MinerU vs SmolDocling
Pick MinerU for Chinese and English academic papers and mixed PDF and Office corpora, where one tool reads PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML. Pick SmolDocling only for small English experiments, because it is a 256M preview model and its authors point users to Granite-Docling. MinerU's main cost is a custom licence and AGPL-tagged VLM weights. SmolDocling's main cost is that it is English only and can loop on some images.
MinerUopendatalab/mineru | SmolDoclinghuggingface/smoldocling | |
|---|---|---|
| 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 | 1.0 s / page |
| Best for | Academic PDFs | Very cheap page conversion |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | Mainly 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 a mixed corpus needs no separate converters.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
- It is a fit for Chinese and English academic papers, and it scores 75.2 overall on olmOCR-Bench (MinerU 2.5.4).
Choose SmolDocling if
- At 256M parameters it runs on modest hardware, and it takes about 0.35 seconds per page on an A100 with vLLM.
- It is licensed Apache-2.0 per its model summary (the metadata tag says CDLA-Permissive-2.0), which is simpler than MinerU's custom licence and AGPL-tagged weights.
- One model handles text, tables (OTSL), code, formulas and charts, and it returns location tags and bounding boxes.
Key differences
| MinerU | SmolDocling | |
|---|---|---|
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); the MinerU2.5 VLM weights are tagged AGPL-3.0 | Apache-2.0 per model summary (metadata tag says CDLA-Permissive-2.0) |
| Model size and hardware | VLM: 1.2B parameters. Basic tier runs on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM | 256M parameters, small enough for modest hardware |
| Input formats | PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML | Page images converted by the VLM; other input types Not published |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | DocTags, Markdown, HTML, JSON, LaTeX, bounding boxes |
| Languages | Chinese and English academic papers are a stated fit | English only |
| Speed | VLM tier reaches 2.12 pages per second on one A100 with vLLM | About 0.35 seconds per page on an A100 with vLLM |
| Known failure | VLM pipeline can repeat content (300 KB figure blocks, issue #5728) and drops merged header rows in tables such as bank statements (issue #5554) | Endless token repetition and missing closing tags are typical defects; output loops on some images, making generation very slow (Docling issue #1515) |
Sources
- MinerU GitHub README
- MinerU2.5 model card
- olmOCR-Bench table
- Issue #5554 table header rows
- SmolDocling model card
- Docling issue #1515
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsSmolDocling
Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.
SmolDocling 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": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesSmolDocling alternativesBest OCR models in 2026