Google Document AI vs Hunyuan OCR
Pick Google Document AI if you want a hosted API on Google Cloud for bulk OCR or RAG chunking, with no GPUs to run. Pick Hunyuan OCR if you want a free, self-hosted ~1B model for photo and scene text, translation, or rare scripts, and you are outside the EU, UK and South Korea. The main split is managed per-page pricing and page limits versus self-hosted compute and a restrictive licence.
Google Document AIgoogle/document-ai | Hunyuan OCRtencent/hunyuan-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 10 credits / page | 2 credits / page |
| Per 1,000 pages | $10.00 | $2.00 |
| Typical speed | 1.4 s / page | 1.5 s / page |
| Best for | Multilingual scans | Chinese documents and photos |
| Inputs | PDF, images | PDF, images |
| Languages | 200+ languages | 100+ languages |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | 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 Google Document AI if
- Enterprise Document OCR costs $1.50 per 1,000 pages, drops to $0.60 above 5M pages a month, and the first 1,000 pages are free.
- Layout Parser includes chunking for RAG at $10 per 1,000 pages, so you do not build that step yourself.
- Batch requests take up to 500 pages, which suits bulk jobs on Google Cloud.
Choose Hunyuan OCR if
- The model is free to self-host, so you pay only for compute, and the llama.cpp GGUF path runs on a CPU, consumer GPU or laptop.
- One ~1B model covers document parsing, text spotting, information extraction and image translation, with 12 task types exposed via the vLLM client.
- It handles images up to 4K and a 128K context window in v1.5, and it supports low-resource and ancient-script OCR.
Key differences
| Google Document AI | Hunyuan OCR | |
|---|---|---|
| How you run it | Hosted API on Google Cloud | Self-hosted via vLLM, Transformers or llama.cpp |
| Licence | Proprietary | Tencent Hunyuan Community License. Excludes the EU, UK and South Korea. A separate licence is needed above 100M monthly active users. |
| Price | Enterprise OCR $1.50 per 1,000 pages. Form Parser $30. Layout Parser $10. | Free, you pay for compute |
| Request limits | Online requests up to 15 pages (30 in imageless mode). Batch up to 500 pages. Form Parser batch up to 100 pages. | Not published as a page limit. Images up to 4K and a 128K context window in v1.5. |
| Output formats | JSON, plain text, bounding boxes, chunks | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes |
| Benchmark | 64.6% on RD-TableBench table accuracy, behind Azure and Textract | ParseBench-2 overall 67.11 and ParseBench mean 63.86 (v1.5). Text score 62.88 in a public CI replay. |
| Known issues | Not suited to long PDFs in one synchronous call or complex tables | Unified setup needs CUDA 13 and vLLM 0.25.1+. An archived 1.0 note said Transformers and vLLM outputs differed in accuracy. |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- HunyuanOCR model card
- Hunyuan Community License
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI 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": "google/document-ai","fallbacks": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI alternativesHunyuan OCR alternativesBest OCR models in 2026