MinerU vs Nougat
Pick MinerU if you need to parse mixed PDFs and Office files, handle Chinese or other non-English text, or ship a commercial product. Pick Nougat only for English, math-heavy scientific papers where you want LaTeX output and your use is non-commercial. The main split is scope and licence: MinerU covers many input types and languages, while Nougat is a narrow paper-to-Markdown model with non-commercial weights.
MinerUopendatalab/mineru | Nougatmeta/nougat | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.0 s / page | 3.0 s / page |
| Best for | Academic PDFs | arXiv-style papers |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Mainly English |
| Max pages per request | 500 | 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 MinerU if
- You need one tool for PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, such as a mixed Office and PDF corpus for RAG.
- You work with Chinese and English academic papers, or any text that is not English.
- You have no GPU: the basic tier runs on CPU with about 2 GB RAM, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.
Choose Nougat if
- Your documents are English arXiv-style papers, which is what it was trained on (arXiv and PubMed Central).
- You want math-heavy PDFs converted to LaTeX, with equations and tables in Mathpix-compatible .mmd Markdown.
- You want a small Python package with small and base checkpoints, a simple CLI and an API, and your use is non-commercial.
Key differences
| MinerU | Nougat | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Code MIT; weights CC-BY-NC |
| Commercial use | Possible, but the custom licence and AGPL-tagged VLM weights complicate it | Not allowed, because the weights are CC-BY-NC |
| Input types | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Scientific PDF pages |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Markdown (.mmd) and LaTeX |
| Hardware | Basic tier on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM | Not published |
| Languages | Chinese and English; converts full-width Chinese punctuation to half-width with no switch (issue #5765) | Works best on English; Chinese, Russian and Japanese do not work |
| Known failure | VLM pipeline repeats content, producing 300 KB figure blocks (issue #5728); VLM tiers drop merged header rows in tables (issue #5554) | Repetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; pages can be dropped as MISSING_PAGE (issue #11) |
Sources
- MinerU GitHub README
- Issue #5728 repetition
- Issue #5554 table header rows
- Nougat GitHub README
- Nougat paper
- Issue #11 repetitions
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU 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": "opendatalab/mineru","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU vs DonutMinerU vs MonkeyOCRDocling vs NougatUnlimited OCR vs NougatMinerU vs DoclingHunyuan OCR vs NougatMinerU vs PaddleOCR (PP-OCR)MinerU vs EasyOCR
MinerU alternativesNougat alternativesBest OCR models in 2026