OCRRouter

PaddleOCR-VL vs MinerU

Pick PaddleOCR-VL for multilingual scans, formula-heavy papers and charts on a modest GPU, under a plain Apache-2.0 licence. Pick MinerU for mixed Office and PDF corpora, for output formats like DOCX, LaTeX and EPUB, or when you need a CPU-only tier. The main split is scope: PaddleOCR-VL is one small model for page parsing, MinerU is a toolkit with several quality tiers and a more complicated licence.

PaddleOCR-VLpaddle/paddleocr-vlMinerUopendatalab/mineru
TypeOpen sourceOpen source
Price6 credits / page2 credits / page
Per 1,000 pages$6.00$2.00
Typical speed1.3 s / page2.0 s / page
Best forCJK documentsAcademic PDFs
InputsPDF, imagesPDF, images
Languages109 languages80+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
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 PaddleOCR-VL if

  • It is Apache-2.0 with no extra conditions, so commercial use is straightforward.
  • It supports 109 languages in one model, including Cyrillic, Arabic, Devanagari and Thai scripts.
  • It has higher published scores: 80.0 on olmOCR-Bench against 75.2 for MinerU 2.5.4, and 96.33 on OmniDocBench v1.6 (reported by the authors).

Choose MinerU if

  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool.
  • It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
  • Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start without a GPU.

Key differences

PaddleOCR-VLMinerU
LicenceApache-2.0MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights are tagged AGPL-3.0
Model size0.9B parametersMinerU2.5 VLM: 1.2B parameters
HardwareNVIDIA GPU recommended; CPU possible but slow; no minimum VRAM statedBasic tier runs on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM
Input and output formatsOutputs Markdown and JSONReads PDF, images, Office files, EPUB, OFD and HTML; writes Markdown, HTML, LaTeX, DOCX, EPUB and JSON
olmOCR-Bench overall80.075.2 (MinerU 2.5.4)
Known failureVersion 1.6 hangs on blurry images, decodes about 11x slower because use_cache ships as false, and regresses Russian and Kazakh OCR on born-digital PDFsVLM tiers drop merged header rows in tables such as bank statement account lines, and the VLM pipeline can generate repeated content such as 300 KB figure blocks
PriceFree, self-hosted (you pay for compute)Free, self-hosted (you pay for compute)

Sources

What each one is

PaddleOCR-VL

Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.

PaddleOCR-VL details

MinerU

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

MinerU 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": "paddle/paddleocr-vl","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

PaddleOCR-VL alternativesMinerU alternativesBest OCR models in 2026