OCRRouter

Mathpix Convert vs Chunkr

Pick Mathpix Convert if your documents are math-heavy papers or textbooks and you need LaTeX or DOCX output from whole PDFs. Pick Chunkr if you want layout parsing and chunking for RAG, or need to self-host. The main split is STEM output formats on a hosted API versus general layout parsing with an open-source option.

Mathpix Convertmathpix/convertChunkrchunkr/chunkr
TypeOCR APIOCR API
Price7 credits / page14 credits / page
Per 1,000 pages$7.00$14.00
Typical speed1.5 s / page3.0 s / page
Best forMath and scientific papersLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
Languages30+ languagesMultilingual
Max pages per request5001,000
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 converts math, tables and chemistry in images and PDFs into LaTeX and Mathpix Markdown.
  • It exports whole PDFs directly to DOCX or LaTeX, and it handles handwritten equations.
  • PDF pricing is published: $0.005 per page up to 1M pages and $0.0035 above that, with images at $0.002 each.

Choose Chunkr if

  • You can self-host it with Docker on GPU, CPU-only or Mac ARM, or use the cloud API.
  • It accepts PDF, PPT, Word and images, and returns HTML, Markdown and JSON with bounding boxes for RAG chunking.
  • It works with any OpenAI-compatible LLM endpoint, and the open-source version is free under AGPL-3.0.

Key differences

Mathpix ConvertChunkr
How you run itHosted API onlyCloud API or self-hosted via Docker
LicenceProprietaryAGPL-3.0 or commercial licence
PricingPDF $0.005 per page (0-1M), $0.0035 above 1M; images $0.002 each; one-time $19.99 API key feeHosted credit-based plans, official prices not verified; open-source is free but you pay for compute and an LLM endpoint
Output formatsLaTeX, Markdown, DOCX, HTML, JSONHTML, Markdown, JSON, bounding boxes
FocusSTEM content: math, tables, chemistryLayout analysis, OCR with bounding boxes, semantic chunking
Input typesImages and PDFsPDF, PPT, Word and images
Known limitsNon-refundable $19.99 fee; images with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrearsOpen-source version uses less accurate community models, has no Excel support, needs an external LLM endpoint, and AGPL requires a commercial licence for closed use
Published benchmarksNot publishedNot published

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesChunkr alternativesBest OCR models in 2026