TrOCR vs Granite Docling
TrOCR is faster; only TrOCR supports handwriting; only Granite Docling supports tables, math, bounding boxes.
TrOCRmicrosoft/trocr | Granite Doclingibm/granite-docling | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 1.2 s / page | 1.5 s / page |
| Best for | Handwritten text lines | Small-model document conversion |
| Inputs | images | PDF, images |
| Languages | English | English, experimental CJK and Arabic |
| Max pages per request | 100 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | No | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | No |
| On OCRRouter | Coming soon | 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
TrOCR
Transformer text recognition model. Reads single text lines, including handwriting.
TrOCR detailsGranite Docling
Compact IBM vision model that converts pages to DocTags for the Docling pipeline.
Granite Docling detailsUse one, fall back to the other
Request body
{
"model": "microsoft/trocr",
"fallbacks": ["ibm/granite-docling"],
"file_url": "https://example.com/document.pdf"
}