Hunyuan OCR vs Typhoon OCR
Pick Hunyuan OCR for photo and scene text, image translation, and low-resource or historical scripts, and only if you are outside the EU, UK and South Korea. Pick Typhoon OCR for Thai and English documents such as government forms and financial reports, and when you want a hosted API as well as open weights. The main split is language and licence: Typhoon is tuned for Thai pages under Apache-2.0, while Hunyuan is a ~1B all-purpose model with a regional licence.
Hunyuan OCRtencent/hunyuan-ocr | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.5 s / page | 1.8 s / page |
| Best for | Chinese documents and photos | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | Thai, English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ 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 Hunyuan OCR if
- You need text spotting or image translation on photos, since one ~1B model covers parsing, spotting, extraction and translation.
- You work with low-resource or ancient scripts, which are among the 12 task types it exposes via vLLM.
- You need to run on a laptop or CPU, because a llama.cpp GGUF path exists, and you can accept a licence that excludes the EU, UK and South Korea.
Choose Typhoon OCR if
- Your documents are Thai or Thai-English mixed, such as government forms, financial reports and books; V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model.
- You want an Apache-2.0 licence (subject to OpenTyphoon Terms) with no regional exclusions, and the choice of self-hosting or the Typhoon API.
- You need tables as HTML with merged cells, equations as LaTeX and marked checkboxes, with olmOCR-bench at 84.7 for a 2B model.
Key differences
| Hunyuan OCR | Typhoon OCR | |
|---|---|---|
| Licence | Tencent Hunyuan Community License; excludes EU, UK and South Korea; separate licence above 100M monthly active users | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| How you run it | Self-host only, via vLLM, Transformers or llama.cpp | Self-host the weights or use the Typhoon API (typhoon-ocr-v2) |
| Model size | ~1B | 2B (V2 and V1.5); 0.8B V2 variant |
| Hardware | NVIDIA GPU with CUDA 13 recommended for the unified vLLM environment; llama.cpp GGUF for CPU, consumer GPU or laptop | Not published |
| Output formats | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes | Markdown, HTML, LaTeX |
| Languages | Includes low-resource and ancient scripts | Only Thai and English evaluated |
| Known failure | Archived 1.0 note said Transformers and vLLM outputs differed in accuracy; ParseBench-2 overall is 67.11 | V2 can loop until the token limit on dense multi-column pages; key-information extraction scores only 21.0 on ThaiOCRBench |
Sources
- HunyuanOCR model card
- Hunyuan Community License
- HunyuanOCR GitHub
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon 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": "tencent/hunyuan-ocr","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Hunyuan OCR alternativesTyphoon OCR alternativesBest OCR models in 2026