Struct Parameters 

pub struct Parameters {

    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub top_k: Option<u32>,
    pub frequency_penalty: Option<f32>,
    pub presence_penalty: Option<f32>,
    pub repetition_penalty: Option<f32>,
    pub min_p: Option<f32>,
    pub seed: Option<u32>,
    pub max_tokens: Option<u32>,
    pub logit_bias: Option<Vec<(String, f32)>>,
    pub logprobs: Option<bool>,
    pub top_logprobs: Option<u8>,
    pub stop: Option<Vec<String>>,
    pub tool_choice: ToolChoice,
    pub parallel_tool_calls: Option<bool>,
    pub reasoning_effort: Option<ReasoningEffort>,
    pub include_reasoning: bool,
    pub structured_outputs: bool,
    pub response_format: Option<Schema>,
    pub websearch: bool,
    pub code_execution: bool,
    pub native_tools: NativeTools,
    pub cache: CacheOptions,
}

Parameters for configuring the behavior of a language model.

This struct contains various parameters that can be used to control how a language model generates responses. All parameters are optional and use the builder pattern for easy configuration.

Examples

use aither::llm::model::Parameters;

let params = Parameters::default()
    .temperature(0.7)
    .top_p(0.9)
    .max_tokens(1000)
    .seed(42);

Fields

temperature: Option<f32>

Sampling temperature.

Controls randomness in generation. Higher values (e.g., 1.0) make output more random, lower values (e.g., 0.1) make it more deterministic.

top_p: Option<f32>

Nucleus sampling probability.

Only consider tokens with cumulative probability up to this value. Typical values are between 0.9 and 1.0.

top_k: Option<u32>

Top-k sampling parameter.

Only consider the k most likely tokens at each step.

frequency_penalty: Option<f32>

Frequency penalty to reduce repetition.

Positive values penalize tokens that have already appeared.

presence_penalty: Option<f32>

Presence penalty to encourage new tokens.

Positive values encourage the model to talk about new topics.

repetition_penalty: Option<f32>

Repetition penalty to penalize repeated tokens.

Values > 1.0 discourage repetition, values < 1.0 encourage it.

Local inference only: this maps onto a llama.cpp sampler and none of the hosted provider APIs accept it, so setting it has no effect on them.

min_p: Option<f32>

Minimum probability for nucleus sampling.

Alternative to top_p that sets a minimum threshold for token probabilities.

Local inference only, like Self::repetition_penalty.

seed: Option<u32>

Random seed for reproducibility.

Use the same seed to get deterministic outputs.

max_tokens: Option<u32>

Maximum number of tokens to generate.

Limits the length of the generated response.

logit_bias: Option<Vec<(String, f32)>>

Biases for specific logits.

Each tuple contains a token string and its bias value.

logprobs: Option<bool>

Whether to return log probabilities.

When true, the model returns probability information for tokens.

top_logprobs: Option<u8>

Number of top log probabilities to return.

Only used when logprobs is true.

stop: Option<Vec<String>>

Stop sequences to end generation.

Generation stops when any of these strings are encountered.

tool_choice: ToolChoice

Tool choice policy for the model.

Controls whether tools are allowed, required, or constrained to a specific tool.

parallel_tool_calls: Option<bool>

Whether the model may request several tools in a single turn.

None leaves the decision to the provider’s own default. Set it only to override that default — forcing false serializes an agent loop that could otherwise fan its tool calls out concurrently.

reasoning_effort: Option<ReasoningEffort>

Preferred reasoning effort when supported.

include_reasoning: bool

Whether the provider should include reasoning summaries in the response stream.

structured_outputs: bool

Whether to enable structured outputs.

When true, the model will attempt to return outputs in a structured format (e.g., JSON).

response_format: Option<Schema>

The expected response format schema.

When set, the model will attempt to return outputs matching this schema.

websearch: bool

Whether to enable native Search tool for grounding.

code_execution: bool

Whether to enable native Code Execution tool.

native_tools: NativeTools

Provider-native tools that are not portable across API families.

cache: CacheOptions

Provider-specific prompt cache controls.

Implementations

impl Parameters

pub fn temperature(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn top_p(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

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

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn frequency_penalty(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn presence_penalty(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn repetition_penalty(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn min_p(self, value: f32) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

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

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

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

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn logit_bias(self, value: Vec<(String, f32)>) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

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

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn top_logprobs(self, value: u8) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

pub fn stop(self, value: Vec<String>) -> Self

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

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

Sets the parameter value using a builder pattern.

Arguments

• value - The value to set for this parameter

impl Parameters

pub const fn include_reasoning(self, include: bool) -> Self

Sets whether providers should include reasoning summaries.

pub const fn reasoning_effort(self, effort: ReasoningEffort) -> Self

Sets the preferred reasoning effort.

pub const fn websearch(self, enabled: bool) -> Self

Sets whether to enable native Google Search tool.

pub const fn code_execution(self, enabled: bool) -> Self

Sets whether to enable native Code Execution tool.

pub fn native_tools(self, tools: NativeTools) -> Self

Sets provider-native tools.

pub fn openai_tools(self, tools: OpenAINativeTools) -> Self

Sets OpenAI Responses-native tools.

pub const fn gemini_tools(self, tools: GeminiNativeTools) -> Self

Sets Gemini-native tools.

pub const fn claude_tools(self, tools: ClaudeNativeTools) -> Self

Sets Claude-native tools.

pub fn prompt_cache_key(self, key: impl Into<String>) -> Self

Sets the OpenAI-compatible prompt cache key.

pub fn prompt_cache_retention( self, retention: OpenAIPromptCacheRetention, ) -> Self

Sets the OpenAI-compatible prompt cache retention policy.

pub const fn claude_prompt_cache(self, cache: ClaudePromptCache) -> Self

Sets Claude prompt caching options.

pub const fn claude_prompt_cache_automatic( self, ttl: ClaudePromptCacheTtl, ) -> Self

Sets Claude prompt caching with automatic top-level cache control.

pub const fn claude_prompt_cache_explicit( self, ttl: ClaudePromptCacheTtl, breakpoints: ClaudeExplicitCacheBreakpoints, ) -> Self

Sets Claude prompt caching with explicit block-level cache breakpoints.

pub const fn claude_prompt_cache_automatic_with_explicit( self, ttl: ClaudePromptCacheTtl, breakpoints: ClaudeExplicitCacheBreakpoints, ) -> Self

Sets Claude prompt caching with automatic and explicit breakpoint modes combined.

pub fn gemini_cached_content(self, cached_content: impl Into<String>) -> Self

Sets the Gemini cached content resource name.

pub fn without_cache(self) -> Self

Clears all provider-specific cache options.

pub fn tool_choice(self, choice: ToolChoice) -> Self

Sets the tool choice policy.

Trait Implementations

impl Clone for Parameters

fn clone(&self) -> Parameters

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Parameters

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

Formats the value using the given formatter.

impl Default for Parameters

fn default() -> Parameters

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Parameters

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Parameters

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for Parameters

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 Parameters