Struct ModelEscalationConfig 

pub struct ModelEscalationConfig {
    pub escalation_model: String,
    pub escalation_threshold_seconds: i64,
}

Model-based escalation configuration for routing requests to a different model at claim time when approaching SLA deadline.

When a request is claimed with less than escalation_threshold_seconds remaining before batch expiry, it will be routed to the escalation_model instead of the original model. The batch API key automatically has access to escalation models in the onwards routing cache (no separate API key needed).

Fields

escalation_model: String

The model to escalate to (e.g., “o1-preview” for requests using “gpt-4”)

escalation_threshold_seconds: i64

Time threshold in seconds - escalate when time remaining before batch expiry is less than this value. Default: 900 (15 minutes)

Trait Implementations

impl Clone for ModelEscalationConfig

fn clone(&self) -> ModelEscalationConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelEscalationConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelEscalationConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ModelEscalationConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.