OCRRouter

docTR vs SmolDocling

Pick docTR when you need words and lines with coordinates from invoices or receipts and plan to feed them into your own extraction code. Pick SmolDocling only for experiments converting English pages to Markdown, HTML or JSON with tables and formulas, and move to Granite-Docling for production. The main split is that docTR returns text boxes only, while SmolDocling returns full document structure but is a preview model with looping failures.

docTRmindee/doctrSmolDoclinghuggingface/smoldocling
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed0.9 s / page1.0 s / page
Best forWord-level OCR with positionsVery cheap page conversion
InputsPDF, imagesPDF, images
LanguagesMainly Latin scriptsMainly English
Max pages per request500500
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
MultilingualNoNo
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 docTR if

  • You need word-level OCR with a nested page, block, line and word structure and coordinates as JSON.
  • You train or tune your own models, since you can choose the detection and recognition architectures and use straight or rotated boxes.
  • You want Docker images and a hosted demo on Hugging Face Spaces, plus a key information extraction predictor.

Choose SmolDocling if

  • You need Markdown, HTML, JSON or LaTeX from a page, with tables (OTSL), code, formulas and charts handled by one model.
  • You want a 256M parameter model that runs on modest hardware, at about 0.35 seconds per page on an A100 with vLLM.
  • You are experimenting with tiny document VLMs on English pages and a low budget.

Key differences

docTRSmolDocling
ApproachTwo-stage text detection and recognition library on PyTorch256M parameter vision-language model that outputs DocTags for Docling
LicenceApache-2.0Apache-2.0 per the model summary; the metadata tag says CDLA-Permissive-2.0
Output formatsJSON, plain text, bounding boxesDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
Tables and formulasNo table, formula or Markdown output; words and lines onlyTables, code, formulas and charts in one model; TEDS 0.82 on FinTabNet at 150dpi (authors' figure)
HardwareCPU or NVIDIA GPU; GPU Docker images need CUDA 12.2 or newerSmall enough for modest hardware; about 0.35 seconds per page on an A100 with vLLM
LanguagesNot publishedEnglish only
Known failureSplit-crop merging misjoins readings across repeated characters (issue #2229); cropping images gives poorer results (issue #2007); ONNX export of MASTER truncates decoding steps (issue #2224)Endless token repetition and missing closing tags; output loops on some images and generation becomes very slow (Docling issue #1515)

Sources

What each one is

docTR

Open-source OCR library from Mindee with separate text detection and recognition models.

docTR 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": "mindee/doctr","fallbacks": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

docTR alternativesSmolDocling alternativesBest OCR models in 2026