Struct Response

pub struct Response {

    pub created_at: u64,
    pub error: Option<ErrorObject>,
    pub id: String,
    pub incomplete_details: Option<IncompleteDetails>,
    pub instructions: Option<String>,
    pub max_output_tokens: Option<u32>,
    pub metadata: Option<HashMap<String, String>>,
    pub model: String,
    pub object: String,
    pub output: Vec<OutputContent>,
    pub parallel_tool_calls: Option<bool>,
    pub previous_response_id: Option<String>,
    pub reasoning: Option<ReasoningConfig>,
    pub service_tier: Option<ServiceTier>,
    pub status: Status,
    pub temperature: Option<f32>,
    pub text: Option<TextConfig>,
    pub tool_choice: Option<ToolChoice>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub top_p: Option<f32>,
    pub truncation: Option<Truncation>,
    pub usage: Option<Usage>,
    pub user: Option<String>,
}

The complete response returned by the Responses API.

Fields

created_at: u64

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

error: Option<ErrorObject>

Error object if the API failed to generate a response.

id: String

Unique identifier for this response.

incomplete_details: Option<IncompleteDetails>

Details about why the response is incomplete, if any.

instructions: Option<String>

Instructions that were inserted as the first item in context.

max_output_tokens: Option<u32>

The value of max_output_tokens that was honored.

metadata: Option<HashMap<String, String>>

Metadata tags/values that were attached to this response.

model: String

Model ID used to generate the response.

object: String

The object type – always response.

output: Vec<OutputContent>

The array of content items generated by the model.

parallel_tool_calls: Option<bool>

Whether parallel tool calls were enabled.

previous_response_id: Option<String>

Previous response ID, if creating part of a multi-turn conversation.

reasoning: Option<ReasoningConfig>

Reasoning configuration echoed back (effort, summary settings).

service_tier: Option<ServiceTier>

The service tier that actually processed this response.

status: Status

The status of the response generation.

temperature: Option<f32>

Sampling temperature that was used.

text: Option<TextConfig>

Text format configuration echoed back (plain, json_object, json_schema).

tool_choice: Option<ToolChoice>

How the model chose or was forced to choose a tool.

tools: Option<Vec<ToolDefinition>>

Tool definitions that were provided.

top_p: Option<f32>

Nucleus sampling cutoff that was used.

truncation: Option<Truncation>

Truncation strategy that was applied.

usage: Option<Usage>

Token usage statistics for this request.

user: Option<String>

End-user ID for which this response was generated.

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<'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 PartialEq for Response

fn eq(&self, other: &Response) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

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.

impl StructuralPartialEq for Response