OCRRouter

Amazon Textract vs Google Cloud Vision OCR

Pick Amazon Textract for English forms, invoices and tables on AWS, and for large scanned PDF batches. Pick Google Cloud Vision OCR for plain text from photos, handwritten notes and high-volume extraction. The main split is structure: Textract returns tables and forms, while Vision OCR returns text and geometry only.

Amazon Textractaws/textractGoogle Cloud Vision OCRgoogle/cloud-vision
TypeOCR APIOCR API
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page1.0 s / page
Best forForms and key-value extractionPhotos and simple scans
InputsPDF, imagesPDF, images
Languages6 languages100+ languages
Max pages per request3,0002,000
Tables✓ YesNo
Handwriting✓ Yes✓ Yes
MathNoNo
Bounding boxes✓ Yes✓ Yes
Confidence✓ Yes✓ Yes
Forms✓ YesNo
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 Amazon Textract if

  • It extracts tables, forms and queries, priced at $0.015, $0.05 and $0.015 per page, while Vision OCR has no table or layout structure.
  • It has an independent table score of 80.9% on RD-TableBench, and Vision OCR has no published benchmark.
  • Its async API takes PDFs up to 500 MB and 3,000 pages, so large scanned batches fit in one job.

Choose Google Cloud Vision OCR if

  • It is cheaper for plain text at volume: $1.50 per 1,000 units, dropping to $0.60 per 1,000 above 5M units.
  • Handwriting works through DOCUMENT_TEXT_DETECTION and language hints, while Textract handwriting works only on English.
  • TEXT_DETECTION suits photos of signs and labels, and the response gives a page, block, paragraph, word and symbol hierarchy with bounding polygons.

Key differences

Amazon TextractGoogle Cloud Vision OCR
Tables and formsTables, Forms and Queries supportedNo table or layout structure; Google points to Document AI
Plain text priceDetect Document Text $0.0015/page ($1.50 per 1,000), first 1M pages/month, US West (Oregon)First 1,000 units/month free, then $1.50 per 1,000 up to 5M, $0.60 per 1,000 above
Table benchmark80.9% on RD-TableBench (independent)No benchmark listed
Languages and handwritingText detection covers English, French, German, Italian, Portuguese and Spanish; handwriting and Queries English onlyHandwriting supported via DOCUMENT_TEXT_DETECTION and language hints
PDF handlingAsync API takes PDFs up to 500 MB and 3,000 pages; sync API takes one pagePDF and TIFF need async processing via Cloud Storage; async batch takes up to 2,000 image files per request
OutputJSON, plain text, bounding boxes, with word and line geometry and confidence scoresJSON, plain text, bounding boxes, with page, block, paragraph, word and symbol hierarchy; no Markdown, you rebuild reading order
Setup and licenceProprietary hosted API on AWSProprietary hosted API on Google Cloud; billing must be enabled even for the free units

Sources

What each one is

Amazon Textract

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

Amazon Textract details

Google Cloud Vision OCR

Google Cloud's image OCR with text and document text detection, word boxes and confidence.

Google Cloud Vision OCR 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": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026