OCRRouter

Mathpix Convert vs PaddleOCR (PP-OCR)

Pick Mathpix Convert for math-heavy papers and textbooks where you need LaTeX, Markdown or DOCX from whole PDFs, including handwritten equations. Pick PaddleOCR for printed text in Chinese, English and other languages that you want to run yourself for free on CPU, GPU, edge devices or in the browser. The main split is a paid hosted STEM converter versus a free, open-source text detector and recognizer.

Mathpix Convertmathpix/convertPaddleOCR (PP-OCR)paddle/paddleocr
TypeOCR APIOpen source
Price7 credits / page1 credit / page
Per 1,000 pages$7.00$1.00
Typical speed1.5 s / page0.7 s / page
Best forMath and scientific papersFast printed text, Chinese and English
InputsPDF, imagesPDF, images
Languages30+ languages80+ languages
Max pages per request500500
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
Confidence✓ Yes✓ Yes
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 turns PDFs and images with math, tables and chemistry into LaTeX, Markdown, DOCX, HTML or JSON.
  • It exports DOCX and LaTeX directly from whole PDFs, so you do not need a second pipeline for layout.
  • It is listed for handwritten equations and math-heavy papers and textbooks.

Choose PaddleOCR (PP-OCR) if

  • It is Apache-2.0 and free to self-host, so you pay only for compute and keep documents on your own machines.
  • One PP-OCRv6 model covers 50 languages, including Chinese, English, Japanese and 46 Latin-script languages.
  • The 34.5M-parameter PP-OCRv6 medium model runs on CPU, NVIDIA GPU and other accelerators, and in the browser through PaddleOCR.js.

Key differences

Mathpix ConvertPaddleOCR (PP-OCR)
How you run itHosted APILibrary: Python package, C++ or the PaddleOCR.js browser SDK
LicenceProprietaryApache-2.0
PricePDF $0.005 per page (0-1M), $0.0035 above 1M; images $0.002 each; one-time $19.99 API key activation feeFree, self-hosted (you pay for compute)
Output formatsLaTeX, Markdown, DOCX, HTML, JSONPlain text, bounding boxes, JSON
Tables and formulasConverts math, tables and chemistry to LaTeX and MarkdownReturns text lines and boxes only; tables and formulas need the separate PP-Structure or VL pipelines
BenchmarksNot published on general OCR leaderboardsAuthors report PP-OCRv6 medium beats PP-OCRv5_server by 4.6% detection and 5.1% recognition
Known issuesImages with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrearsPP-OCRv6 weights contain denormals that make CPU inference 4 to 11x slower (RapidOCR issue #743); NotImplementedError with PaddleOCR 3.7.0 on PaddlePaddle 3.3.1 (issue #18162)

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

PaddleOCR (PP-OCR)

Baidu's classic open-source text detection and recognition pipeline. Light enough to run on CPU.

PaddleOCR (PP-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": ["paddle/paddleocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesPaddleOCR (PP-OCR) alternativesBest OCR models in 2026