OCRRouter

DeepSeek-OCR vs SmolDocling

Pick DeepSeek-OCR for cheap self-hosted bulk OCR where an MIT licence and GPU throughput matter. Pick SmolDocling only for English page-conversion experiments on small hardware, since it is a preview release and its authors point users to Granite-Docling. Both loop on some inputs, so check output on your own tables.

DeepSeek-OCRdeepseek/deepseek-ocrSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.1 s / page1.0 s / page
Best forCheap bulk conversionVery cheap page conversion
InputsPDF, imagesPDF, images
Languages100+ languagesMainly English
Max pages per request200500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ 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 DeepSeek-OCR if

  • The MIT licence allows commercial use without a licence conflict.
  • It offers resolution modes from 64 to 400 vision tokens per page, so you can trade detail for cost.
  • The authors quote about 2,500 tokens per second of PDF throughput on one A100-40G.

Choose SmolDocling if

  • At 256M parameters it is small enough to run on modest hardware.
  • It outputs DocTags, Markdown, HTML, JSON and LaTeX, and one model handles text, tables, code, formulas and charts with location tags.
  • The authors report about 0.35 seconds per page on an A100 with vLLM.

Key differences

DeepSeek-OCRSmolDocling
LicenceMITApache-2.0 per the model summary; the metadata tag says CDLA-Permissive-2.0
How you run itSelf-host with Transformers or vLLM on a CUDA GPU (reference setup CUDA 11.8, PyTorch 2.6, bfloat16)Self-host, 256M parameters, outputs DocTags for Docling
PriceFree, you pay for computeFree, you pay for compute
Output formatsMarkdown, plain text, HTML, bounding boxesDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
Reported benchmarksNoneTable TEDS 0.82 on FinTabNet 150dpi, full-page OCR F1 0.80, OCRBench 338 (authors)
LanguagesNot statedEnglish only
Known failuresRepeated tokens and looping over table headers (GitHub issues #12 and #16); a blank image took 30 seconds and gave repeated garbage; it corrects nonsense words instead of copying themEndless token repetition and missing closing tags; output loops on some images and generation gets very slow (Docling issue #1515)
Project statusCurrent releasePreview release, superseded by Granite-Docling, which scores higher on every reported task (TEDS 0.97 vs 0.82)

Sources

What each one is

DeepSeek-OCR

Open-source vision model that compresses pages into few tokens.

DeepSeek-OCR 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": "deepseek/deepseek-ocr","fallbacks": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

DeepSeek-OCR alternativesSmolDocling alternativesBest OCR models in 2026