MinerU vs dots.ocr
Pick MinerU when you need to parse mixed PDF and Office files (DOCX, PPTX, XLSX, EPUB, HTML) or must run on CPU only. Pick dots.ocr when you have a GPU and want one MIT-licensed VLM that returns layout boxes, text, HTML tables and LaTeX formulas for multilingual PDFs. The main split is scope and licence: MinerU covers more input formats and a CPU tier but carries a custom licence and AGPL-tagged VLM weights, while dots.ocr is a GPU-bound 3B model with MIT code.
MinerUopendatalab/mineru | dots.ocrrednote/dots-ocr | |
|---|---|---|
| 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 | Multilingual document parsing |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | 100+ languages |
| 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 | ✓ 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 accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which suits mixed RAG corpora.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can batch-convert without a GPU.
- It can render to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and its VLM tier reaches 2.12 pages per second on one A100 with vLLM.
Choose dots.ocr if
- Its code is MIT-licensed, which is simpler than MinerU's custom licence and AGPL-tagged VLM weights.
- One model returns layout boxes, categories and text, with tables as HTML and formulas as LaTeX.
- Its authors report 79.1 on olmOCR-bench for the original model and 83.9 for dots.mocr (v1.5), against 75.2 for MinerU 2.5.4 from an independent table.
Key differences
| MinerU | dots.ocr | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | MIT (repository also includes a separate dots.ocr license agreement file) |
| Model size | MinerU2.5 VLM: 1.2B | 3B (1.7B LLM backbone) |
| Hardware | Basic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | Single CUDA GPU with vLLM is the documented path; no VRAM figure stated; not recommended for CPU-only production |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTML | Not published |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | JSON, Markdown, HTML, LaTeX, bounding boxes, SVG |
| olmOCR-Bench score | 75.2 (MinerU 2.5.4, independent) | 79.1 (dots.ocr) and 83.9 (dots.mocr / 1.5), both reported by the authors |
| Known failure | VLM tiers drop merged header rows in tables such as bank statement account lines; repeated content can produce 300 KB figure blocks | Runs of ellipses or underscores can make output repeat endlessly; a table above 1000 grid cells raises an error and drops the whole page in Docling |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- dots.ocr GitHub README
- dots.ocr blog / limitations
- Docling issue #5146
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsdots.ocr
Single vision model from rednote that does layout detection and content recognition together.
dots.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": ["rednote/dots-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesdots.ocr alternativesBest OCR models in 2026