Amazon Textract vs Hunyuan OCR
Pick Amazon Textract for English forms and invoices on AWS, and for large scanned PDF batches. It is a managed API with async PDF support up to 3,000 pages and per-page pricing from $0.0015. Pick Hunyuan OCR if you need Chinese, Japanese, low-resource or historical scripts, photo text, image translation, or Markdown/HTML/LaTeX output, and you can run a ~1B model yourself outside the EU, UK and South Korea.
Amazon Textractaws/textract | Hunyuan OCRtencent/hunyuan-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 | 1.5 s / page |
| Best for | Forms and key-value extraction | Chinese documents and photos |
| Inputs | PDF, images | PDF, images |
| Languages | 6 languages | 100+ languages |
| Max pages per request | 3,000 | 500 |
| 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
- You work on English forms and invoices and want managed Forms, Tables and Queries extraction on AWS.
- You process large scanned PDF batches: the async API takes PDFs up to 500 MB and 3,000 pages.
- You want word and line geometry with confidence scores, and plain text detection at $1.50 per 1,000 pages.
Choose Hunyuan OCR if
- You need OCR beyond Textract's six Latin-script languages, including low-resource and ancient scripts, or photo and scene text spotting.
- You want Markdown, HTML, LaTeX or JSON output from one ~1B model that also handles extraction and image translation, with no per-page fee.
- You want to run it on your own hardware: vLLM on an NVIDIA GPU with CUDA 13, or llama.cpp GGUF on a CPU, consumer GPU or laptop.
Key differences
| Amazon Textract | Hunyuan OCR | |
|---|---|---|
| How you run it | Hosted AWS API | Self-hosted via vLLM, Transformers or llama.cpp |
| Licence | Proprietary | Tencent Hunyuan Community License; excludes EU, UK and South Korea; separate license needed above 100M monthly active users |
| 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 | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes |
| Languages | Text detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. No vertical Japanese or Chinese. | Covers low-resource and ancient-script OCR; full language list Not published |
| Benchmark | RD-TableBench table accuracy 80.9% | ParseBench-2 overall 67.11; ParseBench mean 63.86 (v1.5) |
| Limits and known issues | Sync API takes one page; async handles up to 500 MB and 3,000 pages | Needs CUDA 13 and vLLM 0.25.1+ for the unified environment; archived 1.0 note said Transformers and vLLM outputs differed in accuracy |
Sources
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsHunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesHunyuan OCR alternativesBest OCR models in 2026