Google Document AI vs Typhoon OCR
Pick Google Document AI for bulk OCR on Google Cloud and for RAG chunking with Layout Parser. Pick Typhoon OCR for Thai and English documents such as government forms, financial reports and books. The main split is scope: Document AI is a hosted, per-page-priced service, while Typhoon OCR is an open 2B model tuned for Thai.
Google Document AIgoogle/document-ai | Typhoon OCRtyphoon/typhoon-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 | 1.8 s / page |
| Best for | Multilingual scans | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 200+ languages | Thai, English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| 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
- You want a managed API with Enterprise Document OCR at $1.50 per 1,000 pages, dropping to $0.60 above 5M pages a month.
- You need RAG chunking, which Layout Parser includes at $10 per 1,000 pages.
- You process large batches, since batch requests take up to 500 pages.
Choose Typhoon OCR if
- Your documents are Thai or Thai-English mixed, such as government forms, financial reports or books.
- You want to self-host open weights under Apache-2.0 and pay only for compute.
- You need tables as HTML with merged cells, equations as LaTeX and checkboxes marked.
Key differences
| Google Document AI | Typhoon OCR | |
|---|---|---|
| How you run it | Hosted API only | Self-host the weights, or use the Typhoon API as typhoon-ocr-v2 |
| Licence | Proprietary | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| Price | Enterprise Document OCR $1.50 per 1,000 pages ($0.60 above 5M/month, first 1,000 free); Layout Parser $10; Form Parser $30 per 1,000 pages | Free when self-hosted, you pay for compute. Typhoon API pricing not published on the model card |
| Output formats | JSON, plain text, bounding boxes, chunks | Markdown, HTML, LaTeX |
| Page and size limits | Online requests 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch 100 pages | Not published |
| Table benchmark | 64.6% on RD-TableBench (independent, Reducto), behind Azure and Textract | Not published on RD-TableBench. Authors report 84.7 on olmOCR-bench and 90.97 on OmniDocBench v1.6 (V2 2B) |
| Known failure | Weak on complex tables; not suited to long PDFs in one synchronous call | V2 can loop until the token limit on dense multi-column pages; key-information extraction scores only 21.0 on ThaiOCRBench |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI 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.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Use one, fall back to the other
{"model": "google/document-ai","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI vs Florence-2Google Document AI vs GOT-OCR 2.0DeepSeek-OCR vs Typhoon OCRAzure Document Intelligence vs Typhoon OCRTyphoon OCR vs PixtralGoogle Document AI vs GLM-OCRGLM-OCR vs Typhoon OCRTyphoon OCR vs InternVL3.5
Google Document AI alternativesTyphoon OCR alternativesBest OCR models in 2026