Amazon Textract vs Unlimited OCR
Pick Amazon Textract for English forms, invoices and large scanned PDF batches if you already run on AWS and want a managed API with per-page pricing. Pick Unlimited OCR for long reports and books that you want as Markdown or text with boxes in one request, if you can run an NVIDIA GPU or use the Baidu Cloud endpoint. The main split is hosted AWS API with language limits versus an MIT-licensed self-hosted model with GPU needs and reported looping and hallucination.
Amazon Textractaws/textract | Unlimited OCRbaidu/unlimited-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 1.2 s / page | 1.2 s / page |
| Best for | Forms and key-value extraction | Books and very long documents |
| Inputs | PDF, images | PDF, images |
| Languages | 6 languages | 30+ languages |
| Max pages per request | 3,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| 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
- Basic text detection costs $0.0015 per page ($1.50 per 1,000 pages) in US West (Oregon) for the first 1M pages a month, with no GPU to run.
- The async API handles PDFs up to 500 MB and 3,000 pages, and returns word and line geometry with confidence scores.
- It extracts tables, forms and queries through the AWS API, and scores 80.9% on RD-TableBench table accuracy in an independent test.
Choose Unlimited OCR if
- It is MIT licensed, so you can use it commercially with no copyleft, and self-hosting costs only your compute.
- It parses 40+ pages in a single forward pass with roughly constant memory, and outputs Markdown, plain text and bounding boxes.
- You are not tied to a cloud: run it with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product.
Key differences
| Amazon Textract | Unlimited OCR | |
|---|---|---|
| How you run it | Hosted AWS API only | Self-host with vLLM, SGLang or transformers, or hosted in Baidu Cloud |
| Licence | Proprietary | MIT |
| Price | $0.0015/page text detection, $0.015 Tables, $0.05 Forms, $0.015 Queries (US West Oregon, first 1M pages/month) | Free self-hosted, you pay for compute; hosted price Not published |
| Output formats | JSON, plain text, bounding boxes (no Markdown without post-processing) | Markdown, plain text, bounding boxes |
| Document size | Async API: PDFs up to 500 MB and 3,000 pages; sync API takes one page | 40+ pages in one pass; context capped at 32,768 tokens, multi-page input only in base mode |
| Languages | Text detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. No vertical Japanese or Chinese | Not published |
| Known failures and hardware | Not published | Repetition loops (issue #55), hallucinated text (issue #58), little bold or italic styling kept, needs an NVIDIA GPU; version 2 runs out of memory on 12 GB GPUs under SGLang |
Sources
- Textract pricing
- Textract quotas
- Reducto RD-TableBench
- Hugging Face model card
- Issue #55 repetition
- Issue #116 OOM on 12 GB
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsUnlimited OCR
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Unlimited OCR 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": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesUnlimited OCR alternativesBest OCR models in 2026