OCRRouter

Mathpix Convert vs OpenOCR

Pick Mathpix Convert for math-heavy papers and textbooks where you need LaTeX, DOCX or Markdown from whole PDFs, including handwritten equations, and you want a hosted API. Pick OpenOCR for Chinese and English academic PDFs with formulas when you want to self-host under Apache-2.0 and pay only for compute. The main split is hosted, paid and proprietary versus self-hosted, free and open source.

Mathpix Convertmathpix/convertOpenOCRfudan/openocr
TypeOCR APIOpen source
Price7 credits / page1 credit / page
Per 1,000 pages$7.00$1.00
Typical speed1.5 s / page0.5 s / page
Best forMath and scientific papersLightweight OCR pipeline on CPU
InputsPDF, imagesPDF, images
Languages30+ languagesChinese and English
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
MultilingualNoNo
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

  • You need whole PDFs converted straight to LaTeX or DOCX, with Markdown, HTML and JSON also available.
  • Your content is math, tables and chemistry, including handwritten equations.
  • You want a hosted API with per-page pricing: $0.005 per PDF page, $0.002 per image.

Choose OpenOCR if

  • You want to run it yourself under an Apache-2.0 licence with no per-page fee, paying only for compute.
  • Your documents are in Chinese or English and include formulas, and you want a 0.1B-parameter model that reports 90.57 on OmniDocBench v1.5.
  • You want ONNX export and bounding box output for your own deployment.

Key differences

Mathpix ConvertOpenOCR
DeploymentHosted APISelf-hosted Python library
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; you pay for compute
Output formatsLaTeX, Markdown, DOCX, HTML, JSONPlain text, LaTeX, bounding boxes
BenchmarkNo published accuracy benchmark on general OCR leaderboardsOpenDoc-0.1B reports 90.57 on OmniDocBench v1.5, self-reported by the authors with no independent replication found
LanguagesNot publishedOpenDoc and UniRec support only Chinese and English
Known failure or catchImages with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrearsDocument parsing depends on a separate layout model, PP-DocLayoutV2 from PaddlePaddle; no hardware requirements or throughput figures published

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

OpenOCR

Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.

OpenOCR 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": ["fudan/openocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesOpenOCR alternativesBest OCR models in 2026