Struct Response

pub struct Response {

    pub id: String,
    pub object: String,
    pub created_at: usize,
    pub status: String,
    pub background: bool,
    pub error: Option<String>,
    pub incomplete_details: Option<String>,
    pub instructions: Option<String>,
    pub max_output_tokens: Option<usize>,
    pub max_tool_calls: Option<usize>,
    pub model: String,
    pub output: Vec<Output>,
    pub parallel_tool_calls: bool,
    pub previous_response_id: Option<String>,
    pub reasoning: Reasoning,
    pub service_tier: Option<String>,
    pub store: Option<bool>,
    pub temperature: Option<f64>,
    pub text: Text,
    pub tool_choice: Option<String>,
    pub tools: Option<Vec<Tool>>,
    pub top_logprobs: Option<usize>,
    pub top_p: Option<f64>,
    pub truncation: Option<String>,
    pub usage: Option<Usage>,
    pub user: Option<String>,
    pub metadata: HashMap<String, String>,
}

Complete response from the OpenAI Responses API.

This struct contains all the information returned by the API, including the AI’s outputs, usage statistics, and metadata about the request processing.

Fields

id: String

Unique identifier for this response

object: String

Object type, typically “response”

created_at: usize

Unix timestamp when the response was created

status: String

Status of the response processing

background: bool

Whether the response was processed in the background

error: Option<String>

Error message if the request failed

incomplete_details: Option<String>

Details about incomplete responses

instructions: Option<String>

Instructions that were used for this response

max_output_tokens: Option<usize>

Maximum number of output tokens that were allowed

max_tool_calls: Option<usize>

Maximum number of tool calls that were allowed

model: String

The model that was used to generate the response

output: Vec<Output>

List of outputs from the AI (text, function calls, etc.)

parallel_tool_calls: bool

Whether parallel tool calls were enabled

previous_response_id: Option<String>

ID of the previous response in a conversation chain

reasoning: Reasoning

Reasoning information from the AI

service_tier: Option<String>

Service tier used for processing

store: Option<bool>

Whether the response should be stored

temperature: Option<f64>

Temperature setting used for generation

text: Text

Text formatting configuration

tool_choice: Option<String>

Tool choice configuration that was used

tools: Option<Vec<Tool>>

Tools that were available during generation

top_logprobs: Option<usize>

Number of top log probabilities returned

top_p: Option<f64>

Top-p (nucleus sampling) parameter used

truncation: Option<String>

Truncation strategy that was applied

usage: Option<Usage>

Token usage statistics

user: Option<String>

User identifier associated with the request

metadata: HashMap<String, String>

Additional metadata as key-value pairs

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.

impl Default for Response

fn default() -> Response

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Response

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Response

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.