CrossRegionTrafficConfig
The cross-Region traffic cap for an endpoint. The cap limits the requests per second
that the endpoint accepts from inference routers in other AWS Regions. The
cap is MaxCrossRegionPercentPerEndpoint percent of
MaxInvocationsPerSecondPerInstance multiplied by the number of
InService instances, rounded up. All production variants and inference
components of the endpoint share it. Requests that you send to the endpoint directly aren't
counted. A request over the cap fails with a ThrottlingException.
Contents
- MaxCrossRegionPercentPerEndpoint
-
The percentage of the endpoint's capacity that requests from inference routers in other AWS Regions can use.
Type: Integer
Valid Range: Minimum value of 1. Maximum value of 100.
Required: Yes
- MaxInvocationsPerSecondPerInstance
-
The number of invocations per second that you expect one
InServiceinstance to serve. One value applies to every production variant, whatever its instance type.Type: Integer
Valid Range: Minimum value of 1. Maximum value of 10000.
Required: Yes
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: