OCRRouter

Mathpix Convert vs Phi-4-multimodal

Pick Mathpix Convert when the job is turning math-heavy papers, textbooks or handwritten equations into LaTeX, Markdown or DOCX through a hosted API. Pick Phi-4-multimodal when you need English document Q&A under an MIT licence on your own GPUs, or one model that also takes audio. The main split is a paid, STEM-focused conversion API versus a free, self-hosted general model that returns text, Markdown or JSON.

Mathpix Convertmathpix/convertPhi-4-multimodalmicrosoft/phi-4-multimodal
TypeOCR APIVision model
Price7 credits / page2 credits / page
Per 1,000 pages$7.00$2.00
Typical speed1.5 s / page2.5 s / page
Best forMath and scientific papersSmall model for OCR and questions
InputsPDF, imagesimages
Languages30+ languagesEnglish for vision
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
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

  • It is built for STEM content, so math, tables and chemistry come out as LaTeX or Markdown.
  • It exports whole PDFs straight to DOCX or LaTeX, which Phi-4-multimodal does not list as outputs.
  • It is a hosted API, so you do not provision GPUs or manage attention settings.

Choose Phi-4-multimodal if

  • It is MIT licensed and free to self-host, so you pay only for compute.
  • Microsoft reports DocVQA 93.2 and OCRBench 84.4 at 5.6B parameters, which suits English document Q&A on modest GPUs.
  • It takes audio as well as images, with a 128K token context, so one model can serve a mixed audio and image pipeline.

Key differences

Mathpix ConvertPhi-4-multimodal
LicenceProprietaryMIT
How you run itHosted APISelf-host, or use via Azure AI Foundry
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, Markdown, JSON
BenchmarksNot publishedDocVQA 93.2, OCRBench 84.4, ChartQA 81.4, InfoVQA 72.7 (reported by the authors)
LanguagesNot publishedVision supported for English only; performance drops in other languages
Known failureImages with more than 12 text rows may be billed at the PDF page rateModel card warns of repetitive or inconsistent output in long chats; V100 and older GPUs need eager attention

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

Phi-4-multimodal

Microsoft's 5.6B text, vision and audio model (February 2025). Scores 84.4 on OCRBench per its model card.

Phi-4-multimodal 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": ["microsoft/phi-4-multimodal"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesPhi-4-multimodal alternativesBest OCR models in 2026