AI-901 practice question 4 of 10

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 model. You need to provide an image for analysis. Which content item should you include in the request?

Full set: 50 questions
Answer options
A: image_base64
B: image_generation
C: output_image
D: input_image Correct answer
Correct Answer:
D. input_image
Explanation

For vision-enabled model deployments, the image to be analysed must be supplied as a separate content item whose type is inputimage. When the Azure OpenAI Responses (batch) API receives a message that contains a content array, it looks for an item marked inputimage and passes the referenced or in-line image to the vision model; any other type name is ignored or considered invalid for analysis. Therefore, inputimage is the only valid key for providing the image itself.

Why Incorrect

A. imagebase64 – Not a recognised content-item type; base-64 data must still be wrapped in an inputimage item.
B. imagegeneration – Reserved for DALL-E image creation tasks, not accepted when submitting an image for analysis.
C. outputimage – Used by the service when it returns generated images; it cannot be used in the request body.

References

1. Microsoft Learn: “Call vision-enabled deployments with the Requests/Responses API”, section “content items”, bullet “inputimage” – learn.microsoft.com/azure/ai-services/openai/how-to/vision#content-items

2. Microsoft Learn REST reference: “chat/completions – request schema”, 2024-03-01-preview, Table 2 “type enumeration (text | inputimage | imageurl | …)” – learn.microsoft.com/rest/api/ai-services/openai/chat-completions

3. Microsoft Learn: “Using batch Requests/Responses with multimodal models”, Example 1 JSON (lines showing "type":"inputimage") – learn.microsoft.com/azure/ai-services/openai/how-to/batch-requests-responses#multimodal-example

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.

Drafted with AI assistance and checked against the answer key.

Keep practicing

Take the free AI-901 practice test

Ten exam-style questions with answers and explanations, plus the exam facts and study guides.

Start the free practice test

More questions

Other AI-901 practice questions

Scroll to Top