Struct Model 

pub struct Model {

    pub billing: Option<ModelBilling>,
    pub capabilities: ModelCapabilities,
    pub default_reasoning_effort: Option<String>,
    pub id: String,
    pub info_messages: Option<Vec<ModelMessage>>,
    pub model_picker_category: Option<ModelPickerCategory>,
    pub model_picker_price_category: Option<ModelPickerPriceCategory>,
    pub name: String,
    pub policy: Option<ModelPolicy>,
    pub supported_context_tiers: Option<Vec<String>>,
    pub supported_reasoning_efforts: Option<Vec<String>>,
    pub warning_messages: Option<Vec<ModelMessage>>,
    pub warning_text: Option<ModelWarningText>,
}

Copilot model metadata, including identifier, display name, capabilities, policy, billing, reasoning efforts, and picker categories.

Experimental. This type is part of an experimental wire-protocol surface and may change or be removed in future SDK or CLI releases.

Fields

billing: Option<ModelBilling>

Billing information

capabilities: ModelCapabilities

Model capabilities and limits

default_reasoning_effort: Option<String>

Default reasoning effort level (only present if model supports reasoning effort)

id: String

Model identifier (e.g., “claude-sonnet-4.5”)

info_messages: Option<Vec<ModelMessage>>

Informational notices the service published for this model, such as an upcoming change or a recommended alternative. Present only when the service published at least one notice. Hosts should surface these without implying anything is wrong with the model.

model_picker_category: Option<ModelPickerCategory>

Model capability category for grouping in the model picker

model_picker_price_category: Option<ModelPickerPriceCategory>

Relative cost tier for token-based billing users

name: String

Display name

policy: Option<ModelPolicy>

Policy state (if applicable)

supported_context_tiers: Option<Vec<String>>

Context-window tiers this model offers, when the provider advertises them independently of tiered token pricing. Copilot models carry their tiers in billing.tokenPrices; a provider that has no pricing to publish (an agent host reached over AHP, for example) declares them here instead, so the model picker can still offer the tier toggle.

supported_reasoning_efforts: Option<Vec<String>>

Supported reasoning effort levels (only present if model supports reasoning effort)

warning_messages: Option<Vec<ModelMessage>>

Warnings the service published for this model, such as a deprecated client version. Present only when the service published at least one warning. The model remains usable; hosts should surface these as advisory rather than blocking.

warning_text: Option<ModelWarningText>

Warning text the service requires hosts to surface for this model. Present only when the service published at least one warning.

Trait Implementations

impl Clone for Model

fn clone(&self) -> Model

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Model

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

Formats the value using the given formatter.

impl Default for Model

fn default() -> Model

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Model

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Model

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

where __S: Serializer,

Serialize this value into the given Serde serializer.