SmolVLM OCR online
Hugging Face's small open vision models (256M to 2.2B).
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- huggingface/smolvlm
- Type
- Open source
- Price
- 1 credit / page ($1.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- images
- Languages
- Mainly English
- Max pages per request
- 50
- Output
- Markdown, JSON
- License
- Apache-2.0
- Supports
- Multilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "huggingface/smolvlm",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'SmolVLM speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
SmolVLM pricing
SmolVLM 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 50 free credits, enough for about 50 pages with this model. See pricing for credit packs.
Similar models
1OCRmyPDFCommand-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
ocrmypdf/ocrmypdf1 credit / page2Llama 3.2 11B VisionMeta's smaller Llama 3.2 vision model (September 2024).meta/llama-3-2-11b-vision1 credit / page3Mistral Small 3.2Open-weight 24B Mistral model with image input.mistral/mistral-small-3-21 credit / pageAll SmolVLM alternativesBest OCR models by use case
Compare SmolVLM
SmolVLM vs OCRmyPDFSmolVLM vs Llama 3.2 11B VisionSmolVLM vs Mistral Small 3.2SmolVLM vs Llama 4 ScoutSmolVLM vs Claude Haiku 4.5SmolVLM vs o4-mini