OCRRouter

PaddleOCR-VL vs Typhoon OCR

Pick PaddleOCR-VL for multilingual documents (109 languages) with formulas, tables and charts, run on your own GPU. Pick Typhoon OCR for Thai and English documents such as government forms and financial reports, or when you want a hosted API option. The main split is language coverage: PaddleOCR-VL is broad, while Typhoon OCR is tuned for Thai and only Thai and English were evaluated.

PaddleOCR-VLpaddle/paddleocr-vlTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price6 credits / page2 credits / page
Per 1,000 pages$6.00$2.00
Typical speed1.3 s / page1.8 s / page
Best forCJK documentsThai documents
InputsPDF, imagesPDF, images
Languages109 languagesThai, English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
FormsNoNo
Multilingual✓ Yes✓ Yes
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 PaddleOCR-VL if

  • It supports 109 languages in one model, including Cyrillic, Arabic, Devanagari and Thai scripts.
  • It recognizes text, tables, formulas and charts, and outputs Markdown and JSON for full pages.
  • At under 1B parameters it runs on much smaller GPUs than 7B document VLMs like olmOCR.

Choose Typhoon OCR if

  • It beat GPT-5 and Gemini 2.5 Pro on Thai government forms in V1.5 (BLEU 0.870), and V2 2B scores 81.3 on MDPBench Thai pages versus 61.3 for its base model.
  • It outputs tables as HTML with merged cells, equations as LaTeX, and marks checkboxes.
  • You can self-host the weights or call it on the Typhoon API as typhoon-ocr-v2.

Key differences

PaddleOCR-VLTyphoon OCR
Languages109 languages, including Cyrillic, Arabic, Devanagari and ThaiThai and English only evaluated
How you run itSelf-host only, via PaddleOCR, vLLM or transformersSelf-host the weights or use the Typhoon API (typhoon-ocr-v2)
LicenceApache-2.0Apache-2.0, subject to OpenTyphoon Terms and Conditions
Size0.9B parameters2B parameters (V2 and V1.5); 0.8B V2 variant
Output formatsMarkdown, JSONMarkdown, HTML, LaTeX
olmOCR-Bench80.0 (independent)84.7 (V2 2B, reported by the authors)
Known failureVersion 1.6 hangs on blurry images, and decoding is about 11x slower because use_cache ships as false. It also regresses Russian and Kazakh OCR on born-digital PDFs versus 1.5.V2 can loop until the token limit, mostly on dense multi-column pages. Key-information extraction is weakest, at 21.0 on ThaiOCRBench.

Sources

What each one is

PaddleOCR-VL

Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.

PaddleOCR-VL details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR 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": "paddle/paddleocr-vl","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

PaddleOCR-VL alternativesTyphoon OCR alternativesBest OCR models in 2026