OCRRouter

MinerU vs Unstructured

Pick MinerU if you want a free, self-hosted parser for Chinese and English academic papers or mixed Office and PDF corpora, and you can live with its custom licence. Pick Unstructured if you want a hosted API with a free first 10,000 pages and an Apache-2.0 library for mixed-file RAG ingestion. The main split is how you run it: MinerU is self-host only, while Unstructured offers both a library and a paid hosted platform.

MinerUopendatalab/mineruUnstructuredunstructured/unstructured
TypeOpen sourceOCR API
Price2 credits / page20 credits / page
Per 1,000 pages$2.00$20.00
Typical speed2.0 s / page3.0 s / page
Best forAcademic PDFsMixed file types into RAG
InputsPDF, imagesPDF, images, DOCX
Languages80+ languagesMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
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 Chinese and English academic papers parsed, which is its stated best fit.
  • You want to run on CPU only: the basic ONNX tier needs about 2 GB RAM and no GPU.
  • You want output as Markdown, HTML, LaTeX, DOCX, EPUB or JSON, and input including PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML.

Choose Unstructured if

  • You want a hosted API: the first 10,000 pages are free, then $0.015 per page.
  • You need a plain Apache-2.0 library with many connectors, with no AGPL-tagged weights.
  • You ingest born-digital PDFs and want the fast strategy, or want to switch between Auto, Fast, High-Res and VLM.

Key differences

MinerUUnstructured
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0Apache-2.0 for the open-source library; proprietary for the hosted platform
How you run itSelf-host only, as a CLI, API or WebUISelf-host the Python library or use the hosted API
PriceFree; you pay for computeLibrary free. Hosted: first 10,000 pages free, then $0.015 per page. Business is custom.
HardwareBasic tier runs on CPU with 2 GB RAM. VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM.Not published
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONJSON, HTML, plain text, bounding boxes
BenchmarkolmOCR-Bench overall 75.2 (MinerU 2.5.4, independent)Table cell content 0.426 for the open-source library vs 0.866 hosted (the vendor's own benchmark)
Known failureVLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554). The VLM pipeline can repeat content and produce 300 KB figure blocks (issue #5728).hi_res tables cut off at edges and drop first letters (issue #3262). Table OCR ignores language settings (issue #1694).

Sources

What each one is

MinerU

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

MinerU details

Unstructured

Document ETL for RAG. Partitions many file types into typed elements; open-source library too.

Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesUnstructured alternativesBest OCR models in 2026