OCRRouter

Amazon Textract vs Unstructured

Pick Amazon Textract for English forms, invoices and large scanned PDF batches if you already run on AWS. Pick Unstructured for ingesting mixed file types (PDF, HTML, Word, PowerPoint, email, images) into a RAG pipeline, or when you want a self-hostable Apache-2.0 library. The main split is scope: Textract is a hosted OCR and form/table API with English-centred features, while Unstructured is a partitioning library and platform for many file types.

Amazon Textractaws/textractUnstructuredunstructured/unstructured
TypeOCR APIOCR API
Price25 credits / page20 credits / page
Per 1,000 pages$25.00$20.00
Typical speed1.2 s / page3.0 s / page
Best forForms and key-value extractionMixed file types into RAG
InputsPDF, imagesPDF, images, DOCX
Languages6 languagesMultilingual
Max pages per request3,0001,000
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNoNo
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
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

  • Basic text detection costs $1.50 per 1,000 pages ($0.0015/page), and the async API takes PDFs up to 500 MB and 3,000 pages.
  • It extracts forms ($0.05/page), tables ($0.015/page) and queries ($0.015/page), and returns word and line geometry with confidence scores.
  • It scored 80.9% on the independent RD-TableBench table accuracy test.

Choose Unstructured if

  • One library handles PDFs, HTML, Word, PowerPoint, emails and images, with many connectors.
  • You can self-host the Apache-2.0 open-source library for free, or use the hosted API with the first 10,000 pages free, then $0.015 per page.
  • Strategies Auto, Fast, High-Res and VLM let you trade speed for quality, and Fast suits born-digital PDFs.

Key differences

Amazon TextractUnstructured
How you run itHosted AWS API only.Self-host the open-source library, or use the hosted API.
LicenceProprietary.Apache-2.0 for the library; proprietary for the hosted platform.
Price$0.0015/page text detection, $0.015 tables, $0.05 forms, $0.015 queries (US West Oregon, first 1M pages/month).Hosted: first 10,000 pages free, then $0.015/page. Open-source library is free.
Input scopeScanned documents and PDFs; async handles up to 500 MB and 3,000 pages, sync takes one page.PDFs, HTML, Word, PowerPoint, emails and images.
Output formatsJSON, plain text, bounding boxes. Markdown for RAG needs post-processing.JSON, HTML, plain text, bounding boxes.
Table quality80.9% on RD-TableBench (independent).Vendor's own benchmark: table cell content 0.426 for the open-source library versus 0.866 hosted. hi_res tables can cut off at edges and drop first letters (issue #3262).
LanguagesText detection covers English, French, German, Italian, Portuguese and Spanish. Handwriting and Queries are English only. Vertical Japanese and Chinese are not supported.Table OCR ignores language settings (issue #1694), so non-English tables are a weak spot.

Sources

What each one is

Amazon Textract

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

Amazon Textract details

Unstructured

Document ETL for RAG. Partitions many file types into typed elements; open-source library too.

Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesUnstructured alternativesBest OCR models in 2026