Florence-2 vs Doubao-Seed-1.6
Florence-2 is cheaper per page. Florence-2 is faster. Only Florence-2 supports Bounding boxes. Only Doubao-Seed-1.6 supports Tables, Math, Multilingual.
Florence-2microsoft/florence-2 | Doubao-Seed-1.6bytedance/doubao-seed-1-6 | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 3 credits / page |
| Per 1,000 pages | $1.00 | $3.00 |
| Typical speed | 0.8 s / page | 2.5 s / page |
| Best for | Lightweight OCR with boxes | Chinese documents via Volcano Engine |
| Inputs | images | images |
| Languages | English | Mainly Chinese and English |
| Max pages per request | 500 | 50 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| 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
Florence-2
Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.
Florence-2 detailsDoubao-Seed-1.6
ByteDance's multimodal Doubao model on Volcano Engine, with image input.
Doubao-Seed-1.6 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": "microsoft/florence-2","fallbacks": ["bytedance/doubao-seed-1-6"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Florence-2 vs SmolVLMFlorence-2 vs GLM-4.1V-ThinkingTesseract.js vs Doubao-Seed-1.6Typhoon OCR vs Doubao-Seed-1.6Qianfan OCR vs Florence-2Florence-2 vs RolmOCRolmOCR vs Florence-2Florence-2 vs InternVL3.5
Florence-2 alternativesDoubao-Seed-1.6 alternativesBest OCR models in 2026