MinerU vs Nanonets-OCR
Pick MinerU for mixed corpora of PDFs and Office files, Chinese and English academic papers, or CPU-only batch conversion. Pick Nanonets-OCR for printed business documents that carry signatures, watermarks and checkboxes, or for flowcharts you want as Mermaid. MinerU scores higher on olmOCR-Bench (75.2 vs 69.5), but its licence is more complicated and its VLM tiers drop merged table header rows.
MinerUopendatalab/mineru | Nanonets-OCRnanonets/nanonets-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 | 1.8 s / page |
| Best for | Academic PDFs | Markdown with semantic tags |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Multilingual |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | ✓ Yes |
| 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
- You need one tool for PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML input.
- You have no GPU: the basic ONNX tier runs on CPU with about 2 GB RAM.
- You process Chinese and English academic papers and want output as Markdown, HTML, LaTeX, DOCX, EPUB or JSON.
Choose Nanonets-OCR if
- Your documents have signatures, watermarks or checkboxes, which it tags or converts to unicode symbols.
- You want flowcharts and org charts extracted as Mermaid code.
- You want a single 3B image-to-Markdown model for printed PDFs that feeds an LLM, with inline and display LaTeX kept apart.
Key differences
| MinerU | Nanonets-OCR | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights are tagged AGPL-3.0 | Not stated on the Nanonets-OCR2-3B model card; base model is Qwen2.5-VL-3B |
| Model size and hardware | MinerU2.5 VLM is 1.2B. Basic tier runs on CPU with 2 GB RAM. VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM. | 3B (Hugging Face lists about 4B), fine-tuned from Qwen2.5-VL-3B. Hardware needs: Not published |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML | Images (image-to-Markdown model) |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Markdown, HTML, LaTeX, Mermaid |
| olmOCR-Bench overall | 75.2 (MinerU 2.5.4, independent) | 69.5 (OCR2-3B, reported by the authors) |
| Handwriting | Not published | Not trained on handwriting and can hallucinate. One handwriting test saw generation loops with CER up to 2100%. |
| Known failure | Drops merged header rows in tables such as bank statement account lines (issue #5554). Repeated content can produce 300 KB figure blocks (issue #5728). | Trained on a fixed prompt, so hallucination with other prompts is expected. Loses to Gemini 2.5 Flash in 52.43% of head-to-head Markdown comparisons. |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- Nanonets-OCR2-3B model card
- Nanonets-OCR-s announcement
- HF discussion fixed prompt
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsNanonets-OCR
Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.
Nanonets-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": ["nanonets/nanonets-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesNanonets-OCR alternativesBest OCR models in 2026