Qianfan OCR vs SmolDocling
SmolDocling is faster; only Qianfan OCR supports handwriting, multilingual; only SmolDocling supports bounding boxes.
Qianfan OCRbaidu/qianfan-ocr | SmolDoclinghuggingface/smoldocling | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 2.0 s / page | 1.0 s / page |
| Best for | Chinese documents | Very cheap page conversion |
| Inputs | PDF, images | PDF, images |
| Languages | Chinese, English and more | Mainly English |
| Max pages per request | 200 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| On OCRRouter | Available | Coming soon |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
Qianfan OCR
Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.
Qianfan OCR detailsSmolDocling
Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.
SmolDocling detailsUse one, fall back to the other
Request body
{
"model": "baidu/qianfan-ocr",
"fallbacks": ["huggingface/smoldocling"],
"file_url": "https://example.com/document.pdf"
}