Vision Language Models
Send images to vision-language models for understanding, description, and analysis.
Vision-Language Models (VLMs) can process both image and text inputs. Use the image_url content type in the messages array to pass images alongside text.
For list of all available models, checkout Model Catalog
Image via URL
Image via Base64
Multiple images
You can send multiple images in a single request:
Notes
- Base64-encoded images should ideally be under 1 MB to avoid timeouts.
- Image tokens count toward billing together with text tokens.
- Streaming is supported with vision inputs.
Last updated on