OCRRouter

Surya vs MonkeyOCR

Pick Surya for local layout detection, reading order and bounding boxes across 90+ languages, especially on a laptop or CPU. Pick MonkeyOCR for English and Simplified Chinese PDFs such as academic papers with formulas and tables, but only for research unless you get a written commercial license. Surya is free for companies under $5M funding or revenue, while MonkeyOCR v1 weights are non-commercial.

Suryadatalab/suryaMonkeyOCRmonkeyocr/monkeyocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page1.5 s / page
Best forLayout and line-level OCRChinese and English PDFs
InputsPDF, imagesPDF, images
Languages90+ languagesChinese, English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ 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 Surya if

  • It runs on CPU and Apple Silicon through llama.cpp, with peak memory of about 4.3-5.9 GB on an M4 Max.
  • One 689M model returns layout labels, reading order, OCR, HTML tables and KaTeX math with per-block bounding boxes.
  • It covers 90+ languages and is free for personal use and for companies under $5M funding or revenue.

Choose MonkeyOCR if

  • Pro-3B reports the best overall OmniDocBench edit distance among the models compared, in English and Chinese (0.138 / 0.206).
  • It reports table TEDS of 81.5 English and 87.5 Chinese on OmniDocBench, which suits papers with tables and formulas.
  • Pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy, and quantized weights run on an 8GB RTX 4060.

Key differences

SuryaMonkeyOCR
LicenceCode Apache-2.0; weights free for research, personal use and companies under $5M funding/revenueCode Apache-2.0; v1 weights research and non-commercial only, commercial use needs a written license
How you run itLight client against a vLLM or llama.cpp server you run yourselfSelf-hosted via LMDeploy or Docker; 20/30/40-series and V100 Docker needs a patched image
Model size689M parameters3B and 1.2B
HardwareNVIDIA GPU via vLLM, or CPU/Apple Silicon via llama.cppTested on RTX 3090/4090, A6000, H800, A100; RTX 4060 8GB with quantized models
Speed4.52 pages/s at 192 DPI on one H100 with vLLM; 0.198 pages/s on an M4 Max at 96 DPI with llama.cpp Q8_0About 0.49 pages/s for pro-3B on a 3090
Output formatsJSON, HTML, LaTeX, bounding boxes, plain textMarkdown, JSON, LaTeX, HTML, bounding boxes
Known failureSurya 2.5 table output lacks row/column geometry; multilingual tables score 58.1; not for photos or natural scenesPhotographed text, handwriting, Traditional Chinese and multilingual text are not fully supported

Sources

What each one is

Surya

Open-source OCR toolkit with line detection, layout analysis, reading order and tables.

Surya details

MonkeyOCR

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

MonkeyOCR 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": "datalab/surya","fallbacks": ["monkeyocr/monkeyocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Surya alternativesMonkeyOCR alternativesBest OCR models in 2026