Struct Response

pub struct Response {

    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: Vec<Tool>,
    pub tool_choice: ResponseProperties_ToolChoice,
    pub truncation: Option<String>,
    pub id: String,
    pub object: String,
    pub status: Option<String>,
    pub created_at: f64,
    pub error: Option<ResponseError>,
    pub incomplete_details: Option<Response_Variant3_IncompleteDetails>,
    pub output: Vec<OutputItem>,
    pub output_text: Option<String>,
    pub usage: Option<ResponseUsage>,
    pub parallel_tool_calls: 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: Vec<Tool>

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

tool_choice: ResponseProperties_ToolChoice

truncation: Option<String>

The truncation strategy to use for the model response.

id: String

Unique identifier for this Response.

object: String

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

status: Option<String>

The status of the response generation.

created_at: f64

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

error: Option<ResponseError>

incomplete_details: Option<Response_Variant3_IncompleteDetails>

output: Vec<OutputItem>

An array of content items generated by the model.

output_text: Option<String>

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

usage: Option<ResponseUsage>

parallel_tool_calls: bool

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

Trait Implementations

impl Clone for Response

fn clone(&self) -> Response

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Response

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

Formats the value using the given formatter.