OCRRouter

MinerU vs Phi-3.5-vision

Phi-3.5-vision is cheaper per page. MinerU is faster. Only MinerU supports Tables, Math, Bounding boxes.

MinerUopendatalab/mineruPhi-3.5-visionmicrosoft/phi-3-5-vision
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page3.0 s / page
Best forAcademic PDFsSmall self-hosted model
InputsPDF, imagesimages
Languages80+ languagesEnglish for vision
Max pages per request50050
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.

What each one is

MinerU

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

MinerU details

Phi-3.5-vision

Microsoft's 4.2B vision model (August 2024).

Phi-3.5-vision 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 10 files at onceNo file?

Use one, fall back to the other

{"model": "opendatalab/mineru","fallbacks": ["microsoft/phi-3-5-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesPhi-3.5-vision alternativesBest OCR models in 2026