Enum ScalerType 

pub enum ScalerType {
    QueueDelay,
    RequestCount,
}

Scaling strategy for serverless endpoint worker management.

Determines how the serverless infrastructure responds to incoming request load by automatically scaling the number of active workers up or down.

Strategies

Queue Delay (QueueDelay)

Latency-optimized scaling that prioritizes response time consistency.

• Scales up when requests wait longer than the configured threshold
• Maintains responsive service with predictable latency characteristics
• Best for interactive applications, real-time inference, SLA-sensitive workloads
• Higher baseline costs to ensure responsiveness

Request Count (RequestCount)

Throughput-optimized scaling that balances load efficiently across workers.

• Maintains approximately queue_size / scaler_value workers
• Optimizes for cost efficiency and overall throughput
• Best for batch processing, background tasks, cost-sensitive workloads
• May have higher latency during traffic spikes

Examples

use runpod_sdk::model::ScalerType;

// For real-time AI inference requiring <3s response times
let latency_optimized = ScalerType::QueueDelay;
// scaler_value = 2 means scale up if any request waits >2 seconds

// For batch image processing where cost matters more than speed
let cost_optimized = ScalerType::RequestCount;
// scaler_value = 10 means maintain 1 worker per 10 queued requests

Variants

QueueDelay

Queue delay-based scaling - prioritizes response time consistency. Scales up when requests wait longer than the threshold.

RequestCount

Request count-based scaling - optimizes for throughput and cost. Maintains workers proportional to queue depth.

Trait Implementations

impl Clone for ScalerType

fn clone(&self) -> ScalerType

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScalerType

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

Formats the value using the given formatter.

impl Default for ScalerType

fn default() -> ScalerType

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ScalerType

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Display for ScalerType

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

Formats the value using the given formatter.

impl FromStr for ScalerType

type Err = ParseError

The associated error which can be returned from parsing.

fn from_str(s: &str) -> Result<ScalerType, <Self as FromStr>::Err>

Parses a string s to return a value of this type.

impl PartialEq for ScalerType

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ScalerType

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl TryFrom<&str> for ScalerType

type Error = ParseError

The type returned in the event of a conversion error.

fn try_from(s: &str) -> Result<ScalerType, <Self as TryFrom<&str>>::Error>

Performs the conversion.

impl Copy for ScalerType

impl Eq for ScalerType

impl StructuralPartialEq for ScalerType