DeepSeek-OCR vs Jina OCR
DeepSeek-OCR is faster; only DeepSeek-OCR supports bounding boxes.
DeepSeek-OCRdeepseek/deepseek-ocr | Jina OCRjina/jina-ocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credits / page | 1 credits / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 1.1 s / page | 1.5 s / page |
| Best for | Cheap bulk conversion | Clean Markdown at low cost |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | About 100 languages |
| Max pages per request | 200 | 200 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ 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
Jina OCR
Compact page-to-Markdown model from Jina AI, built on the DeepSeek-OCR encoder.
Jina OCR detailsTry both on your own file
Run the file once with each model and compare the output.
结果
识别出的 Markdown 或 JSON 会显示在这里。
Use one, fall back to the other
Request body
{
"model": "deepseek/deepseek-ocr",
"fallbacks": ["jina/jina-ocr"],
"file_url": "https://example.com/document.pdf"
}