Struct ModelPreferences 

#[non_exhaustive]
pub struct ModelPreferences {
    pub hints: Option<Vec<ModelHint>>,
    pub cost_priority: Option<f32>,
    pub speed_priority: Option<f32>,
    pub intelligence_priority: Option<f32>,
}

👎Deprecated since 2.0.0:

Sampling is deprecated by SEP-2577 and will be removed in a future release. See https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577

Preferences for model selection and behavior in sampling requests.

This allows servers to express their preferences for which model to use and how to balance different priorities when the client has multiple model options available.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

hints: Option<Vec<ModelHint>>

👎Deprecated since 2.0.0:

Sampling is deprecated by SEP-2577 and will be removed in a future release. See https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577

Specific model names or families to prefer (e.g., “claude”, “gpt”)

cost_priority: Option<f32>

👎Deprecated since 2.0.0:

Sampling is deprecated by SEP-2577 and will be removed in a future release. See https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577

Priority for cost optimization (0.0 to 1.0, higher = prefer cheaper models)

speed_priority: Option<f32>

👎Deprecated since 2.0.0:

Sampling is deprecated by SEP-2577 and will be removed in a future release. See https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577

Priority for speed/latency (0.0 to 1.0, higher = prefer faster models)

intelligence_priority: Option<f32>

👎Deprecated since 2.0.0:

Sampling is deprecated by SEP-2577 and will be removed in a future release. See https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577

Priority for intelligence/capability (0.0 to 1.0, higher = prefer more capable models)

Implementations

impl ModelPreferences

pub fn new() -> ModelPreferences

Create a new default ModelPreferences.

pub fn with_hints(self, hints: Vec<ModelHint>) -> ModelPreferences

Set hints for model selection.

pub fn with_cost_priority(self, cost_priority: f32) -> ModelPreferences

Set cost priority (0.0 to 1.0).

pub fn with_speed_priority(self, speed_priority: f32) -> ModelPreferences

Set speed priority (0.0 to 1.0).

pub fn with_intelligence_priority( self, intelligence_priority: f32, ) -> ModelPreferences

Set intelligence priority (0.0 to 1.0).

Trait Implementations

impl Clone for ModelPreferences

fn clone(&self) -> ModelPreferences

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelPreferences

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

Formats the value using the given formatter.

impl Default for ModelPreferences

fn default() -> ModelPreferences

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelPreferences

fn deserialize<__D>( __deserializer: __D, ) -> Result<ModelPreferences, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for ModelPreferences

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for ModelPreferences

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ModelPreferences

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelPreferences