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 questionsFor 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.
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.
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
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
- The clue is 'Responses API' plus 'provide an image for analysis', which means image input.
- Responses API content item types are prefixed by direction: input_text and input_image for requests, output_* for results.
- An image coming in for analysis is therefore input_image, carrying a URL or base64 data URL.
- image_generation is a tool for creating images, and output_image refers to output, so both are eliminated.
Each option
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.
Keep practicing
Take the free AI-901 practice test
Ten exam-style questions with answers and explanations, plus the exam facts and study guides.
More questions
Other AI-901 practice questions
- Question 1You have a Microsoft Foundry project that contains a vision-enabled model deployment. You…
- Question 2You need to create an AI agent in Microsoft Foundry that follows a specific role and beha…
- Question 3You need to compare the costs of large language models (LLMs) for a generative AI solutio…
