Amazon Textract vs TrOCR
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you need tables, forms and page-level JSON from one API call. Pick TrOCR when you already have cropped single text-line images, mostly English handwriting or receipts, and want an MIT-licensed model you can run and fine-tune yourself. The main split is scope: Textract reads whole documents, TrOCR reads one line at a time.
Amazon Textractaws/textract | TrOCRmicrosoft/trocr | |
|---|---|---|
| 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 | 1.2 s / page |
| Best for | Forms and key-value extraction | Handwritten text lines |
| Inputs | PDF, images | images |
| Languages | 6 languages | English |
| Max pages per request | 3,000 | 100 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | ✓ Yes |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| 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 reads full pages and PDFs, and the async API handles files up to 500 MB and 3,000 pages.
- It extracts tables, forms and queries, and scores 80.9% on RD-TableBench table accuracy in an independent test.
- It returns word and line geometry with confidence scores as JSON, plain text and bounding boxes.
Choose TrOCR if
- It reports a 2.89 character error rate on the IAM handwriting set with the large model, per the paper.
- It is MIT licensed and free to self-host, and you only pay for compute.
- It ships separate checkpoints for handwritten (IAM), printed (SROIE) and scene text, and you can fine-tune it on your own line images.
Key differences
| Amazon Textract | TrOCR | |
|---|---|---|
| Input scope | Full pages and PDFs; sync API takes one page, async API takes up to 3,000 pages | Single text-line images only; you need a separate line detector |
| How you run it | Hosted API on AWS | Library you run locally through Hugging Face transformers |
| Licence | Proprietary | MIT (microsoft/unilm repository) |
| Price | US West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015/page, Forms $0.05/page, Queries $0.015/page | Free, self-hosted (you pay for compute) |
| Output | JSON, plain text, bounding boxes with confidence scores | Plain text only; no layout, table or page-level output |
| Languages | Text detection covers English, French, German, Italian, Portuguese and Spanish; handwriting and Queries are English only | Released checkpoints are English-focused; other languages need fine-tuning |
| Benchmark | 80.9% on RD-TableBench table accuracy (independent) | 2.89 CER on IAM handwriting with TrOCR-large (reported by the authors) |
Sources
- Textract pricing
- Textract quotas
- Reducto RD-TableBench
- TrOCR paper (arXiv 2109.10282)
- trocr-large-handwritten model card
- microsoft/unilm repository
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsTrOCR
Transformer text recognition model. Reads single text lines, including handwriting.
TrOCR 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": ["microsoft/trocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesTrOCR alternativesBest OCR models in 2026