Struct ModelResponse 

pub struct ModelResponse {

    pub id: String,
    pub object: String,
    pub created_at: i64,
    pub model: String,
    pub output: Vec<ModelOutput>,
    pub parallel_tool_calls: bool,
    pub text: ModelResponseConfiguration,
    pub tool_choice: ModelToolChoice,
    pub tools: Vec<ModelTool>,
    pub status: String,
    pub store: bool,
    pub metadata: Value,
    pub usage: Option<ModelUsage>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub max_output_tokens: Option<i32>,
    pub previous_response_id: Option<String>,
    pub reasoning: Option<ReasoningConfiguration>,
    pub user: Option<String>,
    pub incomplete_details: Option<IncompleteDetails>,
    pub background: Option<bool>,
    pub debug_output: Option<DebugOutput>,
}

The response body for /v1/responses endpoint.

Fields

id: String

Unique ID of the response.

object: String

The object type of this resource. Always set to response.

created_at: i64

The Unix timestamp (in seconds) for the response creation time.

model: String

Model name used to generate the response.

output: Vec<ModelOutput>

The response generated by the model.

parallel_tool_calls: bool

Whether to allow the model to run parallel tool calls.

text: ModelResponseConfiguration

Settings for customizing a text response from the model.

tool_choice: ModelToolChoice

Controls which (if any) tool is called by the model.

tools: Vec<ModelTool>

A list of tools the model may call.

status: String

Status of the response. One of completed, in_progress or incomplete.

store: bool

Whether to store the input message(s) and model response for later retrieval.

metadata: Value

Only included for compatibility.

usage: Option<ModelUsage>

Token usage information.

temperature: Option<f32>

What sampling temperature to use, between 0 and 2.

top_p: Option<f32>

An alternative to sampling with temperature, called nucleus sampling.

max_output_tokens: Option<i32>

Max number of tokens that can be generated in a response.

previous_response_id: Option<String>

The ID of the previous response from the model.

reasoning: Option<ReasoningConfiguration>

Reasoning configuration. Only for reasoning models.

user: Option<String>

A unique identifier representing your end-user.

incomplete_details: Option<IncompleteDetails>

Details about why the response is incomplete.

background: Option<bool>

Whether to process the response asynchronously in the background.

debug_output: Option<DebugOutput>

Debug output. Only available to trusted testers.

Trait Implementations

impl Clone for ModelResponse

fn clone(&self) -> ModelResponse

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelResponse

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

Formats the value using the given formatter.

impl Default for ModelResponse

fn default() -> ModelResponse

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelResponse

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelResponse

fn eq(&self, other: &ModelResponse) -> 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 ModelResponse

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 ModelResponse