OCRRouter

Gemini Flash vs Nougat

Pick Gemini Flash for commercial products, bulk PDF to Markdown and JSON extraction across mixed-language documents, because it is a hosted API with no licence restriction on use. Pick Nougat only for English arXiv-style papers where you need LaTeX math and can run it non-commercially on your own GPU. Nougat is unsuited to forms, invoices and non-Latin scripts.

Gemini Flashgoogle/gemini-flashNougatmeta/nougat
TypeVision modelOpen source
Price15 credits / page2 credits / page
Per 1,000 pages$15.00$2.00
Typical speed1.6 s / page3.0 s / page
Best forHandwriting and mixed layoutsarXiv-style papers
InputsPDF, imagesPDF, images
Languages100+ languagesMainly English
Max pages per request1,000200
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 Gemini Flash if

  • You are building a commercial product, since Nougat's weights are CC-BY-NC and bar commercial use.
  • You process mixed-language documents, while Nougat works best on English and does not work on Chinese, Russian or Japanese.
  • You need JSON or HTML output from a prompt or schema, and a 1M-token context window to fit long documents in one request.

Choose Nougat if

  • You convert English scientific papers and want Mathpix-style Markdown with LaTeX for equations and tables.
  • You need to self-host or run air-gapped, and you only pay for your own compute.
  • You work on non-commercial research with arXiv or PubMed Central style papers, which is what the model was trained on.

Key differences

Gemini FlashNougat
LicenceProprietaryCode MIT; weights CC-BY-NC (no commercial use)
How you run itHosted API via Gemini API or Vertex AISelf-hosted Python package with a CLI and API
PriceGemini 3 Flash Preview: $0.50 per 1M input tokens, $3.00 per 1M output tokens; Batch/Flex $0.25 and $1.50Free for non-commercial use; you pay for compute
Output formatsMarkdown, JSON, HTML, plain textMarkdown (.mmd) and LaTeX
BenchmarkGemini 3 Flash scores 92.62 on OmniDocBench v1.6Not published
LanguagesHandles mixed-language documentsBest on English; Chinese, Russian and Japanese do not work
Known failureCost per page varies with page density and output length; output is prompt-driven with no fixed schema or confidence scoresRepetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; looping pages can be dropped as MISSING_PAGE

Sources

What each one is

Gemini Flash

General vision model with strong handwriting and layout understanding at a low price.

Gemini Flash 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": "google/gemini-flash","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Gemini Flash alternativesNougat alternativesBest OCR models in 2026