Typhoon OCR vs Google Cloud Vision OCR
Pick Typhoon OCR for Thai and Thai-English documents such as government forms, financial reports and books, where you want Markdown or HTML tables and can self-host. Pick Google Cloud Vision OCR for high-volume plain text from photos, labels and handwritten notes, where bounding boxes and a pay-per-page hosted API fit. The main split is structured output and self-hosting on one side, raw text with coordinates on the other.
Typhoon OCRtyphoon/typhoon-ocr | Google Cloud Vision OCRgoogle/cloud-vision | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.8 s / page | 1.0 s / page |
| Best for | Thai documents | Photos and simple scans |
| Inputs | PDF, images | PDF, images |
| Languages | Thai, English | 100+ languages |
| Max pages per request | 500 | 2,000 |
| Tables | ✓ Yes | No |
| Handwriting | No | ✓ Yes |
| Math | No | No |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | ✓ Yes |
| Forms | No | 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 Typhoon OCR if
- You need tables as HTML with merged cells, equations as LaTeX and Markdown output for an LLM pipeline.
- Your documents are Thai or Thai-English, such as government forms and financial reports, where V1.5 scored BLEU 0.870 and beat GPT-5 and Gemini 2.5 Pro.
- You want to self-host the weights under Apache-2.0 (subject to OpenTyphoon Terms and Conditions) and pay only for compute.
Choose Google Cloud Vision OCR if
- You need word, paragraph, block and page boxes with bounding polygons rather than reading-order Markdown.
- You process photos of signs and labels, or handwritten notes, using DOCUMENT_TEXT_DETECTION with language hints.
- You run high volume: the first 1,000 units a month are free, and the price drops to $0.60 per 1,000 above 5M units.
Key differences
| Typhoon OCR | Google Cloud Vision OCR | |
|---|---|---|
| How you run it | Self-host the weights, or call the Typhoon API as typhoon-ocr-v2 | Hosted API on Google Cloud only, over REST or client libraries |
| Licence | Apache-2.0, subject to OpenTyphoon Terms and Conditions | Proprietary |
| Price | Free when self-hosted, you pay for compute. Typhoon API price not published on the model card | First 1,000 units a month free, then $1.50 per 1,000 up to 5M, $0.60 per 1,000 above. One PDF page is one unit |
| Output formats | Markdown, HTML, LaTeX | JSON, plain text, bounding boxes |
| Tables and layout | Tables as HTML with merged cells, checkboxes marked | No table or layout structure; Google points to Document AI for forms and tables |
| Languages | Thai and English only evaluated | Not published |
| Known failure | V2 can loop until the token limit on dense multi-column pages. Key-information extraction is weakest, 21.0 on ThaiOCRBench | You rebuild reading order yourself. PDF and TIFF need async processing via Cloud Storage, and billing must be enabled even for the free units |
Sources
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
- Typhoon OCR 1.5 release blog
- Vision pricing
- OCR docs
What each one is
Typhoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon OCR detailsGoogle Cloud Vision OCR
Google Cloud's image OCR with text and document text detection, word boxes and confidence.
Google Cloud Vision 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": "typhoon/typhoon-ocr","fallbacks": ["google/cloud-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Typhoon OCR alternativesGoogle Cloud Vision OCR alternativesBest OCR models in 2026