OCRRouter

Nanonets-OCR vs SmolDocling

Pick Nanonets-OCR for printed business documents where you need signatures, watermarks, checkboxes or flowcharts turned into structured output, and accept that its olmOCR-bench overall score is 69.5. Pick SmolDocling only for cheap English experiments with a 256M model that gives bounding boxes. It is a preview release, so move to Granite-Docling for anything in production.

Nanonets-OCRnanonets/nanonets-ocrSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.8 s / page1.0 s / page
Best forMarkdown with semantic tagsVery cheap page conversion
InputsPDF, imagesPDF, images
LanguagesMultilingualMainly English
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
Forms✓ YesNo
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 Nanonets-OCR if

  • It tags signatures, watermarks and image descriptions, and converts checkboxes to unicode symbols.
  • It extracts flowcharts and org charts as Mermaid code and tells inline LaTeX from display LaTeX.
  • The authors report DocVQA 89.43 and ChartQA 78.56 for the OCR2-3B model.

Choose SmolDocling if

  • At 256M parameters it runs on modest hardware, and the authors report about 0.35 seconds per page on an A100 with vLLM.
  • It returns DocTags with location tags and bounding boxes, plus Markdown, HTML and JSON.
  • It carries a stated Apache-2.0 licence, while the Nanonets-OCR2-3B model card states none.

Key differences

Nanonets-OCRSmolDocling
Model size3B (Hugging Face lists about 4B params)256M
LicenceNot stated on the Nanonets-OCR2-3B model card; base model is Qwen2.5-VL-3BApache-2.0 per model summary (metadata tag says CDLA-Permissive-2.0)
Output formatsMarkdown, HTML, LaTeX, MermaidDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
Reported benchmarksolmOCR-bench overall 69.5, DocVQA 89.43, ChartQA 78.56 (OCR2-3B, by the authors)Table TEDS 0.82 on FinTabNet 150dpi, full-page OCR F1 0.80, OCRBench 338 (by the authors)
HandwritingNot trained on handwriting and can hallucinate. One test saw generation loops with CER up to 2100% and 69.1s per image on an L4.Not published
LanguagesNot publishedEnglish only
Known failureFixed prompt only. The team expects hallucination with other prompts.Endless token repetition and missing closing tags. Output can loop on some images and become very slow.

Sources

What each one is

Nanonets-OCR

Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.

Nanonets-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": "nanonets/nanonets-ocr","fallbacks": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Nanonets-OCR alternativesSmolDocling alternativesBest OCR models in 2026