OCRRouter

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-aiTyphoon OCRtyphoon/typhoon-ocr
TypeOCR APIOpen source
Price10 credits / page2 credits / page
Per 1,000 pages$10.00$2.00
Typical speed1.4 s / page1.8 s / page
Best forMultilingual scansThai documents
InputsPDF, imagesPDF, images
Languages200+ languagesThai, English
Max pages per request500500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNoNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
Forms✓ YesNo
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 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 AITyphoon OCR
How you run itHosted API onlySelf-host the weights, or use the Typhoon API as typhoon-ocr-v2
LicenceProprietaryApache-2.0, subject to OpenTyphoon Terms and Conditions
PriceEnterprise 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 pagesFree when self-hosted, you pay for compute. Typhoon API pricing not published on the model card
Output formatsJSON, plain text, bounding boxes, chunksMarkdown, HTML, LaTeX
Page and size limitsOnline requests 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch 100 pagesNot published
Table benchmark64.6% on RD-TableBench (independent, Reducto), behind Azure and TextractNot published on RD-TableBench. Authors report 84.7 on olmOCR-bench and 90.97 on OmniDocBench v1.6 (V2 2B)
Known failureWeak on complex tables; not suited to long PDFs in one synchronous callV2 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

Google Document AI

Google Cloud OCR with layout parsing and specialised processors.

Google Document AI 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": "google/document-ai","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Google Document AI alternativesTyphoon OCR alternativesBest OCR models in 2026