Amazon Textract vs OCRmyPDF
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you need tables, forms and word-level geometry as JSON. Pick OCRmyPDF to make scanned PDF archives searchable as PDF/A on your own hardware, in 100+ languages, for free. The main split is structured extraction from a hosted API versus a local text layer on the original PDF.
Amazon Textractaws/textract | OCRmyPDFocrmypdf/ocrmypdf | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 1 credit / page |
| Per 1,000 pages | $25.00 | $1.00 |
| Typical speed | 1.2 s / page | 1.0 s / page |
| Best for | Forms and key-value extraction | Searchable PDFs from scans |
| Inputs | PDF, images | PDF, images |
| Languages | 6 languages | 100+ languages (via Tesseract) |
| Max pages per request | 3,000 | 1,000 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
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 tables, forms or queries as structured JSON, priced at $0.015, $0.05 and $0.015 per page for the first 1M pages a month in US West (Oregon).
- You process big scanned PDF batches, since the async API takes PDFs up to 500 MB and 3,000 pages.
- You want word and line bounding boxes with confidence scores, plus handwriting on English documents.
Choose OCRmyPDF if
- You need validated searchable PDF/A output for archiving or compliance workflows.
- You want free, self-hosted OCR under MPL-2.0 that runs on CPU only and uses all cores, with no per-page fee beyond your own compute.
- You need languages beyond Textract's six, because Tesseract language packs cover 100+ languages.
Key differences
| Amazon Textract | OCRmyPDF | |
|---|---|---|
| How you run it | Hosted AWS API | Local command-line tool and library, CPU only |
| Licence | Proprietary | MPL-2.0 |
| Price | Text detection $0.0015/page; Tables $0.015; Forms $0.05; Queries $0.015 (US West Oregon, first 1M pages/month) | Free, self-hosted; you pay for compute |
| Output | JSON, plain text, bounding boxes | Searchable PDF/A, plain text. No layout, table or Markdown output |
| Languages | Text detection in English, French, German, Italian, Portuguese and Spanish; handwriting and Queries English only | 100+ languages via Tesseract language packs |
| Table benchmark | 80.9% on RD-TableBench (independent) | Not published |
| Known failure | No vertical Japanese or Chinese text; sync API takes one page | --skip-text with default PDF/A output removes form fields; file size can double or quadruple with --deskew --clean-final; hangs on PDFs whose forms share one Resources dictionary |
Sources
- Textract pricing
- Textract quotas
- Reducto RD-TableBench
- OCRmyPDF GitHub README
- Issue #1790 form fields
- Issue #948 file size
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsOCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "aws/textract","fallbacks": ["ocrmypdf/ocrmypdf"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesOCRmyPDF alternativesBest OCR models in 2026