1. Packages
  2. AWS Cloud Control
  3. API Docs
  4. sagemaker
  5. Endpoint

We recommend new projects start with resources from the AWS provider.

AWS Cloud Control v1.27.0 published on Monday, Apr 14, 2025 by Pulumi

aws-native.sagemaker.Endpoint

Explore with Pulumi AI

We recommend new projects start with resources from the AWS provider.

AWS Cloud Control v1.27.0 published on Monday, Apr 14, 2025 by Pulumi

Resource Type definition for AWS::SageMaker::Endpoint

Create Endpoint Resource

Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.

Constructor syntax

new Endpoint(name: string, args: EndpointArgs, opts?: CustomResourceOptions);
@overload
def Endpoint(resource_name: str,
             args: EndpointArgs,
             opts: Optional[ResourceOptions] = None)

@overload
def Endpoint(resource_name: str,
             opts: Optional[ResourceOptions] = None,
             endpoint_config_name: Optional[str] = None,
             deployment_config: Optional[EndpointDeploymentConfigArgs] = None,
             endpoint_name: Optional[str] = None,
             exclude_retained_variant_properties: Optional[Sequence[EndpointVariantPropertyArgs]] = None,
             retain_all_variant_properties: Optional[bool] = None,
             retain_deployment_config: Optional[bool] = None,
             tags: Optional[Sequence[_root_inputs.TagArgs]] = None)
func NewEndpoint(ctx *Context, name string, args EndpointArgs, opts ...ResourceOption) (*Endpoint, error)
public Endpoint(string name, EndpointArgs args, CustomResourceOptions? opts = null)
public Endpoint(String name, EndpointArgs args)
public Endpoint(String name, EndpointArgs args, CustomResourceOptions options)
type: aws-native:sagemaker:Endpoint
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

Parameters

name This property is required. string
The unique name of the resource.
args This property is required. EndpointArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
resource_name This property is required. str
The unique name of the resource.
args This property is required. EndpointArgs
The arguments to resource properties.
opts ResourceOptions
Bag of options to control resource's behavior.
ctx Context
Context object for the current deployment.
name This property is required. string
The unique name of the resource.
args This property is required. EndpointArgs
The arguments to resource properties.
opts ResourceOption
Bag of options to control resource's behavior.
name This property is required. string
The unique name of the resource.
args This property is required. EndpointArgs
The arguments to resource properties.
opts CustomResourceOptions
Bag of options to control resource's behavior.
name This property is required. String
The unique name of the resource.
args This property is required. EndpointArgs
The arguments to resource properties.
options CustomResourceOptions
Bag of options to control resource's behavior.

Endpoint Resource Properties

To learn more about resource properties and how to use them, see Inputs and Outputs in the Architecture and Concepts docs.

Inputs

In Python, inputs that are objects can be passed either as argument classes or as dictionary literals.

The Endpoint resource accepts the following input properties:

EndpointConfigName This property is required. string
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
DeploymentConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointDeploymentConfig
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
EndpointName string
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
ExcludeRetainedVariantProperties List<Pulumi.AwsNative.SageMaker.Inputs.EndpointVariantProperty>
Specifies a list of variant properties that you want to exclude when updating an endpoint.
RetainAllVariantProperties bool
When set to true, retains all variant properties for an endpoint when it is updated.
RetainDeploymentConfig bool
When set to true, retains the deployment configuration during endpoint updates.
Tags List<Pulumi.AwsNative.Inputs.Tag>
An array of key-value pairs to apply to this resource.
EndpointConfigName This property is required. string
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
DeploymentConfig EndpointDeploymentConfigArgs
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
EndpointName string
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
ExcludeRetainedVariantProperties []EndpointVariantPropertyArgs
Specifies a list of variant properties that you want to exclude when updating an endpoint.
RetainAllVariantProperties bool
When set to true, retains all variant properties for an endpoint when it is updated.
RetainDeploymentConfig bool
When set to true, retains the deployment configuration during endpoint updates.
Tags TagArgs
An array of key-value pairs to apply to this resource.
endpointConfigName This property is required. String
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
deploymentConfig EndpointDeploymentConfig
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
endpointName String
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
excludeRetainedVariantProperties List<EndpointVariantProperty>
Specifies a list of variant properties that you want to exclude when updating an endpoint.
retainAllVariantProperties Boolean
When set to true, retains all variant properties for an endpoint when it is updated.
retainDeploymentConfig Boolean
When set to true, retains the deployment configuration during endpoint updates.
tags List<Tag>
An array of key-value pairs to apply to this resource.
endpointConfigName This property is required. string
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
deploymentConfig EndpointDeploymentConfig
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
endpointName string
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
excludeRetainedVariantProperties EndpointVariantProperty[]
Specifies a list of variant properties that you want to exclude when updating an endpoint.
retainAllVariantProperties boolean
When set to true, retains all variant properties for an endpoint when it is updated.
retainDeploymentConfig boolean
When set to true, retains the deployment configuration during endpoint updates.
tags Tag[]
An array of key-value pairs to apply to this resource.
endpoint_config_name This property is required. str
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
deployment_config EndpointDeploymentConfigArgs
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
endpoint_name str
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
exclude_retained_variant_properties Sequence[EndpointVariantPropertyArgs]
Specifies a list of variant properties that you want to exclude when updating an endpoint.
retain_all_variant_properties bool
When set to true, retains all variant properties for an endpoint when it is updated.
retain_deployment_config bool
When set to true, retains the deployment configuration during endpoint updates.
tags Sequence[TagArgs]
An array of key-value pairs to apply to this resource.
endpointConfigName This property is required. String
The name of the endpoint configuration for the SageMaker endpoint. This is a required property.
deploymentConfig Property Map
Specifies deployment configuration for updating the SageMaker endpoint. Includes rollback and update policies.
endpointName String
The name of the SageMaker endpoint. This name must be unique within an AWS Region.
excludeRetainedVariantProperties List<Property Map>
Specifies a list of variant properties that you want to exclude when updating an endpoint.
retainAllVariantProperties Boolean
When set to true, retains all variant properties for an endpoint when it is updated.
retainDeploymentConfig Boolean
When set to true, retains the deployment configuration during endpoint updates.
tags List<Property Map>
An array of key-value pairs to apply to this resource.

Outputs

All input properties are implicitly available as output properties. Additionally, the Endpoint resource produces the following output properties:

EndpointArn string
The Amazon Resource Name (ARN) of the endpoint.
Id string
The provider-assigned unique ID for this managed resource.
EndpointArn string
The Amazon Resource Name (ARN) of the endpoint.
Id string
The provider-assigned unique ID for this managed resource.
endpointArn String
The Amazon Resource Name (ARN) of the endpoint.
id String
The provider-assigned unique ID for this managed resource.
endpointArn string
The Amazon Resource Name (ARN) of the endpoint.
id string
The provider-assigned unique ID for this managed resource.
endpoint_arn str
The Amazon Resource Name (ARN) of the endpoint.
id str
The provider-assigned unique ID for this managed resource.
endpointArn String
The Amazon Resource Name (ARN) of the endpoint.
id String
The provider-assigned unique ID for this managed resource.

Supporting Types

EndpointAlarm
, EndpointAlarmArgs

AlarmName This property is required. string
The name of the CloudWatch alarm.
AlarmName This property is required. string
The name of the CloudWatch alarm.
alarmName This property is required. String
The name of the CloudWatch alarm.
alarmName This property is required. string
The name of the CloudWatch alarm.
alarm_name This property is required. str
The name of the CloudWatch alarm.
alarmName This property is required. String
The name of the CloudWatch alarm.

EndpointAutoRollbackConfig
, EndpointAutoRollbackConfigArgs

Alarms This property is required. List<Pulumi.AwsNative.SageMaker.Inputs.EndpointAlarm>
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.
Alarms This property is required. []EndpointAlarm
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.
alarms This property is required. List<EndpointAlarm>
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.
alarms This property is required. EndpointAlarm[]
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.
alarms This property is required. Sequence[EndpointAlarm]
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.
alarms This property is required. List<Property Map>
List of CloudWatch alarms to monitor during the deployment. If any alarm goes off, the deployment is rolled back.

EndpointBlueGreenUpdatePolicy
, EndpointBlueGreenUpdatePolicyArgs

TrafficRoutingConfiguration This property is required. Pulumi.AwsNative.SageMaker.Inputs.EndpointTrafficRoutingConfig
The traffic routing configuration for the blue/green deployment.
MaximumExecutionTimeoutInSeconds int
The maximum time allowed for the blue/green update, in seconds.
TerminationWaitInSeconds int
The wait time before terminating the old endpoint during a blue/green deployment.
TrafficRoutingConfiguration This property is required. EndpointTrafficRoutingConfig
The traffic routing configuration for the blue/green deployment.
MaximumExecutionTimeoutInSeconds int
The maximum time allowed for the blue/green update, in seconds.
TerminationWaitInSeconds int
The wait time before terminating the old endpoint during a blue/green deployment.
trafficRoutingConfiguration This property is required. EndpointTrafficRoutingConfig
The traffic routing configuration for the blue/green deployment.
maximumExecutionTimeoutInSeconds Integer
The maximum time allowed for the blue/green update, in seconds.
terminationWaitInSeconds Integer
The wait time before terminating the old endpoint during a blue/green deployment.
trafficRoutingConfiguration This property is required. EndpointTrafficRoutingConfig
The traffic routing configuration for the blue/green deployment.
maximumExecutionTimeoutInSeconds number
The maximum time allowed for the blue/green update, in seconds.
terminationWaitInSeconds number
The wait time before terminating the old endpoint during a blue/green deployment.
traffic_routing_configuration This property is required. EndpointTrafficRoutingConfig
The traffic routing configuration for the blue/green deployment.
maximum_execution_timeout_in_seconds int
The maximum time allowed for the blue/green update, in seconds.
termination_wait_in_seconds int
The wait time before terminating the old endpoint during a blue/green deployment.
trafficRoutingConfiguration This property is required. Property Map
The traffic routing configuration for the blue/green deployment.
maximumExecutionTimeoutInSeconds Number
The maximum time allowed for the blue/green update, in seconds.
terminationWaitInSeconds Number
The wait time before terminating the old endpoint during a blue/green deployment.

EndpointCapacitySize
, EndpointCapacitySizeArgs

Type This property is required. string
Specifies whether the Value is an instance count or a capacity unit.
Value This property is required. int
The value representing either the number of instances or the number of capacity units.
Type This property is required. string
Specifies whether the Value is an instance count or a capacity unit.
Value This property is required. int
The value representing either the number of instances or the number of capacity units.
type This property is required. String
Specifies whether the Value is an instance count or a capacity unit.
value This property is required. Integer
The value representing either the number of instances or the number of capacity units.
type This property is required. string
Specifies whether the Value is an instance count or a capacity unit.
value This property is required. number
The value representing either the number of instances or the number of capacity units.
type This property is required. str
Specifies whether the Value is an instance count or a capacity unit.
value This property is required. int
The value representing either the number of instances or the number of capacity units.
type This property is required. String
Specifies whether the Value is an instance count or a capacity unit.
value This property is required. Number
The value representing either the number of instances or the number of capacity units.

EndpointDeploymentConfig
, EndpointDeploymentConfigArgs

AutoRollbackConfiguration Pulumi.AwsNative.SageMaker.Inputs.EndpointAutoRollbackConfig
Configuration for automatic rollback if an error occurs during deployment.
BlueGreenUpdatePolicy Pulumi.AwsNative.SageMaker.Inputs.EndpointBlueGreenUpdatePolicy
Configuration for blue-green update deployment policies.
RollingUpdatePolicy Pulumi.AwsNative.SageMaker.Inputs.EndpointRollingUpdatePolicy
Configuration for rolling update deployment policies.
AutoRollbackConfiguration EndpointAutoRollbackConfig
Configuration for automatic rollback if an error occurs during deployment.
BlueGreenUpdatePolicy EndpointBlueGreenUpdatePolicy
Configuration for blue-green update deployment policies.
RollingUpdatePolicy EndpointRollingUpdatePolicy
Configuration for rolling update deployment policies.
autoRollbackConfiguration EndpointAutoRollbackConfig
Configuration for automatic rollback if an error occurs during deployment.
blueGreenUpdatePolicy EndpointBlueGreenUpdatePolicy
Configuration for blue-green update deployment policies.
rollingUpdatePolicy EndpointRollingUpdatePolicy
Configuration for rolling update deployment policies.
autoRollbackConfiguration EndpointAutoRollbackConfig
Configuration for automatic rollback if an error occurs during deployment.
blueGreenUpdatePolicy EndpointBlueGreenUpdatePolicy
Configuration for blue-green update deployment policies.
rollingUpdatePolicy EndpointRollingUpdatePolicy
Configuration for rolling update deployment policies.
auto_rollback_configuration EndpointAutoRollbackConfig
Configuration for automatic rollback if an error occurs during deployment.
blue_green_update_policy EndpointBlueGreenUpdatePolicy
Configuration for blue-green update deployment policies.
rolling_update_policy EndpointRollingUpdatePolicy
Configuration for rolling update deployment policies.
autoRollbackConfiguration Property Map
Configuration for automatic rollback if an error occurs during deployment.
blueGreenUpdatePolicy Property Map
Configuration for blue-green update deployment policies.
rollingUpdatePolicy Property Map
Configuration for rolling update deployment policies.

EndpointRollingUpdatePolicy
, EndpointRollingUpdatePolicyArgs

MaximumBatchSize This property is required. Pulumi.AwsNative.SageMaker.Inputs.EndpointCapacitySize
Specifies the maximum batch size for each rolling update.
WaitIntervalInSeconds This property is required. int
The time to wait between steps during the rolling update, in seconds.
MaximumExecutionTimeoutInSeconds int
The maximum time allowed for the rolling update, in seconds.
RollbackMaximumBatchSize Pulumi.AwsNative.SageMaker.Inputs.EndpointCapacitySize
The maximum batch size for rollback during an update failure.
MaximumBatchSize This property is required. EndpointCapacitySize
Specifies the maximum batch size for each rolling update.
WaitIntervalInSeconds This property is required. int
The time to wait between steps during the rolling update, in seconds.
MaximumExecutionTimeoutInSeconds int
The maximum time allowed for the rolling update, in seconds.
RollbackMaximumBatchSize EndpointCapacitySize
The maximum batch size for rollback during an update failure.
maximumBatchSize This property is required. EndpointCapacitySize
Specifies the maximum batch size for each rolling update.
waitIntervalInSeconds This property is required. Integer
The time to wait between steps during the rolling update, in seconds.
maximumExecutionTimeoutInSeconds Integer
The maximum time allowed for the rolling update, in seconds.
rollbackMaximumBatchSize EndpointCapacitySize
The maximum batch size for rollback during an update failure.
maximumBatchSize This property is required. EndpointCapacitySize
Specifies the maximum batch size for each rolling update.
waitIntervalInSeconds This property is required. number
The time to wait between steps during the rolling update, in seconds.
maximumExecutionTimeoutInSeconds number
The maximum time allowed for the rolling update, in seconds.
rollbackMaximumBatchSize EndpointCapacitySize
The maximum batch size for rollback during an update failure.
maximum_batch_size This property is required. EndpointCapacitySize
Specifies the maximum batch size for each rolling update.
wait_interval_in_seconds This property is required. int
The time to wait between steps during the rolling update, in seconds.
maximum_execution_timeout_in_seconds int
The maximum time allowed for the rolling update, in seconds.
rollback_maximum_batch_size EndpointCapacitySize
The maximum batch size for rollback during an update failure.
maximumBatchSize This property is required. Property Map
Specifies the maximum batch size for each rolling update.
waitIntervalInSeconds This property is required. Number
The time to wait between steps during the rolling update, in seconds.
maximumExecutionTimeoutInSeconds Number
The maximum time allowed for the rolling update, in seconds.
rollbackMaximumBatchSize Property Map
The maximum batch size for rollback during an update failure.

EndpointTrafficRoutingConfig
, EndpointTrafficRoutingConfigArgs

Type This property is required. string
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
CanarySize Pulumi.AwsNative.SageMaker.Inputs.EndpointCapacitySize
Specifies the size of the canary traffic in a canary deployment.
LinearStepSize Pulumi.AwsNative.SageMaker.Inputs.EndpointCapacitySize
Specifies the step size for linear traffic routing.
WaitIntervalInSeconds int
Specifies the wait interval between traffic shifts, in seconds.
Type This property is required. string
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
CanarySize EndpointCapacitySize
Specifies the size of the canary traffic in a canary deployment.
LinearStepSize EndpointCapacitySize
Specifies the step size for linear traffic routing.
WaitIntervalInSeconds int
Specifies the wait interval between traffic shifts, in seconds.
type This property is required. String
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
canarySize EndpointCapacitySize
Specifies the size of the canary traffic in a canary deployment.
linearStepSize EndpointCapacitySize
Specifies the step size for linear traffic routing.
waitIntervalInSeconds Integer
Specifies the wait interval between traffic shifts, in seconds.
type This property is required. string
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
canarySize EndpointCapacitySize
Specifies the size of the canary traffic in a canary deployment.
linearStepSize EndpointCapacitySize
Specifies the step size for linear traffic routing.
waitIntervalInSeconds number
Specifies the wait interval between traffic shifts, in seconds.
type This property is required. str
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
canary_size EndpointCapacitySize
Specifies the size of the canary traffic in a canary deployment.
linear_step_size EndpointCapacitySize
Specifies the step size for linear traffic routing.
wait_interval_in_seconds int
Specifies the wait interval between traffic shifts, in seconds.
type This property is required. String
Specifies the type of traffic routing (e.g., 'AllAtOnce', 'Canary', 'Linear').
canarySize Property Map
Specifies the size of the canary traffic in a canary deployment.
linearStepSize Property Map
Specifies the step size for linear traffic routing.
waitIntervalInSeconds Number
Specifies the wait interval between traffic shifts, in seconds.

EndpointVariantProperty
, EndpointVariantPropertyArgs

VariantPropertyType string
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').
VariantPropertyType string
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').
variantPropertyType String
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').
variantPropertyType string
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').
variant_property_type str
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').
variantPropertyType String
The type of variant property (e.g., 'DesiredInstanceCount', 'DesiredWeight', 'DataCaptureConfig').

Tag
, TagArgs

Key This property is required. string
The key name of the tag
Value This property is required. string
The value of the tag
Key This property is required. string
The key name of the tag
Value This property is required. string
The value of the tag
key This property is required. String
The key name of the tag
value This property is required. String
The value of the tag
key This property is required. string
The key name of the tag
value This property is required. string
The value of the tag
key This property is required. str
The key name of the tag
value This property is required. str
The value of the tag
key This property is required. String
The key name of the tag
value This property is required. String
The value of the tag

Package Details

Repository
AWS Native pulumi/pulumi-aws-native
License
Apache-2.0

We recommend new projects start with resources from the AWS provider.

AWS Cloud Control v1.27.0 published on Monday, Apr 14, 2025 by Pulumi