deploy

TabularFoundationModel.deploy(instance_type: str | None = None, endpoint_name: str | None = None, hyperparameters: Dict[str, Any] | None = None, framework_version: str = 'latest', custom_image_uri: str | None = None, wait: bool = True, inference_mode: Literal['realtime'] = 'realtime', inference_config: Dict[str, Any] | None = None, **backend_kwargs) → TabularEndpoint

Deploy the tabular foundation model to an inference endpoint.

The returned endpoint accepts both labeled train_data and the rows to predict. It fits a request-scoped TabularPredictor before producing predictions.

Only real-time inference is supported. Tabular foundation models such as Mitra require a provisioned instance and cannot be deployed with SageMaker Serverless Inference.