OCRRouter

Mathpix Convert vs Hunyuan OCR

Pick Mathpix Convert for math-heavy papers and textbooks that need LaTeX or DOCX output, or for handwritten equations, and you accept a hosted, paid API. Pick Hunyuan OCR to self-host a free, roughly 1B parameter model for photo and scene text, text-image translation or low-resource scripts, if you are outside the EU, UK and South Korea.

Mathpix Convertmathpix/convertHunyuan OCRtencent/hunyuan-ocr
TypeOCR APIOpen source
Price7 credits / page2 credits / page
Per 1,000 pages$7.00$2.00
Typical speed1.5 s / page1.5 s / page
Best forMath and scientific papersChinese documents and photos
InputsPDF, imagesPDF, images
Languages30+ languages100+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
MultilingualNo✓ 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 Mathpix Convert if

  • It is built for STEM content and turns math, tables and chemistry into LaTeX and Markdown.
  • It exports whole PDFs directly to DOCX and LaTeX, and it handles handwritten equations.
  • It is a hosted API with no GPU to manage, at $0.005 per page for PDFs and $0.002 per image.

Choose Hunyuan OCR if

  • It is free to self-host, so you pay only for compute, and a llama.cpp GGUF build runs on laptops.
  • One model handles document parsing, text spotting, information extraction and image translation, with 12 task types via the vLLM client.
  • It covers low-resource and ancient scripts, takes images up to 4K and has a 128K context window in v1.5.

Key differences

Mathpix ConvertHunyuan OCR
How you run itHosted APISelf-hosted via vLLM, Transformers or llama.cpp
LicenceProprietaryTencent Hunyuan Community License; excludes EU, UK and South Korea; separate license needed above 100M monthly active users
PricePDF $0.005 per page (0-1M), $0.0035 above 1M; images $0.002 each; one-time $19.99 API key feeFree; you pay for compute
Output formatsLaTeX, Markdown, DOCX, HTML, JSONMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
Best document typesMath-heavy papers, textbooks, handwritten equationsPhoto and scene text, text-image translation, historical scripts
BenchmarkNo published accuracy benchmark on general OCR leaderboardsParseBench-2 overall 67.11, ParseBench mean 63.86 (v1.5)
Known drawbacksNon-refundable $19.99 fee; images with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrearsNeeds CUDA 13 and vLLM 0.25.1+ for the unified environment; text score 62.88 on ParseBench-2; an archived 1.0 note said Transformers and vLLM outputs differed in accuracy

Sources

What each one is

Mathpix Convert

Specialist for math, science papers and handwritten formulas. Outputs LaTeX.

Mathpix Convert 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": "mathpix/convert","fallbacks": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesHunyuan OCR alternativesBest OCR models in 2026