MinerU vs MonkeyOCR
Pick MinerU if you need to parse mixed Office and PDF files, or need to start on a CPU-only machine, and can accept a custom licence. Pick MonkeyOCR for English and Simplified Chinese PDFs with formulas and tables, but only for research, since its v1 weights cannot be used commercially without a written licence. The main split is input range and licence: MinerU takes more file types, while MonkeyOCR is narrower and bars commercial use.
MinerUopendatalab/mineru | MonkeyOCRmonkeyocr/monkeyocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 2.0 s / page | 1.5 s / page |
| Best for | Academic PDFs | Chinese and English PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Chinese, English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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 accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start without a GPU.
- It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.
Choose MonkeyOCR if
- Its pro-3B model reports the best overall OmniDocBench edit distance among the models the authors compared, in English and Chinese (0.138 / 0.206).
- It runs on an 8GB RTX 4060 with quantized weights, and pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy.
- It outputs Markdown plus layout PDF and JSON with block coordinates, which suits work that needs block positions.
Key differences
| MinerU | MonkeyOCR | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights are tagged AGPL-3.0 | Code Apache-2.0; v1 weights research and non-commercial only, commercial use needs a written licence |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Built for PDFs; photographed text and handwriting are not fully supported |
| Model size | MinerU2.5 VLM: 1.2B | 3B and 1.2B |
| Hardware | Basic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | Tested on RTX 3090/4090, A6000, H800, A100; RTX 4060 8GB works with quantized models |
| Speed | 2.12 pages per second on one A100 with vLLM (VLM tier) | Pro-3B about 0.49 pages/s on a 3090 |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | OmniDocBench pro-3B: edit distance 0.138 EN / 0.206 ZH, table TEDS 81.5 / 87.5 (reported by the authors) |
| Known failure | VLM tiers drop merged header rows in tables such as bank statement account lines; the VLM pipeline can generate repeated content, including 300 KB figure blocks | Traditional Chinese and multilingual text are not fully supported; Docker on 20/30/40-series and V100 needs a patched image to avoid an LMDeploy shared-memory error |
Sources
- MinerU GitHub README
- MinerU2.5 model card
- olmOCR-Bench table
- Issue #5554 table header rows
- MonkeyOCR GitHub README
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsMonkeyOCR
Open-source document parser that splits work into structure, recognition and relation steps.
MonkeyOCR 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": ["monkeyocr/monkeyocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesMonkeyOCR alternativesBest OCR models in 2026