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/mineru | Google Cloud Vision OCRgoogle/cloud-vision | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.0 s / page | 1.0 s / page |
| Best for | Academic PDFs | Photos and simple scans |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | 100+ languages |
| Max pages per request | 500 | 2,000 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | ✓ Yes |
| 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
- 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
| MinerU | Google Cloud Vision OCR | |
|---|---|---|
| How you run it | Self-host as CLI, API or WebUI | Hosted REST API on Google Cloud; PDF and TIFF need async processing via Cloud Storage |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Proprietary |
| Price | Free software; you pay for compute | First 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 formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | JSON, plain text, bounding boxes; no Markdown |
| Tables and layout | Parses 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 |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published |
| Known failure | VLM 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
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Issue #5728 repetition
- Vision pricing
- OCR docs
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsGoogle Cloud Vision OCR
Google Cloud's image OCR with text and document text detection, word boxes and confidence.
Google Cloud Vision OCR 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": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026