Amazon Textract
Extract data from documents
Extracts text, handwriting, tables, key-value pairs in forms, and invoice and ID document data from images and scanned PDFs; goes far beyond ordinary OCR because it understands document structure.
- Cost$ Low
- Difficulty●●●●●
- Costs money when idle?No
- Serverless
- In examsCLF · SAA
Think of it asLike a super-fast data entry clerk: reads a paper form and fills each field correctly into the system.
When to use it
✓ Use it when
You need to digitize scanned forms, invoices, and contracts into structured data.
✗ Avoid it when
You need to recognize objects or faces in images → Rekognition.
Common uses
- Automated invoice processing
- Digitize loan and insurance applications
- Extract information from national ID cards/passports
What does it cost?
- Pricing model: Charged by number of pages processed; analyzing forms, tables, and queries costs more than text extraction alone.
⚠️ Cost traps
Enabling every feature (forms, tables, queries) for all pages drives costs up sharply; enable only what you need.
