Claude vs Typhoon OCR
Pick Claude when you need to read long reports, answer questions with page-level citations, or pull data into JSON with reasoning, and you can pay per token. Pick Typhoon OCR for Thai and Thai-English documents such as government forms, financial reports and books, especially when you want to self-host a 2B model under Apache-2.0 and pay only for compute. The main split is hosted token-priced reading versus a small open model tuned for Thai.
Claudeanthropic/claude | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 2.6 s / page | 1.8 s / page |
| Best for | Long dense documents | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 50+ languages | Thai, English |
| Max pages per request | 100 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| 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 Claude if
- You need citations at page level, because the API accepts PDFs natively and returns them.
- You need long inputs: up to 600 pages per request on 1M-context models (100 otherwise), with a 32 MB payload.
- You want JSON extraction with reasoning, since each page is read as text plus a rendered image, so charts and scans are visible to the model.
Choose Typhoon OCR if
- Your documents are Thai or Thai-English: V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870), and V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model.
- You want to self-host: weights are Apache-2.0 (subject to OpenTyphoon Terms and Conditions), with a 2B model and a 0.8B V2 variant.
- You need tables as HTML with merged cells, equations as LaTeX and marked checkboxes.
Key differences
| Claude | Typhoon OCR | |
|---|---|---|
| Deployment | Hosted API only | Self-hosted weights, or the Typhoon API as typhoon-ocr-v2 |
| Licence | Proprietary | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| Price | Per token, no extra PDF fee; a PDF page uses 1,500 to 3,000 tokens plus image tokens | Free to self-host, you pay for compute; Typhoon API pricing not published on the model card |
| Output formats | Markdown, JSON, plain text | Markdown, HTML, LaTeX |
| Benchmarks | No published OmniDocBench score for any Claude model in the leaderboards checked | OmniDocBench v1.6 90.97, olmOCR-bench 84.7, ThaiOCRBench 59.9 (V2 2B, author-reported) |
| Languages | Not published | Only Thai and English evaluated |
| Known failure | Password-protected or encrypted PDFs are not supported; bulk OCR is costly | V2 can loop until the token limit on dense multi-column pages; key-information extraction is weakest at 21.0 on ThaiOCRBench |
Sources
- Claude PDF support docs
- Claude PDF page limits
- OmniDocBench leaderboard
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
Typhoon 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": "anthropic/claude","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Claude vs Florence-2Claude vs GOT-OCR 2.0LlamaParse vs Typhoon OCRGPT vs Typhoon OCRPaddleOCR (PP-OCR) vs Typhoon OCRHunyuan OCR vs Typhoon OCRTrOCR vs Typhoon OCRGoogle Document AI vs Typhoon OCR
Claude alternativesTyphoon OCR alternativesBest OCR models in 2026