OCRRouter

MinerU vs Donut

Pick MinerU when you need full-page conversion of PDFs, images and Office files into Markdown, HTML, LaTeX or JSON without training anything. Pick Donut when you have a narrow, fixed-layout document type such as receipts or forms and can fine-tune it for field extraction. The main split is that MinerU works out of the box on whole documents, while Donut's base checkpoint is pretrain-only and must be fine-tuned first.

MinerUopendatalab/mineruDonutnaver/donut
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 PDFsReceipt and form fields after fine-tuning
InputsPDF, imagesimages
Languages80+ languagesEnglish, Chinese, Japanese, Korean
Max pages per request500100
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNo✓ Yes
Multilingual✓ YesNo
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

  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, so mixed corpora for RAG need a single pipeline.
  • It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, which suits full-page conversion of Chinese and English academic papers.
  • Its basic tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.

Choose Donut if

  • It is MIT licensed and available in Hugging Face Transformers, which avoids the custom licence and AGPL-tagged weights that complicate MinerU in commercial use.
  • It maps document images straight to structured JSON with no external OCR step, which fits receipt and form field extraction after fine-tuning.
  • A practitioner on Hacker News reports that about 200 fine-tuning documents can reach human-level accuracy on narrow data.

Key differences

MinerUDonut
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights are tagged AGPL-3.0MIT
Ready to useWorks as a toolkit with CLI, API or WebUIBase checkpoint is pretrain-only and must be fine-tuned before use
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONJSON, plain text
Input typesPDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTMLDocument images
HardwareBasic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAMNot published
BenchmarksolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)Not published
Known failureVLM tiers drop merged header rows in tables such as bank statement account lines; VLM pipeline can produce repeated contentMisses tiny text in large images due to input resolution limits; Transformers v5 dropped image-to-text pipeline support, so it needs direct loading or v4

Sources

What each one is

MinerU

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

MinerU details

Donut

OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.

Donut 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": ["naver/donut"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesDonut alternativesBest OCR models in 2026