docTR vs Nougat
Pick docTR if you need word-level text with coordinates from invoices, receipts or other business documents, and you want an Apache-2.0 library you can use commercially. Pick Nougat if you convert English scientific papers with heavy math into Markdown and LaTeX, and your use is non-commercial. The main split is output and licence: docTR returns words and boxes under Apache-2.0, Nougat returns Markdown with LaTeX under CC-BY-NC weights.
docTRmindee/doctr | Nougatmeta/nougat | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 0.9 s / page | 3.0 s / page |
| Best for | Word-level OCR with positions | arXiv-style papers |
| Inputs | PDF, images | PDF, images |
| Languages | Mainly Latin scripts | Mainly English |
| Max pages per request | 500 | 200 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | No | 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 docTR if
- Its Apache-2.0 licence has no commercial restriction, so you can ship it in a product.
- It returns a nested page, block, line and word structure with coordinates as JSON, which suits custom extraction on invoices and receipts.
- You can choose detection and recognition architectures, use straight or rotated boxes, and train your own models in Python.
Choose Nougat if
- It is built for academic papers, trained on arXiv and PubMed Central documents.
- It outputs LaTeX for equations and tables inside Mathpix-compatible .mmd Markdown, which docTR does not produce at all.
- It offers small and base checkpoints with a simple CLI and API for converting math-heavy PDFs.
Key differences
| docTR | Nougat | |
|---|---|---|
| Licence | Apache-2.0 | Code MIT; weights CC-BY-NC, so no commercial use |
| Output formats | JSON, plain text, bounding boxes | Markdown, LaTeX |
| Tables and formulas | No table, formula or Markdown output; words and lines only | LaTeX for equations and tables in .mmd Markdown |
| Best document type | Invoices and receipts feeding custom extraction, word-level OCR | English arXiv-style scientific papers |
| Languages | Not published | Works best on English; Chinese, Russian and Japanese do not work |
| Known failure | Split-crop merging misjoins readings across repeated characters (issue #2229); cropping images gives poorer results (issue #2007) | Repetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; repetition detection can drop pages as MISSING_PAGE (issue #11) |
| Hardware and price | CPU or NVIDIA GPU; GPU Docker images need CUDA 12.2 or newer; free, self-hosted | Free for non-commercial use, self-hosted; benchmarks Not published |
Sources
What each one is
docTR
Open-source OCR library from Mindee with separate text detection and recognition models.
docTR 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": "mindee/doctr","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
docTR vs DonutdocTR vs MonkeyOCRKraken vs NougatRapidOCR vs NougatAzure Document Intelligence vs NougatdocTR vs Florence-2Amazon Textract vs NougatdocTR vs Unstructured
docTR alternativesNougat alternativesBest OCR models in 2026