Access to Vision Models

[omkar.gangan]

More information regarding input format for the image payload is here sambanova_cloud_api_reference

@karan.srivastava

• For multimodal content, use an array of objects to represent different content types, such as text and image. Example format for multimodal:
• [{ "type": "text", "text": "What's in this image?" }, { "type": "image_url", "image_url": { "url": "base64 encoded string of image" } }]

Thanks & Regards