Struct ModelLimits 

pub struct ModelLimits {
    pub context_window: u32,
    pub max_output_tokens: u32,
    pub max_thinking_budget: Option<u32>,
}

Fields

context_window: u32

max_output_tokens: u32

max_thinking_budget: Option<u32>

Maximum extended-thinking / reasoning budget (in tokens) the upstream accepts for this model. None means the provider validates the budget itself (Anthropic) or maps it to an effort bucket (OpenAI); set it for providers that reject an out-of-range numeric budget (Gemini: 24576 for flash, 32768 for pro). The gateway clamps the requested budget to this.

Trait Implementations

impl Clone for ModelLimits

fn clone(&self) -> ModelLimits

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelLimits

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

Formats the value using the given formatter.

impl Default for ModelLimits

fn default() -> ModelLimits

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelLimits

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for ModelLimits

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 Serialize for ModelLimits

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for ModelLimits