Enum InferenceProfile 

pub enum InferenceProfile {
    None,
    US,
    EU,
    APAC,
    Global,
}

Cross-region inference profile configuration for Bedrock

Inference profiles enable cross-region load balancing for higher throughput and improved reliability. When enabled, Bedrock automatically routes requests to the optimal region within the specified geographic scope.

Some newer models (Claude 4/4.5, Nova 2 Lite) require inference profiles and don’t support direct single-region invocation.

See: https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference.html

Variants

None

No inference profile - single-region invocation (default)

Requests go directly to the region configured in your AWS SDK. Use this for predictable routing and when data locality is important.

US

US regions only (us-east-1, us-east-2, us-west-2, etc.)

EU

European regions only (eu-central-1, eu-west-1, eu-west-2, etc.)

APAC

Asia-Pacific regions (ap-northeast-1, ap-southeast-1, etc.)

Global

Global cross-region inference (all commercial AWS regions)

Provides maximum throughput but may route to any region worldwide.

Implementations

impl InferenceProfile

pub fn apply_to(&self, base_model_id: &str) -> String

Apply this inference profile to a base model ID

Returns the full model ID to use with Bedrock API.

Trait Implementations

impl Clone for InferenceProfile

fn clone(&self) -> InferenceProfile

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for InferenceProfile

impl Debug for InferenceProfile

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

Formats the value using the given formatter.

impl Default for InferenceProfile

fn default() -> InferenceProfile

Returns the “default value” for a type.

impl Eq for InferenceProfile

impl PartialEq for InferenceProfile

fn eq(&self, other: &InferenceProfile) -> 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 StructuralPartialEq for InferenceProfile