OCRRouter

Mathpix Convert vs olmOCR

Pick Mathpix Convert for math-heavy papers and textbooks where you need LaTeX or DOCX out of a whole PDF, and you are fine with a hosted, paid API. Pick olmOCR for large-scale PDF to Markdown for LLM training or RAG, where you can run a GPU and want open weights and a low per-page cost.

Mathpix Convertmathpix/convertolmOCRallenai/olmocr
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 papersBulk PDF to text for datasets
InputsPDF, imagesPDF, images
Languages30+ languagesMainly English
Max pages per request5001,000
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
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

  • You need LaTeX, DOCX or HTML export directly from whole PDFs, not just Markdown.
  • Your documents are STEM papers and textbooks with math, tables and chemistry, including handwritten equations.
  • You want a hosted API with no GPU to set up or maintain.

Choose olmOCR if

  • You want an Apache-2.0 toolkit with released weights, training data and code, and the option to self-host.
  • You process PDFs at scale: self-hosted cost is under $200 per million pages, per Ai2.
  • You need Markdown for LLM training or RAG from mixed printed and handwritten pages, with headers and footers stripped in reading order.

Key differences

Mathpix ConvertolmOCR
How you run itHosted API onlySelf-host with vLLM on a GPU, or call third-party hosted endpoints
LicenceProprietaryApache-2.0 (toolkit); weights, training data and code are released
PricePDF $0.005 per page (0-1M), $0.0035 per page above 1M; images $0.002 each; one-time $19.99 API key activation feeSelf-hosted: under $200 per million pages, per Ai2. DeepInfra hosted: $0.09 input / $0.19 output per million tokens
Output formatsLaTeX, Markdown, DOCX, HTML, JSONMarkdown, JSON
HardwareNone needed on your sideNVIDIA GPU with at least 12 GB VRAM and 30 GB free disk; no CPU-only use
BenchmarkNot published82.4 on olmOCR-Bench (v0.4.0), above Marker (76.1), MinerU 2.5.4 (75.2) and Mistral OCR (72.0), as reported by the authors
Known failureImages with more than 12 text rows may be billed at the PDF page rateOut of memory on a 12 GB GPU (issue #424), gets stuck on the last few pages (issue #433), unreliable image bounding box coordinates (issue #437)

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

olmOCR

Open-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.

olmOCR 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": ["allenai/olmocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesolmOCR alternativesBest OCR models in 2026