Struct ChatOptions 

pub struct ChatOptions {

    pub temperature: Option<f64>,
    pub max_tokens: Option<u32>,
    pub top_p: Option<f64>,
    pub stop_sequences: Vec<String>,
    pub capture_usage: Option<bool>,
    pub capture_content: Option<bool>,
    pub capture_reasoning_content: Option<bool>,
    pub capture_tool_calls: Option<bool>,
    pub capture_raw_body: Option<bool>,
    pub response_format: Option<ChatResponseFormat>,
    pub normalize_reasoning_content: Option<bool>,
    pub reasoning_effort: Option<ReasoningEffort>,
    pub verbosity: Option<Verbosity>,
    pub seed: Option<u64>,
    pub service_tier: Option<ServiceTier>,
    pub extra_headers: Option<Headers>,
}

Options considered by all Client::exec_* chat calls.

A default can be set on the Client during builder configuration. Per-call options take precedence over client defaults.

Fields

temperature: Option<f64>

Sampling temperature (if supported by the provider).

max_tokens: Option<u32>

Maximum tokens to generate (if supported).

top_p: Option<f64>

Nucleus sampling (top-p), if supported.

stop_sequences: Vec<String>

Sequences that halt generation when encountered.

capture_usage: Option<bool>

(streaming) Capture usage metadata; available in StreamEnd.captured_usage.

capture_content: Option<bool>

(streaming) Concatenate content chunks; available in StreamEnd.captured_content.

capture_reasoning_content: Option<bool>

(streaming) Concatenate reasoning chunks; available in StreamEnd.captured_reasoning_content.

capture_tool_calls: Option<bool>

(streaming) Collect tool calls; available in StreamEnd.captured_tool_calls.

capture_raw_body: Option<bool>

Capture the raw HTTP body (primarily for debugging/inspection).

response_format: Option<ChatResponseFormat>

Desired response format (e.g., ChatResponseFormat::JsonMode for OpenAI-style JSON mode).

Note: Additional formats may be added in the future.

normalize_reasoning_content: Option<bool>

Extract -style reasoning blocks into ChatResponse.reasoning_content when present.

reasoning_effort: Option<ReasoningEffort>

Preferred reasoning effort, when supported by the provider.

verbosity: Option<Verbosity>

Verbosity (for OpenAI gpt-5),

seed: Option<u64>

Seed for repeatability, if supported.

service_tier: Option<ServiceTier>

Service tier preference (OpenAI-specific, for flex processing).

extra_headers: Option<Headers>

Additional HTTP headers to include with the request.

Implementations

impl ChatOptions

Chainable Setters

pub fn with_temperature(self, value: f64) -> Self

Sets the sampling temperature.

pub fn with_max_tokens(self, value: u32) -> Self

Sets the maximum number of output tokens.

pub fn with_top_p(self, value: f64) -> Self

Sets nucleus sampling (top-p).

pub fn with_capture_usage(self, value: bool) -> Self

Enables or disables capturing usage in streaming mode.

pub fn with_capture_content(self, value: bool) -> Self

Enables or disables capturing concatenated content in streaming mode.

pub fn with_capture_reasoning_content(self, value: bool) -> Self

Enables or disables capturing concatenated reasoning content in streaming mode.

pub fn with_capture_tool_calls(self, value: bool) -> Self

Enables or disables capturing tool calls in streaming mode.

pub fn with_capture_raw_body(self, value: bool) -> Self

Enables or disables capturing the raw HTTP body.

pub fn with_stop_sequences(self, values: Vec<String>) -> Self

Sets the stop sequences.

pub fn with_normalize_reasoning_content(self, value: bool) -> Self

Enables or disables normalization of reasoning content (e.g., <think>...</think>).

pub fn with_response_format( self, res_format: impl Into<ChatResponseFormat>, ) -> Self

Sets the response format.

pub fn with_reasoning_effort(self, value: ReasoningEffort) -> Self

Sets the reasoning effort hint.

pub fn with_verbosity(self, value: Verbosity) -> Self

Sets the verbosity hint.

pub fn with_seed(self, value: u64) -> Self

Sets the deterministic seed.

pub fn with_service_tier(self, value: ServiceTier) -> Self

Sets the service tier preference (OpenAI-specific).

pub fn with_extra_headers(self, headers: impl Into<Headers>) -> Self

Adds extra HTTP headers.

pub fn with_json_mode(self, value: bool) -> Self

👎Deprecated: Use with_response_format(ChatResponseFormat::JsonMode)

Deprecated: use with_response_format(ChatResponseFormat::JsonMode).

When using JSON mode, you should still instruct the model to produce JSON in your prompt for broad provider compatibility (e.g., mention “json” in system/user messages).

Trait Implementations

impl Clone for ChatOptions

fn clone(&self) -> ChatOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatOptions

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

Formats the value using the given formatter.

impl Default for ChatOptions

fn default() -> ChatOptions

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatOptions

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChatOptions

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

where __S: Serializer,

Serialize this value into the given Serde serializer.