OCRRouter

Amazon Textract vs Nougat

Pick Amazon Textract for English forms, invoices and large scanned PDF batches, especially if you already run on AWS. Pick Nougat for English scientific papers that you want as Markdown with LaTeX math, but only for non-commercial work because its weights are CC-BY-NC. The main split is scope: Textract is a hosted business-document service, Nougat is a self-hosted model for academic PDFs.

Amazon Textractaws/textractNougatmeta/nougat
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forForms and key-value extractionarXiv-style papers
InputsPDF, imagesPDF, images
Languages6 languagesMainly English
Max pages per request3,000200
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
Forms✓ YesNo
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 Amazon Textract if

  • You need forms, tables or queries from English invoices and similar business documents through a hosted AWS API.
  • You process big scanned PDF batches: the async API takes files up to 500 MB and 3,000 pages.
  • You want a commercial-use service with per-page pricing, starting at $0.0015 per page for basic text detection.

Choose Nougat if

  • You convert English arXiv-style papers and need equations and tables as LaTeX in Mathpix-compatible Markdown.
  • You want to self-host and pay only for compute, for a non-commercial or research project.
  • You want a small Python package with small and base checkpoints and a simple CLI and API.

Key differences

Amazon TextractNougat
How you run itHosted API on AWSSelf-hosted Python package
LicenceProprietaryCode MIT; weights CC-BY-NC, so no commercial use
PriceUS West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015, Queries $0.015, Forms $0.05Free for non-commercial use; you pay for compute
Output formatsJSON, plain text, bounding boxes (word and line geometry with confidence scores)Markdown and LaTeX
Best document typesEnglish forms and invoices, large scanned PDF batchesEnglish arXiv-style scientific papers, math-heavy PDFs
LanguagesText detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English onlyWorks best on English; README says Chinese, Russian and Japanese do not work
Known failureVertical Japanese and Chinese text not supported; sync API takes one pageRepetition loops on 1.5% of test pages in the paper, more on out-of-domain documents; pages can be dropped as MISSING_PAGE

Sources

What each one is

Amazon Textract

AWS OCR with form key-value pairs, tables and per-word confidence scores.

Amazon Textract 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": "aws/textract","fallbacks": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesNougat alternativesBest OCR models in 2026