QuestionQ91

VerifiedImplement AI solutions by using Microsoft Foundry

You have a Microsoft Foundry project that includes a vision-enabled GPT model deployment.

You need to build an application that sends an image and a text-based question to the model in one request.

What should you use?

Explanation

The Azure OpenAI Responses API supports multimodal input for vision-enabled GPT models by placing input_text and input_image content parts in the same request, enabling the model to answer a text question about an image.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!