OCRRouter

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/mineruOCRmyPDFocrmypdf/ocrmypdf
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page1.0 s / page
Best forAcademic PDFsSearchable PDFs from scans
InputsPDF, imagesPDF, images
Languages80+ languages100+ languages (via Tesseract)
Max pages per request5001,000
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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

MinerUOCRmyPDF
What it producesMarkdown, HTML, LaTeX, DOCX, EPUB, JSONSearchable PDF/A and plain text
Input formatsPDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTMLScanned PDFs
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0MPL-2.0
HardwareBasic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAMCPU only, spread across all cores
BenchmarkolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)Not published
Tables and layoutParses 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 failuresVLM 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

What each one is

MinerU

Open-source PDF to Markdown pipeline popular for academic and Chinese documents.

MinerU details

OCRmyPDF

Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.

OCRmyPDF details

Try 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": ["ocrmypdf/ocrmypdf"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesOCRmyPDF alternativesBest OCR models in 2026