API in Foundry and Azure OpenAI that accepts an input array of messages and content items, for instance input_text and input_image, and produces output items; response.output_text holds the text.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains Responses API in context, with comparison tables and the common traps.
Terms in this definition
- API
Short for application programming interface: a contract that client code calls programmatically, for example a web API secured with tokens or the Files, Images or Responses APIs.
- Azure OpenAI
Use of OpenAI models in Azure, including GPT, o-series, embeddings, image and Whisper, through either a Foundry resource or an Azure OpenAI resource. Content Understanding isn't available from a standalone Azure OpenAI resource.
- Agents (classic) API
First-generation Foundry Agent Service API, based on threads, messages and runs. It is deprecated, replaced by conversations and responses, and retires on 31 March 2027.
Related terms
- Chat Completions API
Azure OpenAI interface built around a messages array of roles, plus
response_formatand tools that nest a function object; it remains supported, though the Responses API is advised for new applications. - input_image
The Responses API content item representing an image. Its
image_urlholds a base64 data URI or public URL, or afile_idcan point to a Files API upload, anddetailmay be set optionally. - input_text
The Responses API content item that holds the prompt text in its
textfield. A single user message can combine it withinput_imageitems. - output_text
Shortcut property on a Responses API result containing the text the model generated.
- Response compaction
Operation in the Responses API that condenses the context of a lengthy conversation into compaction items, leaving room in the context window for further turns.