MinerU vs OpenOCR
Pick MinerU when you need to convert mixed PDF, image and Office files into Markdown, HTML, LaTeX, DOCX or JSON, or when you must run on CPU only. Pick OpenOCR when your documents are Chinese or English academic PDFs with formulas and you want a 0.1B model under Apache-2.0. The main split is scope and licence: MinerU covers more input and output formats but carries a custom licence and AGPL-tagged VLM weights, while OpenOCR is smaller, permissive and limited to two languages.
MinerUopendatalab/mineru | OpenOCRfudan/openocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 0.5 s / page |
| Best for | Academic PDFs | Lightweight OCR pipeline on CPU |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Chinese and 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, so mixed corpora for RAG need no extra converters.
- It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, which suits pipelines that need more than plain text.
- The basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
Choose OpenOCR if
- It uses the Apache-2.0 licence, which avoids the custom terms and AGPL-tagged weights that complicate commercial use of MinerU.
- OpenDoc-0.1B reports 90.57 on OmniDocBench v1.5 with only 0.1B parameters, so the model is very small.
- UniRec-0.1B recognizes plain text and single or multi-line formulas in one model, which fits academic PDFs with formulas.
Key differences
| MinerU | OpenOCR | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Apache-2.0 |
| Model size | MinerU2.5 VLM: 1.2B parameters | 0.1B (OpenDoc-0.1B and UniRec-0.1B) |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Not published |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Plain text, LaTeX, bounding boxes |
| Hardware | Basic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | Not published |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4, independent); ParseBench mean 45.9 (independent) | OmniDocBench v1.5 overall 90.57 (OpenDoc-0.1B, self-reported by the authors, no independent replication found) |
| Known failure | Drops merged header rows in tables such as bank statement account lines; VLM pipeline can generate repeated content, including 300 KB figure blocks | Supports only Chinese and English; document parsing depends on a separate layout model, PP-DocLayoutV2 from PaddlePaddle |
Sources
- MinerU GitHub README
- MinerU2.5 model card
- olmOCR-Bench table
- Issue #5554 table header rows
- Issue #5728 repetition
- GitHub README
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsOpenOCR
Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.
OpenOCR 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": ["fudan/openocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesOpenOCR alternativesBest OCR models in 2026