SmolDocling vs Aya Vision
SmolDocling is faster. Only SmolDocling supports Tables, Math, Bounding boxes. Only Aya Vision supports Multilingual.
SmolDoclinghuggingface/smoldocling | Aya Visioncohere/aya-vision | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 1.0 s / page | 3.0 s / page |
| Best for | Very cheap page conversion | Multilingual image questions |
| Inputs | PDF, images | images |
| Languages | Mainly English | 23 languages |
| Max pages per request | 500 | 50 |
| Tables | ✓ Yes | No |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
SmolDocling
Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.
SmolDocling detailsAya Vision
Cohere's open-weight multilingual vision models (8B and 32B, March 2025).
Aya Vision detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
Use one, fall back to the other
{"model": "huggingface/smoldocling","fallbacks": ["cohere/aya-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
SmolDocling vs Command A VisionSmolDocling vs LLaVA-OneVisionMonkeyOCR vs Aya VisionGranite Docling vs Aya VisionGranite Docling vs SmolDoclingRapidOCR vs SmolDoclingOCRmyPDF vs SmolDoclingQianfan OCR vs SmolDocling
SmolDocling alternativesAya Vision alternativesBest OCR models in 2026