GPT vs Typhoon OCR
Pick GPT when you need handwritten notes, custom JSON extraction or document question answering through a hosted API. Pick Typhoon OCR for Thai and Thai-English documents such as government forms and financial reports, where you can self-host an Apache-2.0 model at 2B parameters. The main split is scope: GPT is a general hosted model with variable per-page cost, and Typhoon OCR is a narrow Thai and English OCR model you can run yourself.
GPTopenai/gpt | Typhoon OCRtyphoon/typhoon-ocr | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 11 credits / page | 2 credits / page |
| Per 1,000 pages | $11.00 | $2.00 |
| Typical speed | 2.4 s / page | 1.8 s / page |
| Best for | Messy scans, custom instructions | 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 GPT if
- Choose GPT for handwritten notes: an HN user reported about 5% errors on messy cursive versus about 30% for Mistral OCR.
- Choose GPT when you need extraction into custom JSON, or question answering over documents, since you can prompt it to do the task directly.
- Choose GPT if you want a hosted API that takes PDFs up to 50 MB per request and sends both extracted text and page images to the model.
Choose Typhoon OCR if
- Choose Typhoon OCR for Thai government forms: V1.5 beat GPT-5 and Gemini 2.5 Pro there with a BLEU of 0.870.
- Choose Typhoon OCR if you need to self-host: weights are free under Apache-2.0 (subject to OpenTyphoon Terms and Conditions) and you pay only for compute.
- Choose Typhoon OCR for tables and equations, since it outputs tables as HTML with merged cells, equations as LaTeX and marks checkboxes.
Key differences
| GPT | Typhoon OCR | |
|---|---|---|
| How you run it | 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 | Token-based per model; page images add input tokens, so cost per page is not fixed | Free when self-hosted (you pay for compute); API pricing not published on the model card |
| Output formats | Markdown, JSON, plain text | Markdown, HTML, LaTeX |
| OmniDocBench | GPT-5.2: 85.50 on v1.5 and 86.59 on v1.6 (independent) | V2 2B: 90.97 on v1.6 (reported by the authors) |
| Languages | Not published | Thai and English only evaluated |
| Known failure | No bounding boxes or confidence scores in the standard response | V2 can loop until the token limit on dense multi-column pages; weakest at key-information extraction (21.0 on ThaiOCRBench) |
Sources
- OpenAI file inputs docs
- OmniDocBench leaderboard
- HN Mistral OCR thread
- OpenAI API pricing
- 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": "openai/gpt","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
GPT vs Florence-2GPT vs GOT-OCR 2.0Claude vs Typhoon OCRGemini Flash vs Typhoon OCRGPT vs dots.ocrTyphoon OCR vs ABBYY FineReaderTyphoon OCR vs PixtralGPT vs Nanonets-OCR
GPT alternativesTyphoon OCR alternativesBest OCR models in 2026