OCRRouter

MinerU vs Google Cloud Vision OCR

Pick MinerU when you need Markdown, HTML or LaTeX from papers and mixed PDF and Office files, and you can run it yourself. Pick Google Cloud Vision OCR when you need plain text, handwriting or bounding boxes from photos and scans through a hosted API. The main split is structure: MinerU returns document structure, while Cloud Vision returns text with coordinates and leaves reading order to you.

MinerUopendatalab/mineruGoogle Cloud Vision OCRgoogle/cloud-vision
TypeOpen sourceOCR API
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.0 s / page
Best forAcademic PDFsPhotos and simple scans
InputsPDF, imagesPDF, images
Languages80+ languages100+ languages
Max pages per request5002,000
Tables✓ YesNo
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNo✓ Yes
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

  • It outputs Markdown, HTML, LaTeX, DOCX, EPUB and JSON, so the result can go straight into an LLM or RAG pipeline.
  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which suits mixed corpora.
  • It runs on your own machine, and the basic ONNX tier needs only a CPU and about 2 GB RAM.

Choose Google Cloud Vision OCR if

  • It reads handwriting through DOCUMENT_TEXT_DETECTION with language hints, and it handles photos of signs and labels.
  • It returns a page, block, paragraph, word and symbol hierarchy with bounding polygons, which helps when you need exact positions.
  • Pricing is simple: 1,000 units free per month, $1.50 per 1,000 up to 5M, then $0.60 per 1,000, with no GPU to manage.

Key differences

MinerUGoogle Cloud Vision OCR
How you run itSelf-host as CLI, API or WebUIHosted REST API on Google Cloud; PDF and TIFF need async processing via Cloud Storage
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0Proprietary
PriceFree software; you pay for computeFirst 1,000 units per month free, then $1.50 per 1,000 up to 5M, $0.60 per 1,000 above; each PDF page is one unit
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONJSON, plain text, bounding boxes; no Markdown
Tables and layoutParses document structure, but VLM tiers drop merged header rows such as bank statement account lines (issue #5554)No table or layout structure; Google points to Document AI for forms and tables
BenchmarkolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)Not published
Known failureVLM pipeline can repeat content, producing 300 KB figure blocks (issue #5728); converts full-width Chinese punctuation to half-width with no switch (issue #5765)You must rebuild reading order yourself; billing must be enabled even for the free 1,000 units

Sources

What each one is

MinerU

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

MinerU details

Google Cloud Vision OCR

Google Cloud's image OCR with text and document text detection, word boxes and confidence.

Google Cloud Vision OCR 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": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026