Amazon Textract vs RapidOCR
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want tables, forms and queries from a managed API. Pick RapidOCR for offline CPU OCR of Chinese and English text, such as screenshots and receipts, where you want a free library you run yourself. The main split is a hosted per-page service with layout analysis versus a local text-only toolkit.
Amazon Textractaws/textract | RapidOCRrapidai/rapidocr | |
|---|---|---|
| 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 | 0.6 s / page |
| Best for | Forms and key-value extraction | Lightweight OCR on CPU or edge |
| Inputs | PDF, images | images |
| Languages | 6 languages | Chinese, English and more |
| Max pages per request | 3,000 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | ✓ Yes |
| 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
- It extracts tables, forms, queries and layout, and RapidOCR is not meant for layout, tables or Markdown output.
- The async API handles PDFs up to 500 MB and 3,000 pages, which suits large scanned batches.
- It scored 80.9% on RD-TableBench table accuracy, a published independent number that RapidOCR does not have.
Choose RapidOCR if
- It is free under Apache-2.0 and runs offline on your own CPU, so you pay only for compute and no page leaves your machine.
- It handles Chinese and English by default, while Textract text detection covers only English, French, German, Italian, Portuguese and Spanish.
- It has bindings for Python, C++, Java and C#, so you can embed it in desktop or server apps.
Key differences
| Amazon Textract | RapidOCR | |
|---|---|---|
| How you run it | Hosted API on AWS | Library you run locally from Python, C++, Java or C#, offline |
| Licence | Proprietary | Apache-2.0 (converted models keep their upstream licences) |
| Price | First 1M pages/month in US West (Oregon): $0.0015/page for text detection, $0.015 for Tables, $0.05 for Forms, $0.015 for Queries | Free, self-hosted (you pay for compute) |
| Output formats | JSON, plain text, bounding boxes, with confidence scores | Plain text, bounding boxes |
| Tables and forms | Extracts tables, forms, queries and layout; 80.9% on RD-TableBench | Not meant for layout, tables or Markdown output |
| Languages | English, French, German, Italian, Portuguese, Spanish for text detection; handwriting and Queries English only; vertical Japanese and Chinese not supported | Chinese and English by default; other languages need extra models |
| Known failure | Sync API takes one page; non-Latin text is not covered | 16-bit grayscale PNG or TIFF give no text or wrong text; sliced inference crashes on large pages; Arabic recognition crashes without manual setup |
Sources
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsRapidOCR
PaddleOCR models packaged for ONNX Runtime and other engines. Easy to deploy without Paddle.
RapidOCR 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": ["rapidai/rapidocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesRapidOCR alternativesBest OCR models in 2026