This is the new Amazon CloudFormation Template Reference Guide. Please update your bookmarks and links. For help getting started with CloudFormation, see the Amazon CloudFormation User Guide.
AWS::BedrockAgentCore::GatewayTarget InferenceProviderTargetConfiguration
The configuration for a provider-based inference target. This configuration explicitly defines the endpoint, model mapping, and operations used to route requests to a large language model (LLM) provider.
Syntax
To declare this entity in your Amazon CloudFormation template, use the following syntax:
JSON
{ "Endpoint" :String, "ModelMapping" :ModelMapping, "Operations" :[ InferenceOperationConfiguration, ... ]}
YAML
Endpoint:StringModelMapping:ModelMappingOperations:- InferenceOperationConfiguration
Properties
Endpoint-
The HTTPS endpoint of the inference provider that the gateway forwards requests to.
Required: Yes
Type: String
Pattern:
^https://[a-zA-Z0-9\-\.]+(:[0-9]{1,5})?(/.*)?$Minimum:
1Maximum:
2048Update requires: No interruption
ModelMapping-
The configuration that translates client-facing model IDs to the model IDs expected by the provider.
Required: No
Type: ModelMapping
Update requires: No interruption
Operations-
A list of per-operation configurations that map request paths to the models supported for each operation.
Required: No
Type: Array of InferenceOperationConfiguration
Minimum:
1Maximum:
10Update requires: No interruption