OCRRouter

Hunyuan OCR vs Google Cloud Vision OCR

Pick Hunyuan OCR if you want to self-host a ~1B model, need photo and scene text spotting or image translation, and are outside the EU, UK and South Korea. Pick Google Cloud Vision OCR if you want a hosted API for high-volume plain text, signs, labels or handwritten notes, with no GPU to run. Neither gives you table structure. Hunyuan OCR at least outputs Markdown, HTML and LaTeX, while Cloud Vision returns only JSON, plain text and bounding boxes.

Hunyuan OCRtencent/hunyuan-ocrGoogle Cloud Vision OCRgoogle/cloud-vision
TypeOpen sourceOCR API
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page1.0 s / page
Best forChinese documents and photosPhotos and simple scans
InputsPDF, imagesPDF, images
Languages100+ languages100+ languages
Max pages per request5002,000
Tables✓ YesNo
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNo✓ Yes
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 want structured output such as Markdown, HTML, LaTeX or JSON from one ~1B model that also does text spotting, information extraction and image translation.
  • You need to run on your own hardware, including a laptop or CPU via the llama.cpp GGUF path, and pay only for compute.
  • You work with low-resource or ancient scripts, which the model covers through its 12 task types in the vLLM client.

Choose Google Cloud Vision OCR if

  • You want a hosted REST API with no GPU, CUDA or vLLM setup, and the first 1,000 units per month free for each feature.
  • You process large volumes of plain text, since the price drops to $0.60 per 1,000 units above 5M and async batch takes up to 2,000 image files per request.
  • You need handwriting and a full page, block, paragraph, word and symbol hierarchy with bounding polygons, and you are in the EU, UK or South Korea where the Hunyuan licence does not apply.

Key differences

Hunyuan OCRGoogle Cloud Vision OCR
How you run itSelf-hosted via vLLM, Transformers or llama.cpp. CUDA 13 recommended for the unified vLLM environment.Hosted API on Google Cloud, called over REST or client libraries.
LicenceTencent Hunyuan Community License. Excludes the EU, UK and South Korea. Separate licence needed above 100M monthly active users.Proprietary.
PriceFree, you pay for compute.First 1,000 units per month free per feature, then $1.50 per 1,000 units up to 5M, $0.60 per 1,000 above. Each PDF page is one unit.
Output formatsMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes.JSON, plain text, bounding boxes. No Markdown, so you rebuild reading order yourself.
Tables and layoutCovers document parsing. Table accuracy is Not published.No table or layout structure. Google points to Document AI for forms and tables.
BenchmarkParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5).Not published
Known failure or limitArchived 1.0 note said Transformers and vLLM outputs differed in accuracy. Needs CUDA 13 and vLLM 0.25.1+ for the unified environment.Billing must be enabled even for the free units. PDF and TIFF require async processing via Cloud Storage.

Sources

What each one is

Hunyuan OCR

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

Hunyuan OCR details

Google Cloud Vision OCR

Google Cloud's image OCR with text and document text detection, word boxes and confidence.

Google Cloud Vision 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": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Hunyuan OCR alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026