MinerU vs OCRmyPDF
Pick MinerU when you need Markdown, JSON or LaTeX from papers and mixed PDF and Office files, and you can accept a custom licence. Pick OCRmyPDF when you only need to make scanned PDFs searchable and archive them as PDF/A under MPL-2.0. The main split is output: MinerU parses layout and tables into structured text, while OCRmyPDF adds a Tesseract text layer and nothing else.
MinerUopendatalab/mineru | OCRmyPDFocrmypdf/ocrmypdf | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 1.0 s / page |
| Best for | Academic PDFs | Searchable PDFs from scans |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | 100+ languages (via Tesseract) |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | No |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| 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 MinerU if
- You need Markdown, HTML, LaTeX, DOCX, EPUB or JSON output rather than a searchable PDF.
- Your corpus mixes PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and you want one tool for all of it.
- You work with Chinese and English academic papers, or you need a CPU-only basic tier that runs on about 2 GB RAM.
Choose OCRmyPDF if
- You need validated searchable PDF/A for archiving, with the OCR layer inserted losslessly where possible.
- You want a permissive MPL-2.0 licence with no extra conditions or AGPL-tagged weights.
- You need Tesseract's 100+ languages via language packs and use of all CPU cores, with no GPU.
Key differences
| MinerU | OCRmyPDF | |
|---|---|---|
| What it produces | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Searchable PDF/A and plain text |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Scanned PDFs |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | MPL-2.0 |
| Hardware | Basic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | CPU only, spread across all cores |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published |
| Tables and layout | Parses them, but VLM tiers drop merged header rows such as bank statement account lines (issue #5554) | No layout, table or Markdown output; accuracy is capped by Tesseract |
| Known failures | VLM pipeline can repeat content into 300 KB figure blocks (issue #5728); full-width Chinese punctuation becomes half-width with no switch (issue #5765) | --deskew --clean-final can double or quadruple file size (issue #948); --skip-text with default PDF/A drops form fields (issue #1790); hangs on PDFs whose forms share one Resources dictionary (issue #1763) |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- OCRmyPDF GitHub README
- Issue #948 file size
- Issue #1790 form fields
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsOCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF 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": "opendatalab/mineru","fallbacks": ["ocrmypdf/ocrmypdf"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesOCRmyPDF alternativesBest OCR models in 2026