OCRRouter

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-ocrOpenOCRfudan/openocr
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.8 s / page0.5 s / page
Best forThai documentsLightweight OCR pipeline on CPU
InputsPDF, imagesPDF, images
LanguagesThai, EnglishChinese and English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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 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 OCROpenOCR
LanguagesThai and English only evaluatedChinese and English only
How you run itSelf-host the weights, or use the Typhoon API (typhoon-ocr-v2)Self-host as a Python library; no hosted API
LicenceApache-2.0, subject to OpenTyphoon Terms and ConditionsApache-2.0
Model size2B (V2 and V1.5); 0.8B V2 variant0.1B (OpenDoc-0.1B and UniRec-0.1B)
Output formatsMarkdown, HTML, LaTeXPlain text, LaTeX, bounding boxes
BenchmarkOmniDocBench v1.6 90.97 and olmOCR-bench 84.7 (V2 2B), reported by the authorsOmniDocBench v1.5 90.57 (OpenDoc-0.1B), reported by the authors; no independent replication found
Known failureV2 can loop until the token limit, mostly on dense multi-column pages; key-information extraction scores 21.0 on ThaiOCRBenchDocument 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 details

OpenOCR

Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.

OpenOCR 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": "typhoon/typhoon-ocr","fallbacks": ["fudan/openocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Typhoon OCR alternativesOpenOCR alternativesBest OCR models in 2026