OCRRouter

Mathpix Convert vs MiniCPM-V 4.5

Pick Mathpix Convert when the job is math-heavy papers, textbooks or handwritten equations that must come out as LaTeX or DOCX. Pick MiniCPM-V 4.5 when you need to run OCR yourself under Apache-2.0, on one GPU or on-device, with no per-page fee. The main split is a hosted, paid STEM converter versus a free, self-hosted general vision model.

Mathpix Convertmathpix/convertMiniCPM-V 4.5openbmb/minicpm-v
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 papersOCR on edge devices
InputsPDF, imagesimages
Languages30+ languages30+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
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 is built for STEM content, so math, tables and chemistry come out as LaTeX or Mathpix Markdown.
  • It exports whole PDFs straight to DOCX, LaTeX, HTML or JSON, so you do not need to build that step yourself.
  • It is a hosted API at $0.005 per page for PDFs, so you run no GPUs or model servers.

Choose MiniCPM-V 4.5 if

  • It is Apache-2.0 for both weights and code, and you pay only for your own compute.
  • It runs locally on llama.cpp, vLLM or Transformers, with int4, GGUF and AWQ builds for on-device or single-GPU use.
  • It is a general vision language model, so it fits local document Q&A as well as OCR.

Key differences

Mathpix ConvertMiniCPM-V 4.5
How you run itHosted APISelf-host with llama.cpp, vLLM, Ollama or Transformers (Ollama support was still pending an official release on the model card)
LicenceProprietaryApache-2.0 weights and code
PricePDF $0.005 per page up to 1M pages, then $0.0035; images $0.002 each; one-time $19.99 API key feeFree; you pay for compute
Output formatsLaTeX, Markdown, DOCX, HTML, JSONPlain text, Markdown, JSON
Best document typesMath papers, textbooks, handwritten equations, chemistryGeneral documents, local document Q&A
Published benchmarksNo accuracy benchmark on general OCR leaderboardsClaims lead on OCRBench and OmniDocBench PDF parsing, but scores are given only as images on the model card
Known limitsImages with more than 12 text rows may be billed at the PDF page rate; billed monthly in arrearsNo bounding box or layout output; no int4 VRAM figure published

Sources

What each one is

Mathpix Convert

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

Mathpix Convert details

MiniCPM-V 4.5

8B vision model from OpenBMB (August 2025) built to run on devices, with strong OCR and document parsing.

MiniCPM-V 4.5 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": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Mathpix Convert alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026