Amazon Textract vs GOT-OCR 2.0
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want a managed API and per-page pricing. Pick GOT-OCR 2.0 for formulas, sheet music, chemical structures or English and Chinese documents that you can run on your own GPU. The main split is hosted API with language limits versus a self-hosted model with a wider range of outputs and known failure modes.
Amazon Textractaws/textract | GOT-OCR 2.0stepfun/got-ocr-2 | |
|---|---|---|
| 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 | 1.5 s / page |
| Best for | Forms and key-value extraction | Formatted text, formulas and charts |
| Inputs | PDF, images | images |
| Languages | 6 languages | Chinese, English |
| Max pages per request | 3,000 | 100 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | No |
| Multilingual | No | No |
| 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 is a hosted AWS API, so there is no model to host, and basic text detection costs $0.0015 per page ($1.50 per 1,000 pages).
- The async API handles PDFs up to 500 MB and 3,000 pages, which suits large scanned batches.
- It extracts tables, forms and queries, and returns word and line geometry with confidence scores.
Choose GOT-OCR 2.0 if
- It reads formulas, charts, sheet music and chemical structures, and outputs Markdown, LaTeX, TikZ, SMILES and kern.
- It is free to run on your own hardware, and the code is Apache-2.0, so you pay only for compute.
- It supports region OCR guided by box coordinates or color, and it covers English and Chinese documents.
Key differences
| Amazon Textract | GOT-OCR 2.0 | |
|---|---|---|
| How you run it | Hosted AWS API | Self-hosted, available in Hugging Face Transformers |
| Licence | Proprietary | Code Apache-2.0; training data CC BY-NC 4.0 |
| Price | US West (Oregon), first 1M pages/month: text $0.0015/page, Tables $0.015, Forms $0.05, Queries $0.015 | Free; you pay for compute |
| Output formats | JSON, plain text, bounding boxes | Plain text, Markdown, LaTeX, TikZ, SMILES, kern |
| Languages | Text detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. Vertical Japanese and Chinese not supported | English and Chinese documents |
| Published benchmark | 80.9% on RD-TableBench table accuracy (independent) | Not published |
| Known failure modes | Sync API takes one page | Output can loop characters midway (issue #226), returns wrong text on images with no text (issue #235), and format mode is much worse than plain OCR mode (issue #317) |
Sources
- Textract pricing
- Textract quotas
- Textract hard limits
- Reducto RD-TableBench
- GOT-OCR2.0 GitHub
- GOT-OCR 2.0 paper
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsGOT-OCR 2.0
Unified OCR model that reads plain text, tables, formulas, sheet music and charts.
GOT-OCR 2.0 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": ["stepfun/got-ocr-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesGOT-OCR 2.0 alternativesBest OCR models in 2026