You have a Microsoft Foundry project that contains a vision-enabled model deployment. You use the Azure OpenAI Responses API to send a prompt to the…

Question breakdown

Tests

Supply images to vision models with the Azure OpenAI Responses API

Difficulty

Medium

Key idea: In the Responses API, an image sent for analysis is placed in the input content array as an item of type input_image.

How to reach the answer

1. The clue is 'Responses API' plus 'provide an image for analysis', which means image input.
2. Responses API content item types are prefixed by direction: input_text and input_image for requests, output_* for results.
3. An image coming in for analysis is therefore input_image, carrying a URL or base64 data URL.
4. image_generation is a tool for creating images, and output_image refers to output, so both are eliminated.

Each option

• AIncorrect. image_base64 is not a content item type; base64 data goes inside an input_image item.
• BIncorrect. image_generation is a tool for creating images, not for submitting one to analyze.
• CIncorrect. output_image refers to content the model produces, not content sent in a request.
• DCorrect. input_image is the content type the Responses API uses for image input to a vision-capable model.

Common trap: image_base64 looks plausible because images are often sent as base64, but encoding is a payload detail, not the content item type.

In practice: When building multimodal apps with the Responses API, you combine an input_text prompt and an input_image item in one user message, for example to extract data from a photographed receipt.

Remember: In the Responses API, send images to the model as input_image content items.

Official documentation: Azure OpenAI Responses API

Drafted with AI assistance and checked against the answer key.