InferenceOperationConfiguration¶
Structure Class¶
dataclass
¶
The configuration for a specific inference operation, including its request path and the models that the operation supports.
Attributes¶
class-attribute
instance-attribute
¶
models: list[ModelEntry] | None = None
The list of models supported for this operation.
instance-attribute
¶
path: str
The request path for this operation (for example, /v1/messages or
/v1/responses).
class-attribute
instance-attribute
¶
provider_path: str | None = None
The provider path to forward requests to, if it differs from the request
path. For example, /anthropic/v1/messages when the provider expects a
different path than the client-facing /v1/messages.