Struct Response

pub struct Response {

    pub metadata: Option<Metadata>,
    pub top_logprobs: Option<i64>,
    pub temperature: Option<Number>,
    pub top_p: Option<Number>,
    pub user: Option<String>,
    pub service_tier: Option<ServiceTier>,
    pub previous_response_id: Option<String>,
    pub model: ModelIdsResponses,
    pub reasoning: Option<Reasoning>,
    pub background: Option<bool>,
    pub max_output_tokens: Option<i64>,
    pub max_tool_calls: Option<i64>,
    pub text: Option<ResponsePropertiesText>,
    pub tools: Vec<Tool>,
    pub tool_choice: ResponsePropertiesToolChoice,
    pub prompt: Option<Prompt>,
    pub truncation: Option<ResponsePropertiesTruncation>,
    pub id: String,
    pub status: Option<ResponseStatus>,
    pub created_at: Number,
    pub error: Option<ResponseError>,
    pub incomplete_details: Option<ResponseIncompleteDetails>,
    pub output: Vec<OutputItem>,
    pub instructions: Option<ResponseInstructions>,
    pub output_text: Option<String>,
    pub usage: Option<ResponseUsage>,
    pub parallel_tool_calls: bool,
}

Fields

metadata: Option<Metadata>

top_logprobs: Option<i64>

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability.

temperature: Option<Number>

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

top_p: Option<Number>

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

user: Option<String>

A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

service_tier: Option<ServiceTier>

previous_response_id: Option<String>

The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state.

model: ModelIdsResponses

Model ID used to generate the response, like gpt-4o or o3. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

reasoning: Option<Reasoning>

background: Option<bool>

Whether to run the model response in the background. Learn more.

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.

max_tool_calls: Option<i64>

The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored.

text: Option<ResponsePropertiesText>

Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more:

• Text inputs and outputs
• Structured Outputs

tools: Vec<Tool>

An array of tools the model may call while generating a response. You can specify which tool to use by setting the tool_choice parameter.

The two categories of tools you can provide the model are:

• Built-in tools: Tools that are provided by OpenAI that extend the model’s capabilities, like web search or file search. Learn more about built-in tools.
• Function calls (custom tools): Functions that are defined by you, enabling the model to call your own code. Learn more about function calling.

tool_choice: ResponsePropertiesToolChoice

How the model should select which tool (or tools) to use when generating a response. See the tools parameter to see how to specify which tools the model can call.

prompt: Option<Prompt>

truncation: Option<ResponsePropertiesTruncation>

The truncation strategy to use for the model response.

• auto: If the context of this response and previous ones exceeds the model’s context window size, the model will truncate the response to fit the context window by dropping input items in the middle of the conversation.
• disabled (default): If a model response will exceed the context window size for a model, the request will fail with a 400 error.

id: String

Unique identifier for this Response.

status: Option<ResponseStatus>

The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.

created_at: Number

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

error: Option<ResponseError>

incomplete_details: Option<ResponseIncompleteDetails>

Details about why the response is incomplete.

output: Vec<OutputItem>

An array of content items generated by the model.

• The length and order of items in the output array is dependent on the model’s response.
• Rather than accessing the first item in the output array and assuming it’s an assistant message with the content generated by the model, you might consider using the output_text property where supported in SDKs.

instructions: Option<ResponseInstructions>

A system (or developer) message inserted into the model’s context.

When using along with previous_response_id, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses.

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. Supported in the Python and JavaScript SDKs.

usage: Option<ResponseUsage>

parallel_tool_calls: bool

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

Implementations

impl Response

pub fn builder() -> ResponseBuilder<((), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), (), ())>

Create a builder for building Response. On the builder, call .metadata(...)(optional), .top_logprobs(...)(optional), .temperature(...)(optional), .top_p(...)(optional), .user(...)(optional), .service_tier(...)(optional), .previous_response_id(...)(optional), .model(...), .reasoning(...)(optional), .background(...)(optional), .max_output_tokens(...)(optional), .max_tool_calls(...)(optional), .text(...)(optional), .tools(...), .tool_choice(...), .prompt(...)(optional), .truncation(...)(optional), .id(...), .status(...)(optional), .created_at(...), .error(...)(optional), .incomplete_details(...)(optional), .output(...), .instructions(...)(optional), .output_text(...)(optional), .usage(...)(optional), .parallel_tool_calls(...) to set the values of the fields. Finally, call .build() to create the instance of Response.

Trait Implementations

impl Clone for Response

fn clone(&self) -> Response

Returns a duplicate of the value.

const 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 ==.

const 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