OCRRouter

MinerU vs Hunyuan OCR

Pick MinerU for Chinese and English academic papers and mixed Office and PDF corpora, especially if you have no GPU and want output in formats like DOCX, EPUB or LaTeX. Pick Hunyuan OCR for photo and scene text, image translation, and low-resource or historical scripts, if your users sit outside the EU, UK and South Korea. The main split is scope: MinerU is a document converter that also takes Office files, while Hunyuan OCR is a single ~1B model that spans parsing, spotting, extraction and translation.

MinerUopendatalab/mineruHunyuan OCRtencent/hunyuan-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 PDFsChinese documents and photos
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 corpora for RAG.
  • Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
  • It renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.

Choose Hunyuan OCR if

  • One ~1B model covers document parsing, text spotting, information extraction and image translation, so you run one model instead of a pipeline.
  • It supports images up to 4K and a 128K context window in v1.5, and exposes 12 task types including low-resource and ancient-script OCR.
  • It scores higher on ParseBench (63.86 mean for v1.5 against 45.9 for MinerU2.5) and can run on a laptop through llama.cpp GGUF.

Key differences

MinerUHunyuan OCR
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); the MinerU2.5 VLM weights are tagged AGPL-3.0Tencent Hunyuan Community License; excludes the EU, UK and South Korea, and needs a separate license above 100M monthly active users
Model sizeMinerU2.5 VLM: 1.2BAbout 1B
HardwareBasic ONNX tier on CPU with 2 GB RAM; VLM tiers need 16 GB RAM and a GPU with 8 GB+ VRAMNVIDIA GPU with CUDA 13 recommended for the unified vLLM environment; llama.cpp GGUF path for CPU, consumer GPU or laptop
Input typesPDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTMLImages and documents for parsing, spotting, extraction and translation tasks
Output formatsMarkdown, HTML, LaTeX, DOCX, EPUB, JSONMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
BenchmarksolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5); olmOCR-Bench: Not published
Known failureVLM tiers drop merged header rows in tables such as bank statement account lines; repeated content can produce 300 KB figure blocks; full-width Chinese punctuation is converted to half-width with no switchUnified environment needs CUDA 13 and vLLM 0.25.1+; an archived 1.0 note said Transformers and vLLM outputs differed in accuracy; ParseBench-2 text score is 62.88

Sources

What each one is

MinerU

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

MinerU details

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MinerU alternativesHunyuan OCR alternativesBest OCR models in 2026