OCRRouter

MinerU vs Qwen-VL

Pick MinerU for batch conversion of Chinese and English papers and mixed PDF and Office files, especially if you have no GPU. Pick Qwen-VL for photos, screenshots and jobs that mix OCR with reasoning, and add loop checks on long runs. MinerU scores higher on olmOCR-Bench (75.2 vs 64.6 for Qwen 3 VL 8B), and it is a document parser, while Qwen-VL is a general model.

MinerUopendatalab/mineruQwen-VLqwen/qwen-vl
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page2.0 s / page
Best forAcademic PDFsFlexible extraction with prompts
InputsPDF, imagesPDF, images
Languages80+ languages30+ languages
Max pages per request500200
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
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 scores 75.2 on olmOCR-Bench (MinerU 2.5.4), above the 64.6 that Qwen 3 VL 8B gets.
  • One tool takes PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and renders to Markdown, HTML, LaTeX, DOCX, EPUB or JSON.
  • The basic tier runs on CPU with about 2 GB RAM, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.

Choose Qwen-VL if

  • It does OCR in 32 languages and handles low light, blur and tilted text, so it suits photos and screenshots with text.
  • It is Apache-2.0 in every size from 2B to 235B-A22B MoE, with no extra licence terms, and it can also be used as a hosted API on Alibaba Cloud.
  • It returns bounding boxes and a Qwen HTML document format, and it can answer questions about the page, so one model covers OCR plus reasoning or VQA.

Key differences

MinerUQwen-VL
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0Apache-2.0 (Qwen3-VL repository)
How you run itSelf-host only: CLI, API or WebUISelf-host the open weights, or use the hosted API on Alibaba Cloud
HardwareBasic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAMFP8 checkpoints need an H100-class GPU and CUDA 12+; the 235B example uses 8-way tensor parallel on vLLM
Model sizeMinerU2.5 VLM: 1.2B2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoE
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONPlain text, HTML, bounding boxes, JSON, Markdown
olmOCR-Bench75.2 overall (MinerU 2.5.4)64.6 (Qwen 3 VL 8B)
Known failureRepeated content such as 300 KB figure blocks (issue #5728); merged header rows dropped in tables such as bank statements (issue #5554); full-width Chinese punctuation turned half-width with no switch (issue #5765)Loops repeating the same text, worse with greedy decoding (issue #1611) and on low-quality scans; Qwen2.5-VL-32B GGUF often gets stuck on scanned documents (llama.cpp #14663)

Sources

What each one is

MinerU

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

MinerU details

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL 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": ["qwen/qwen-vl"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesQwen-VL alternativesBest OCR models in 2026