ChatGPT · Schema

ResponseObject

AgentsAIChatGPTEmbeddingsFine-TuningGPT-4GPT-5Language ModelOpenAIRealtime

Properties

Name	Type	Description
id	string	Unique identifier for the response.
object	string	The object type, always response.
created_at	integer	Unix timestamp (in seconds) of when the response was created.
model	string	The model used to generate the response.
status	string	The status of the response generation. One of completed, failed, in_progress, or incomplete.
output	array	An array of content items generated by the model. Can include messages, function calls, web search calls, file search calls, computer actions, and reasoning items.
error	object	An error object if the response generation failed.
incomplete_details	object	Details about why the response is incomplete.
instructions	string	The instructions provided for the response.
metadata	object	Metadata attached to the response.
temperature	number	The sampling temperature used.
top_p	number	The nucleus sampling value used.
max_output_tokens	integer	The maximum output tokens setting.
previous_response_id	string	The ID of the previous response in the conversation.
reasoning	object	The reasoning configuration used.
text	object	The text format configuration used.
tools	array	The tools available during response generation.
tool_choice	string	The tool choice setting used.
truncation	string	The truncation strategy used.
user	string	The end-user identifier.
service_tier	string	The service tier used.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "ResponseObject",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Unique identifier for the response."
    },
    "object": {
      "type": "string",
      "description": "The object type, always response."
    },
    "created_at": {
      "type": "integer",
      "description": "Unix timestamp (in seconds) of when the response was created.\n"
    },
    "model": {
      "type": "string",
      "description": "The model used to generate the response."
    },
    "status": {
      "type": "string",
      "description": "The status of the response generation. One of completed,\nfailed, in_progress, or incomplete.\n"
    },
    "output": {
      "type": "array",
      "description": "An array of content items generated by the model. Can\ninclude messages, function calls, web search calls,\nfile search calls, computer actions, and reasoning items.\n"
    },
    "error": {
      "type": "object",
      "description": "An error object if the response generation failed.\n"
    },
    "incomplete_details": {
      "type": "object",
      "description": "Details about why the response is incomplete.\n"
    },
    "instructions": {
      "type": "string",
      "description": "The instructions provided for the response."
    },
    "metadata": {
      "type": "object",
      "description": "Metadata attached to the response."
    },
    "temperature": {
      "type": "number",
      "description": "The sampling temperature used."
    },
    "top_p": {
      "type": "number",
      "description": "The nucleus sampling value used."
    },
    "max_output_tokens": {
      "type": "integer",
      "description": "The maximum output tokens setting."
    },
    "previous_response_id": {
      "type": "string",
      "description": "The ID of the previous response in the conversation."
    },
    "reasoning": {
      "type": "object",
      "description": "The reasoning configuration used."
    },
    "text": {
      "type": "object",
      "description": "The text format configuration used."
    },
    "tools": {
      "type": "array",
      "description": "The tools available during response generation."
    },
    "tool_choice": {
      "type": "string",
      "description": "The tool choice setting used."
    },
    "truncation": {
      "type": "string",
      "description": "The truncation strategy used."
    },
    "user": {
      "type": "string",
      "description": "The end-user identifier."
    },
    "service_tier": {
      "type": "string",
      "description": "The service tier used."
    }
  }
}