OCRRouter

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-ocrTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page1.8 s / page
Best forChinese documents and photosThai documents
InputsPDF, imagesPDF, images
Languages100+ languagesThai, English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 OCRTyphoon OCR
LicenceTencent Hunyuan Community License; excludes EU, UK and South Korea; separate licence above 100M monthly active usersApache-2.0, subject to OpenTyphoon Terms and Conditions
How you run itSelf-host only, via vLLM, Transformers or llama.cppSelf-host the weights or use the Typhoon API (typhoon-ocr-v2)
Model size~1B2B (V2 and V1.5); 0.8B V2 variant
HardwareNVIDIA GPU with CUDA 13 recommended for the unified vLLM environment; llama.cpp GGUF for CPU, consumer GPU or laptopNot published
Output formatsMarkdown, HTML, LaTeX, JSON, plain text, bounding boxesMarkdown, HTML, LaTeX
LanguagesIncludes low-resource and ancient scriptsOnly Thai and English evaluated
Known failureArchived 1.0 note said Transformers and vLLM outputs differed in accuracy; ParseBench-2 overall is 67.11V2 can loop until the token limit on dense multi-column pages; key-information extraction scores only 21.0 on ThaiOCRBench

Sources

What each one is

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan OCR details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

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