OCRRouter

Amazon Textract vs PaddleOCR (PP-OCR)

Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want a managed API with table and form extraction. Pick PaddleOCR (PP-OCR) for Chinese, Japanese or multilingual printed text, or when you must run locally, on the edge or in the browser. The main split is a hosted per-page API against a free Apache-2.0 library you run yourself.

Amazon Textractaws/textractPaddleOCR (PP-OCR)paddle/paddleocr
TypeOCR APIOpen source
Price25 credits / page1 credit / page
Per 1,000 pages$25.00$1.00
Typical speed1.2 s / page0.7 s / page
Best forForms and key-value extractionFast printed text, Chinese and English
InputsPDF, imagesPDF, images
Languages6 languages80+ languages
Max pages per request3,000500
Tables✓ YesNo
Handwriting✓ YesNo
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, queries and layout through the AWS API, priced from $0.015/page for Tables and $0.05/page for Forms.
  • The async API handles PDFs up to 500 MB and 3,000 pages, which suits large scanned batches.
  • It returns word and line geometry with confidence scores, and has no servers for you to run.

Choose PaddleOCR (PP-OCR) if

  • It is Apache-2.0 and free to self-host, so you pay only for compute.
  • One PP-OCRv6 model covers 50 languages, including Chinese, Japanese, English and 46 Latin-script languages.
  • It runs on CPU, GPU and other accelerators, and in the browser through the PaddleOCR.js SDK, which fits edge and mobile use.

Key differences

Amazon TextractPaddleOCR (PP-OCR)
How you run itHosted AWS APILibrary: Python package, C++ or PaddleOCR.js in the browser
LicenceProprietaryApache-2.0
PriceText 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)
LanguagesText detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. No vertical Japanese or Chinese.50 languages in one PP-OCRv6 model, including Chinese and Japanese
Tables and formsBuilt in. RD-TableBench table accuracy 80.9% (independent)Not built in. Returns text lines and boxes only; tables need the separate PP-Structure or VL pipelines. No benchmark published
LimitsAsync PDFs up to 500 MB and 3,000 pages; sync API takes one pageNo page limit published. PP-OCRv6 medium is 34.5M parameters
Known issuesNo Markdown output without post-processingNotImplementedError on PaddleOCR 3.7.0 with PaddlePaddle 3.3.1 (issue #18162); denormal weights can make PP-OCRv6 CPU inference 4 to 11x slower (RapidOCR issue #743)

Sources

What each one is

Amazon Textract

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

Amazon Textract details

PaddleOCR (PP-OCR)

Baidu's classic open-source text detection and recognition pipeline. Light enough to run on CPU.

PaddleOCR (PP-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": ["paddle/paddleocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesPaddleOCR (PP-OCR) alternativesBest OCR models in 2026