OCRRouter

Surya vs SmolDocling

Pick Surya when you need layout detection, reading order and bounding boxes across 90+ languages, and you can run a vLLM or llama.cpp backend. Pick SmolDocling only for English page conversion experiments on tiny hardware. It is a preview release and its authors point users to Granite-Docling.

Suryadatalab/suryaSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.5 s / page1.0 s / page
Best forLayout and line-level OCRVery cheap page conversion
InputsPDF, imagesPDF, images
Languages90+ languagesMainly 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 covers 90+ languages, while SmolDocling is English only.
  • One model returns layout labels, reading order, OCR, HTML tables and KaTeX math with per-block bounding boxes.
  • It scores 83.7% on olmOCR-bench and runs on CPU or Apple Silicon via llama.cpp, with peak memory of about 4 to 6 GB on an M4 Max.

Choose SmolDocling if

  • At 256M parameters it is small enough for modest hardware, against 689M for Surya.
  • It runs at about 0.35 seconds per page on an A100 with vLLM.
  • It is Apache-2.0 with no revenue cap, while Surya's weights need a commercial license above $5M in funding or revenue.

Key differences

SuryaSmolDocling
LicenceCode Apache-2.0; weights under a modified AI Pubs Open Rail-M, free for research, personal use and companies under $5M funding or revenueApache-2.0 per the model summary (the metadata tag says CDLA-Permissive-2.0)
Model size689M parameters256M parameters
How you run itLightweight client against a separate vLLM or llama.cpp server; NVIDIA GPU, CPU or Apple SiliconSelf-hosted VLM; about 0.35 s per page on an A100 with vLLM
Languages90+ languages; only 21 of 91 reach a 90% pass rateEnglish only
Output formatsJSON, HTML, LaTeX, bounding boxes, plain textDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
Reported benchmarksolmOCR-bench 83.7%; 91-language multilingual pass rate 74.9%Table TEDS 0.82 on FinTabNet; full-page OCR F1 0.80; OCRBench 338
Known failureSurya 2.5 table output lacks row and column geometry; multilingual tables score 58.1; handwriting and complex tables are better sent to the hosted Datalab APIOutput can loop on some images and become very slow; endless token repetition and missing closing tags are typical defects

Sources

What each one is

Surya

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

Surya details

SmolDocling

Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.

SmolDocling 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": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Surya alternativesSmolDocling alternativesBest OCR models in 2026