OCRRouter

DeepSeek-OCR vs MinerU

Pick DeepSeek-OCR for cheap, self-hosted bulk OCR on a CUDA GPU under a plain MIT licence. Pick MinerU for mixed PDF and Office corpora, Chinese and English academic papers, or CPU-only batch work. The main split is scope: DeepSeek-OCR is a single OCR model, while MinerU is a full parsing toolkit with several tiers and many output formats.

DeepSeek-OCRdeepseek/deepseek-ocrMinerUopendatalab/mineru
TypeOpen sourceOpen source
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.1 s / page2.0 s / page
Best forCheap bulk conversionAcademic PDFs
InputsPDF, imagesPDF, images
Languages100+ languages80+ languages
Max pages per request200500
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 DeepSeek-OCR if

  • The MIT licence allows commercial use with no extra conditions.
  • You can set the resolution from 64 to 400 vision tokens per page, and the authors quote about 2,500 tokens per second on one A100-40G.
  • It suits research on token-efficient OCR, and cheap bulk OCR where you only pay for compute.

Choose MinerU if

  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool, which fits mixed corpora for RAG.
  • The basic ONNX tier runs on CPU with about 2 GB RAM, so you can start without a GPU.
  • It can output Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and it has an independent olmOCR-Bench overall score of 75.2 (MinerU 2.5.4).

Key differences

DeepSeek-OCRMinerU
LicenceMITMinerU Open Source License (Apache-2.0 based with extra conditions); the MinerU2.5 VLM weights are tagged AGPL-3.0
HardwareCUDA GPU; reference setup is CUDA 11.8 and PyTorch 2.6 in bfloat16Basic tier runs on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAM
Output formatsMarkdown, plain text, HTML, bounding boxesMarkdown, HTML, LaTeX, DOCX, EPUB, JSON
Input typesPage images and PDFsPDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML
ThroughputAbout 2,500 tokens per second on one A100-40G (authors' figure)2.12 pages per second on one A100 with vLLM (VLM tier)
BenchmarksNot publishedolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)
Known failureRepeated tokens and looping over table headers (GitHub issues #12 and #16); it corrects nonsense words instead of copying themVLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554) and can produce repeated content (issue #5728)

Sources

What each one is

DeepSeek-OCR

Open-source vision model that compresses pages into few tokens.

DeepSeek-OCR details

MinerU

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

MinerU 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": "deepseek/deepseek-ocr","fallbacks": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

DeepSeek-OCR alternativesMinerU alternativesBest OCR models in 2026