says Chinese, Russian and Japanese do not work |
| Known failure | Trained on a fixed prompt; other prompts are expected to cause hallucination | Repetition loops on 1.5% of test pages, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE |
Sources
- Nanonets-OCR2-3B model card
- Nanonets-OCR-s announcement
- HF discussion fixed prompt
- Nougat GitHub README
- Nougat paper
- Issue #11 repetitions
What each one is
Nanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-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": "nanonets/nanonets-ocr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Nanonets-OCR vs DonutNanonets-OCR vs MonkeyOCRHunyuan OCR vs Nougatdots.ocr vs NougatTesseract vs Nanonets-OCRMonkeyOCR vs NougatMinerU vs NougatDeepSeek-OCR vs Nanonets-OCR
Nanonets-OCR alternativesNougat alternativesBest OCR models in 2026