OCRRouter

GPT vs Nougat

Pick GPT for handwritten notes, custom JSON extraction and document question answering through a hosted API, where you can pay per token. Pick Nougat for English arXiv-style papers with heavy math that must become LaTeX, but only if the use is non-commercial, because its weights are CC-BY-NC and it is self-hosted.

GPTopenai/gptNougatmeta/nougat
TypeVision modelOpen source
Price11 credits / page2 credits / page
Per 1,000 pages$11.00$2.00
Typical speed2.4 s / page3.0 s / page
Best forMessy scans, custom instructionsarXiv-style papers
InputsPDF, imagesPDF, images
Languages50+ languagesMainly English
Max pages per request100200
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
Math✓ Yes✓ Yes
Bounding boxesNoNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 GPT if

  • It reads handwriting well: an HN user reported about 5% errors on messy cursive versus about 30% for Mistral OCR.
  • It can extract data into custom JSON and answer questions about a document, not only transcribe it.
  • It has no licence barrier for products: it is a hosted API that takes files up to 50 MB per request and returns Markdown, JSON or plain text.

Choose Nougat if

  • It is built for scientific papers: trained on arXiv and PubMed Central, it outputs Mathpix-style Markdown with LaTeX for equations and tables.
  • It costs nothing in fees for non-commercial use: you self-host it and pay only for compute.
  • It ships small and base checkpoints with a simple CLI and API, and the code is MIT licensed.

Key differences

GPTNougat
How you run itHosted API from OpenAISelf-hosted Python package
LicenceProprietaryCode MIT; weights CC-BY-NC, so no commercial use
PricingToken-based per model; page images add input tokens, so cost per page is not fixedFree for non-commercial use; you pay for compute
Output formatsMarkdown, JSON, plain textMarkdown (Mathpix-style .mmd) and LaTeX
Best document typesHandwritten notes, custom JSON extraction, document question answeringEnglish arXiv-style papers and math-heavy PDFs
LanguagesNot publishedWorks best on English; Chinese, Russian and Japanese do not work
Known failureNo bounding boxes or confidence scores in the standard responseRepetition loops on 1.5% of test pages, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE

Sources

What each one is

GPT

General vision model. Good at messy scans and following extraction instructions.

GPT details

Nougat

Meta's model that converts academic PDFs to Markdown with LaTeX math.

Nougat 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": "openai/gpt","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GPT alternativesNougat alternativesBest OCR models in 2026