InferenceOperationConfiguration
The configuration for a specific inference operation, including its request path and the models that the operation supports.
Contents
- path
-
The request path for this operation (for example,
/v1/messagesor/v1/responses).Type: String
Length Constraints: Minimum length of 1. Maximum length of 256.
Pattern:
/[a-zA-Z0-9\-\._/]+Required: Yes
- models
-
The list of models supported for this operation.
Type: Array of ModelEntry objects
Array Members: Minimum number of 1 item. Maximum number of 100 items.
Required: No
- providerPath
-
The provider path to forward requests to, if it differs from the request path. For example,
/anthropic/v1/messageswhen the provider expects a different path than the client-facing/v1/messages.Type: String
Length Constraints: Minimum length of 1. Maximum length of 256.
Pattern:
/[a-zA-Z0-9\-\._/]+Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: