v1

latestOpenAPI 3.0.02026-07-2380631.2 KB

post/v1/responses

Request body

model'openai/gpt-5-4' required
backgroundboolean

Whether to run the model response in the background.

instructionsstring nullable

A system (or developer) message inserted into the model's context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

includestring[] nullable

Specify additional output data to include in the model response. Currently supported values are:

  • code_interpreter_call.outputs: Includes the outputs of python code execution in code interpreter tool call items.
  • computer_call_output.output.image_url: Include image urls from the computer call output.
  • file_search_call.results: Include the search results of the file search tool call.
  • message.output_text.logprobs: Include logprobs with assistant messages.
  • reasoning.encrypted_content: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the store parameter is set to false, or when an organization is enrolled in the zero data retention program).
max_output_tokensinteger

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

previous_response_idstring nullable

The unique ID of the previous response to the model. Use this to create multi-turn conversations.

storeboolean nullable

Whether to store the generated model response for later retrieval via API.

streamboolean nullable

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

truncation'auto' | 'disabled'

The truncation strategy to use for the model response.

  • auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
  • disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.
parallel_tool_callsboolean nullable

Whether to allow the model to run tool calls in parallel.

temperaturenumber nullable

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_pnumber

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.

Response

backgroundboolean nullable

Whether to run the model response in the background.

created_atnumber required

Unix timestamp (in seconds) of when this Response was created.

idstring required

Unique identifier for this Response.

max_output_tokensinteger nullable

An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.

metadataobject nullable

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

modelstring required

Model ID used to generate the response.

object'response' required

The object type of this resource - always set to response.

output_textstring nullable

SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present. Supported in the Python and JavaScript SDKs.

parallel_tool_callsboolean required

Whether to allow the model to run tool calls in parallel.

previous_response_idstring nullable

The unique ID of the previous response to the model. Use this to create multi-turn conversations.

service_tierstring nullable

Specifies the processing type used for serving the request.

status'completed' | 'failed' | 'in_progress' | 'cancelled' | 'queued' | 'incomplete'

The status of the response generation.

temperaturenumber nullable

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_pnumber nullable

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

truncation'auto' | 'disabled' nullable

The truncation strategy to use for the model response.

  • auto: If the context of this response and previous ones exceeds the model's context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
  • disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.