OCRRouter

MonkeyOCR vs Typhoon OCR

Pick MonkeyOCR for English and Simplified Chinese PDFs such as academic papers with formulas and tables, where its OmniDocBench edit distance is the best reported by its authors. Pick Typhoon OCR for Thai and Thai-English documents like government forms and financial reports, or if you need a hosted API and a licence without a non-commercial restriction. The main split is language and licence: MonkeyOCR v1 weights cannot be used commercially without a written licence, and Typhoon OCR is Apache-2.0 subject to the OpenTyphoon Terms and Conditions.

MonkeyOCRmonkeyocr/monkeyocrTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page1.8 s / page
Best forChinese and English PDFsThai documents
InputsPDF, imagesPDF, images
LanguagesChinese, EnglishThai, English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 MonkeyOCR if

  • You parse English or Simplified Chinese PDFs, and the pro-3B model reports OmniDocBench overall edit distance of 0.138 (EN) and 0.206 (ZH), lower is better.
  • You work with academic papers and need formulas and tables, with table TEDS of 81.5 (EN) and 87.5 (ZH) on pro-3B.
  • You need block coordinates: output includes JSON with bounding boxes and a layout PDF, plus Markdown, LaTeX and HTML.

Choose Typhoon OCR if

  • Your documents are in Thai or mixed Thai and English: V2 2B scores 81.3 on MDPBench Thai pages against 61.3 for its base model.
  • You process Thai government forms, financial reports or books: V1.5 reached BLEU 0.870 on Thai government forms, ahead of GPT-5 and Gemini 2.5 Pro.
  • You want the choice of self-hosting or the Typhoon API (typhoon-ocr-v2), and a 2B model that scores 84.7 on olmOCR-bench, with a 0.8B V2 variant also available.

Key differences

MonkeyOCRTyphoon OCR
LicenceCode Apache-2.0. v1 weights are research and non-commercial only; commercial use needs a written licence.Apache-2.0, subject to OpenTyphoon Terms and Conditions.
How you run itSelf-hosted only, via LMDeploy or Docker.Self-hosted weights, or the Typhoon API as typhoon-ocr-v2.
Model size3B and 1.2B. The 1.2B model is about 36% faster than 3B for about 1.6% lower accuracy.2B (V2 and V1.5), plus a 0.8B V2 variant.
LanguagesEnglish and Simplified Chinese. Traditional Chinese and multilingual text are not fully supported.Thai and English. No other languages were evaluated.
Output formatsMarkdown, JSON, LaTeX, HTML, bounding boxes.Markdown, HTML, LaTeX. Tables come out as HTML with merged cells, and checkboxes are marked.
Speed and hardwarePro-3B runs at about 0.49 pages/s on a 3090. Works on an 8GB RTX 4060 with quantized weights.Not published
Known failurePhotographed text and handwriting are not fully supported. Docker on 20/30/40-series and V100 needs a patched image to avoid an LMDeploy shared-memory error.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

MonkeyOCR

Open-source document parser that splits work into structure, recognition and relation steps.

MonkeyOCR 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": "monkeyocr/monkeyocr","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MonkeyOCR alternativesTyphoon OCR alternativesBest OCR models in 2026