Typhoon OCR vs OpenOCR
Pick Typhoon OCR for Thai or Thai-English documents such as government forms, financial reports and books. Pick OpenOCR for Chinese and English academic PDFs with formulas, or when you want a very small self-hosted model. The main split is language: Typhoon OCR is built for Thai, while OpenOCR's document models cover only Chinese and English.
Typhoon OCRtyphoon/typhoon-ocr | OpenOCRfudan/openocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 1.8 s / page | 0.5 s / page |
| Best for | Thai documents | Lightweight OCR pipeline on CPU |
| Inputs | PDF, images | PDF, images |
| Languages | Thai, English | Chinese and English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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
- Your documents are in Thai or mixed Thai and English, and V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870).
- You need tables as HTML with merged cells, equations as LaTeX and checkboxes marked in the output.
- You want a hosted option as well as self-hosting, since the model is also served on the Typhoon API as typhoon-ocr-v2.
Choose OpenOCR if
- Your documents are Chinese and English academic PDFs with formulas, and UniRec-0.1B reads plain text and single or multi-line formulas in one model.
- You need a very small model: OpenDoc-0.1B reports 90.57 on OmniDocBench v1.5 at 0.1B parameters.
- You want a plain Apache-2.0 licence with no extra terms, a Python library, and ONNX export for deployment.
Key differences
| Typhoon OCR | OpenOCR | |
|---|---|---|
| Languages | Thai and English only evaluated | Chinese and English only |
| How you run it | Self-host the weights, or use the Typhoon API (typhoon-ocr-v2) | Self-host as a Python library; no hosted API |
| Licence | Apache-2.0, subject to OpenTyphoon Terms and Conditions | Apache-2.0 |
| Model size | 2B (V2 and V1.5); 0.8B V2 variant | 0.1B (OpenDoc-0.1B and UniRec-0.1B) |
| Output formats | Markdown, HTML, LaTeX | Plain text, LaTeX, bounding boxes |
| Benchmark | OmniDocBench v1.6 90.97 and olmOCR-bench 84.7 (V2 2B), reported by the authors | OmniDocBench v1.5 90.57 (OpenDoc-0.1B), reported by the authors; no independent replication found |
| Known failure | V2 can loop until the token limit, mostly on dense multi-column pages; key-information extraction scores 21.0 on ThaiOCRBench | Document parsing depends on a separate layout model, PP-DocLayoutV2 from PaddlePaddle; no hardware or throughput figures published |
Sources
What each one is
Typhoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon OCR detailsOpenOCR
Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.
OpenOCR 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": "typhoon/typhoon-ocr","fallbacks": ["fudan/openocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Typhoon OCR vs RolmOCRTyphoon OCR vs Tesseract.jsFlorence-2 vs OpenOCRGOT-OCR 2.0 vs OpenOCRQianfan OCR vs OpenOCRPaddleOCR-VL vs OpenOCRKraken vs Typhoon OCROpenOCR vs RolmOCR
Typhoon OCR alternativesOpenOCR alternativesBest OCR models in 2026