Image support for prompt passthrough
This topic explains the image requirements for API.
To include an image into the api/v1/prompt and the
api/v1/prompt/stream, you must Base64 Encode the image and include it into
the optional encoded_image request parameter. Images cannot exceed 3.75 MB
and maximum height, and width of an image is 8000 pixels. The supported file types include:
jpg., png, gif, WebP.
Note: Not all models support images. The GenAI platform can only support image uploads for these models:
- Claude 3 Haiku
- Claude 3 Sonnet
- Claude 3.5 Sonnet