| Overview |
Microsoft's computer vision service for image analysis, OCR, spatial analysis, and image captioning with Florence model. |
Access Meta's Llama family of open-source large language models through various hosting providers. |
| Pricing |
Pay-per-use ($-$$) |
Free (Free) |
| Key Features |
- Florence model
- Image analysis
- OCR
- Spatial analysis
- Image captioning
- Object detection
- Custom models
|
- Llama 3.1
- Llama 3
- Multiple sizes (8B-405B)
- Open weights
- Commercial license
|
| Pros |
- Strong OCR
- Florence model
- Azure integration
- Custom training
|
- Fully open weights
- No API costs
- Customizable
- Strong performance
|
| Cons |
- Azure dependency
- Complex pricing
- Region availability
|
- Requires self-hosting or third-party
- No official hosted API
- Resource intensive for large models
|
