Struct Response 

pub struct Response {

    pub id: String,
    pub object: String,
    pub created_at: f64,
    pub model: String,
    pub output: Vec<ResponseOutputItem>,
    pub status: Option<String>,
    pub error: Option<ResponseError>,
    pub incomplete_details: Option<IncompleteDetails>,
    pub instructions: Option<String>,
    pub metadata: Option<HashMap<String, String>>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub max_output_tokens: Option<i64>,
    pub previous_response_id: Option<String>,
    pub usage: Option<ResponseUsage>,
    pub tools: Option<Vec<ResponseTool>>,
    pub tool_choice: Option<ResponseToolChoice>,
    pub parallel_tool_calls: Option<bool>,
    pub truncation: Option<String>,
    pub reasoning: Option<Reasoning>,
    pub service_tier: Option<String>,
    pub text: Option<ResponseTextConfig>,
    pub completed_at: Option<f64>,
    pub background: Option<bool>,
    pub user: Option<String>,
    pub top_logprobs: Option<i64>,
    pub max_tool_calls: Option<i64>,
}

Response from POST /responses.

Fields

id: String

Unique response identifier.

object: String

Object type — always “response”.

created_at: f64

Unix timestamp when the response was created.

model: String

Model used for generation.

output: Vec<ResponseOutputItem>

Output items (messages, function calls, reasoning, etc.).

status: Option<String>

Response status: “in_progress”, “completed”, “failed”, “incomplete”.

error: Option<ResponseError>

Error details if the response failed.

incomplete_details: Option<IncompleteDetails>

Details about why the response is incomplete.

instructions: Option<String>

System instructions used.

metadata: Option<HashMap<String, String>>

Metadata key-value pairs.

temperature: Option<f64>

Temperature used.

top_p: Option<f64>

Top-p (nucleus sampling) used.

max_output_tokens: Option<i64>

Max output tokens limit.

previous_response_id: Option<String>

Previous response ID for multi-turn.

usage: Option<ResponseUsage>

Token usage information.

tools: Option<Vec<ResponseTool>>

Tools used in the response.

tool_choice: Option<ResponseToolChoice>

Tool choice setting.

parallel_tool_calls: Option<bool>

Whether parallel tool calls were enabled.

truncation: Option<String>

Truncation strategy.

reasoning: Option<Reasoning>

Reasoning configuration.

service_tier: Option<String>

Service tier used.

text: Option<ResponseTextConfig>

Text output configuration.

completed_at: Option<f64>

Unix timestamp when the response completed.

background: Option<bool>

Whether the response ran in background mode.

user: Option<String>

End user identifier.

top_logprobs: Option<i64>

Top log probabilities count.

max_tool_calls: Option<i64>

Maximum number of tool calls.

Implementations

impl Response

pub fn output_text(&self) -> String

Get the text output, concatenating all text content blocks.

pub fn function_calls(&self) -> Vec<FunctionCall>

Extract all function calls from the response output.

pub fn has_function_calls(&self) -> bool

Check if the response has any function calls.

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 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.