Struct CreateResponse

pub struct CreateResponse {

    pub metadata: Option<Metadata>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub user: Option<String>,
    pub service_tier: Option<ServiceTier>,
    pub previous_response_id: Option<String>,
    pub model: ModelIdsResponses,
    pub reasoning: Option<Reasoning>,
    pub max_output_tokens: Option<i64>,
    pub instructions: Option<String>,
    pub text: Option<ResponseProperties_Text>,
    pub tools: Option<Vec<Tool>>,
    pub tool_choice: Option<ResponseProperties_ToolChoice>,
    pub truncation: Option<String>,
    pub input: CreateResponse_Variant3_Input,
    pub include: Option<Vec<Includable>>,
    pub parallel_tool_calls: Option<bool>,
    pub store: Option<bool>,
    pub stream: Option<bool>,
}

Fields

metadata: Option<Metadata>

temperature: Option<f64>

What sampling temperature to use, between 0 and 2.

top_p: Option<f64>

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass.

user: Option<String>

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

service_tier: Option<ServiceTier>

previous_response_id: Option<String>

The unique ID of the previous response to the model.

model: ModelIdsResponses

Model ID used to generate the response, like gpt-4o or o3.

reasoning: Option<Reasoning>

max_output_tokens: Option<i64>

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

instructions: Option<String>

Inserts a system (or developer) message as the first item in the model’s context.

text: Option<ResponseProperties_Text>

tools: Option<Vec<Tool>>

An array of tools the model may call while generating a response.

tool_choice: Option<ResponseProperties_ToolChoice>

truncation: Option<String>

The truncation strategy to use for the model response.

input: CreateResponse_Variant3_Input

include: Option<Vec<Includable>>

Specify additional output data to include in the model response.

parallel_tool_calls: Option<bool>

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

store: Option<bool>

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

stream: Option<bool>

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

Trait Implementations

impl Clone for CreateResponse

fn clone(&self) -> CreateResponse

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for CreateResponse

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.