SmolDocling API
Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.
- Model ID
- huggingface/smoldocling
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 1.0 s / page
- Inputs
- PDF, images
- Languages
- Mainly English
- Max pages per request
- 500
- Output
- Markdown, JSON with positions
- Supports
- TablesMathBounding boxes
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "huggingface/smoldocling",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'SmolDocling is not connected yet. The price below is an estimate. You can call the models that are live today with the same request.
SmolDocling speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
SmolDocling pricing
SmolDocling costs 1 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $1.00. You only pay for pages that return a result.
New accounts get 200 free credits, enough for about 200 pages with this model. See pricing for credit packs.
Similar models
1Granite DoclingCompact IBM vision model that converts pages to DocTags for the Docling pipeline.
ibm/granite-docling1 credit / page2GOT-OCR 2.0Unified OCR model that reads plain text, tables, formulas, sheet music and charts.stepfun/got-ocr-21 credit / page3DoclingIBM's open-source document converter with a structured document model.ibm/docling2 credits / pageCompare SmolDocling
SmolDocling vs Granite DoclingSmolDocling vs GOT-OCR 2.0SmolDocling vs DoclingSmolDocling vs TesseractSmolDocling vs Typhoon OCRSmolDocling vs MonkeyOCR