OCRRouter

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/minerudots.ocrrednote/dots-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.5 s / page
Best forAcademic PDFsMultilingual document parsing
InputsPDF, imagesPDF, images
Languages80+ languages100+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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

MinerUdots.ocr
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0MIT (repository also includes a separate dots.ocr license agreement file)
Model sizeMinerU2.5 VLM: 1.2B3B (1.7B LLM backbone)
HardwareBasic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAMSingle CUDA GPU with vLLM is the documented path; no VRAM figure stated; not recommended for CPU-only production
Input formatsPDF, images, DOCX, PPTX, XLSX, EPUB, OFD, HTMLNot published
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONJSON, Markdown, HTML, LaTeX, bounding boxes, SVG
olmOCR-Bench score75.2 (MinerU 2.5.4, independent)79.1 (dots.ocr) and 83.9 (dots.mocr / 1.5), both reported by the authors
Known failureVLM tiers drop merged header rows in tables such as bank statement account lines; repeated content can produce 300 KB figure blocksRuns 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

What each one is

MinerU

Open-source PDF to Markdown pipeline popular for academic and Chinese documents.

MinerU details

dots.ocr

Single vision model from rednote that does layout detection and content recognition together.

dots.ocr details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

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