Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS
  3. API Docs
  4. sagemaker
  5. Endpoint
AWS v6.77.0 published on Wednesday, Apr 9, 2025 by Pulumi
pulumi/pulumi-aws

aws.sagemaker.Endpoint

Explore with Pulumi AI

AWS v6.77.0 published on Wednesday, Apr 9, 2025 by Pulumi
pulumi/pulumi-aws

Provides a SageMaker AI Endpoint resource.

Example Usage

Basic usage:

import * as pulumi from "@pulumi/pulumi";
import * as aws from "@pulumi/aws";

const e = new aws.sagemaker.Endpoint("e", {
    name: "my-endpoint",
    endpointConfigName: ec.name,
    tags: {
        Name: "foo",
    },
});
Copy
import pulumi
import pulumi_aws as aws

e = aws.sagemaker.Endpoint("e",
    name="my-endpoint",
    endpoint_config_name=ec["name"],
    tags={
        "Name": "foo",
    })
Copy
package main

import (
	"github.com/pulumi/pulumi-aws/sdk/v6/go/aws/sagemaker"
	"github.com/pulumi/pulumi/sdk/v3/go/pulumi"
)

func main() {
	pulumi.Run(func(ctx *pulumi.Context) error {
		_, err := sagemaker.NewEndpoint(ctx, "e", &sagemaker.EndpointArgs{
			Name:               pulumi.String("my-endpoint"),
			EndpointConfigName: pulumi.Any(ec.Name),
			Tags: pulumi.StringMap{
				"Name": pulumi.String("foo"),
			},
		})
		if err != nil {
			return err
		}
		return nil
	})
}
Copy
using System.Collections.Generic;
using System.Linq;
using Pulumi;
using Aws = Pulumi.Aws;

return await Deployment.RunAsync(() => 
{
    var e = new Aws.Sagemaker.Endpoint("e", new()
    {
        Name = "my-endpoint",
        EndpointConfigName = ec.Name,
        Tags = 
        {
            { "Name", "foo" },
        },
    });

});
Copy
package generated_program;

import com.pulumi.Context;
import com.pulumi.Pulumi;
import com.pulumi.core.Output;
import com.pulumi.aws.sagemaker.Endpoint;
import com.pulumi.aws.sagemaker.EndpointArgs;
import java.util.List;
import java.util.ArrayList;
import java.util.Map;
import java.io.File;
import java.nio.file.Files;
import java.nio.file.Paths;

public class App {
    public static void main(String[] args) {
        Pulumi.run(App::stack);
    }

    public static void stack(Context ctx) {
        var e = new Endpoint("e", EndpointArgs.builder()
            .name("my-endpoint")
            .endpointConfigName(ec.name())
            .tags(Map.of("Name", "foo"))
            .build());

    }
}
Copy
resources:
  e:
    type: aws:sagemaker:Endpoint
    properties:
      name: my-endpoint
      endpointConfigName: ${ec.name}
      tags:
        Name: foo
Copy

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,
             name: Optional[str] = None,
             tags: Optional[Mapping[str, str]] = 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: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.

Constructor example

The following reference example uses placeholder values for all input properties.

var exampleendpointResourceResourceFromSagemakerendpoint = new Aws.Sagemaker.Endpoint("exampleendpointResourceResourceFromSagemakerendpoint", new()
{
    EndpointConfigName = "string",
    DeploymentConfig = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigArgs
    {
        AutoRollbackConfiguration = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigAutoRollbackConfigurationArgs
        {
            Alarms = new[]
            {
                new Aws.Sagemaker.Inputs.EndpointDeploymentConfigAutoRollbackConfigurationAlarmArgs
                {
                    AlarmName = "string",
                },
            },
        },
        BlueGreenUpdatePolicy = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigBlueGreenUpdatePolicyArgs
        {
            TrafficRoutingConfiguration = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationArgs
            {
                Type = "string",
                WaitIntervalInSeconds = 0,
                CanarySize = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySizeArgs
                {
                    Type = "string",
                    Value = 0,
                },
                LinearStepSize = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSizeArgs
                {
                    Type = "string",
                    Value = 0,
                },
            },
            MaximumExecutionTimeoutInSeconds = 0,
            TerminationWaitInSeconds = 0,
        },
        RollingUpdatePolicy = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigRollingUpdatePolicyArgs
        {
            MaximumBatchSize = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs
            {
                Type = "string",
                Value = 0,
            },
            WaitIntervalInSeconds = 0,
            MaximumExecutionTimeoutInSeconds = 0,
            RollbackMaximumBatchSize = new Aws.Sagemaker.Inputs.EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs
            {
                Type = "string",
                Value = 0,
            },
        },
    },
    Name = "string",
    Tags = 
    {
        { "string", "string" },
    },
});
Copy
example, err := sagemaker.NewEndpoint(ctx, "exampleendpointResourceResourceFromSagemakerendpoint", &sagemaker.EndpointArgs{
	EndpointConfigName: pulumi.String("string"),
	DeploymentConfig: &sagemaker.EndpointDeploymentConfigArgs{
		AutoRollbackConfiguration: &sagemaker.EndpointDeploymentConfigAutoRollbackConfigurationArgs{
			Alarms: sagemaker.EndpointDeploymentConfigAutoRollbackConfigurationAlarmArray{
				&sagemaker.EndpointDeploymentConfigAutoRollbackConfigurationAlarmArgs{
					AlarmName: pulumi.String("string"),
				},
			},
		},
		BlueGreenUpdatePolicy: &sagemaker.EndpointDeploymentConfigBlueGreenUpdatePolicyArgs{
			TrafficRoutingConfiguration: &sagemaker.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationArgs{
				Type:                  pulumi.String("string"),
				WaitIntervalInSeconds: pulumi.Int(0),
				CanarySize: &sagemaker.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySizeArgs{
					Type:  pulumi.String("string"),
					Value: pulumi.Int(0),
				},
				LinearStepSize: &sagemaker.EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSizeArgs{
					Type:  pulumi.String("string"),
					Value: pulumi.Int(0),
				},
			},
			MaximumExecutionTimeoutInSeconds: pulumi.Int(0),
			TerminationWaitInSeconds:         pulumi.Int(0),
		},
		RollingUpdatePolicy: &sagemaker.EndpointDeploymentConfigRollingUpdatePolicyArgs{
			MaximumBatchSize: &sagemaker.EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs{
				Type:  pulumi.String("string"),
				Value: pulumi.Int(0),
			},
			WaitIntervalInSeconds:            pulumi.Int(0),
			MaximumExecutionTimeoutInSeconds: pulumi.Int(0),
			RollbackMaximumBatchSize: &sagemaker.EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs{
				Type:  pulumi.String("string"),
				Value: pulumi.Int(0),
			},
		},
	},
	Name: pulumi.String("string"),
	Tags: pulumi.StringMap{
		"string": pulumi.String("string"),
	},
})
Copy
var exampleendpointResourceResourceFromSagemakerendpoint = new Endpoint("exampleendpointResourceResourceFromSagemakerendpoint", EndpointArgs.builder()
    .endpointConfigName("string")
    .deploymentConfig(EndpointDeploymentConfigArgs.builder()
        .autoRollbackConfiguration(EndpointDeploymentConfigAutoRollbackConfigurationArgs.builder()
            .alarms(EndpointDeploymentConfigAutoRollbackConfigurationAlarmArgs.builder()
                .alarmName("string")
                .build())
            .build())
        .blueGreenUpdatePolicy(EndpointDeploymentConfigBlueGreenUpdatePolicyArgs.builder()
            .trafficRoutingConfiguration(EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationArgs.builder()
                .type("string")
                .waitIntervalInSeconds(0)
                .canarySize(EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySizeArgs.builder()
                    .type("string")
                    .value(0)
                    .build())
                .linearStepSize(EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSizeArgs.builder()
                    .type("string")
                    .value(0)
                    .build())
                .build())
            .maximumExecutionTimeoutInSeconds(0)
            .terminationWaitInSeconds(0)
            .build())
        .rollingUpdatePolicy(EndpointDeploymentConfigRollingUpdatePolicyArgs.builder()
            .maximumBatchSize(EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs.builder()
                .type("string")
                .value(0)
                .build())
            .waitIntervalInSeconds(0)
            .maximumExecutionTimeoutInSeconds(0)
            .rollbackMaximumBatchSize(EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs.builder()
                .type("string")
                .value(0)
                .build())
            .build())
        .build())
    .name("string")
    .tags(Map.of("string", "string"))
    .build());
Copy
exampleendpoint_resource_resource_from_sagemakerendpoint = aws.sagemaker.Endpoint("exampleendpointResourceResourceFromSagemakerendpoint",
    endpoint_config_name="string",
    deployment_config={
        "auto_rollback_configuration": {
            "alarms": [{
                "alarm_name": "string",
            }],
        },
        "blue_green_update_policy": {
            "traffic_routing_configuration": {
                "type": "string",
                "wait_interval_in_seconds": 0,
                "canary_size": {
                    "type": "string",
                    "value": 0,
                },
                "linear_step_size": {
                    "type": "string",
                    "value": 0,
                },
            },
            "maximum_execution_timeout_in_seconds": 0,
            "termination_wait_in_seconds": 0,
        },
        "rolling_update_policy": {
            "maximum_batch_size": {
                "type": "string",
                "value": 0,
            },
            "wait_interval_in_seconds": 0,
            "maximum_execution_timeout_in_seconds": 0,
            "rollback_maximum_batch_size": {
                "type": "string",
                "value": 0,
            },
        },
    },
    name="string",
    tags={
        "string": "string",
    })
Copy
const exampleendpointResourceResourceFromSagemakerendpoint = new aws.sagemaker.Endpoint("exampleendpointResourceResourceFromSagemakerendpoint", {
    endpointConfigName: "string",
    deploymentConfig: {
        autoRollbackConfiguration: {
            alarms: [{
                alarmName: "string",
            }],
        },
        blueGreenUpdatePolicy: {
            trafficRoutingConfiguration: {
                type: "string",
                waitIntervalInSeconds: 0,
                canarySize: {
                    type: "string",
                    value: 0,
                },
                linearStepSize: {
                    type: "string",
                    value: 0,
                },
            },
            maximumExecutionTimeoutInSeconds: 0,
            terminationWaitInSeconds: 0,
        },
        rollingUpdatePolicy: {
            maximumBatchSize: {
                type: "string",
                value: 0,
            },
            waitIntervalInSeconds: 0,
            maximumExecutionTimeoutInSeconds: 0,
            rollbackMaximumBatchSize: {
                type: "string",
                value: 0,
            },
        },
    },
    name: "string",
    tags: {
        string: "string",
    },
});
Copy
type: aws:sagemaker:Endpoint
properties:
    deploymentConfig:
        autoRollbackConfiguration:
            alarms:
                - alarmName: string
        blueGreenUpdatePolicy:
            maximumExecutionTimeoutInSeconds: 0
            terminationWaitInSeconds: 0
            trafficRoutingConfiguration:
                canarySize:
                    type: string
                    value: 0
                linearStepSize:
                    type: string
                    value: 0
                type: string
                waitIntervalInSeconds: 0
        rollingUpdatePolicy:
            maximumBatchSize:
                type: string
                value: 0
            maximumExecutionTimeoutInSeconds: 0
            rollbackMaximumBatchSize:
                type: string
                value: 0
            waitIntervalInSeconds: 0
    endpointConfigName: string
    name: string
    tags:
        string: string
Copy

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 to use.
DeploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
Name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
Tags Dictionary<string, string>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
EndpointConfigName This property is required. string
The name of the endpoint configuration to use.
DeploymentConfig EndpointDeploymentConfigArgs
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
Name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
Tags map[string]string
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
endpointConfigName This property is required. String
The name of the endpoint configuration to use.
deploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
name Changes to this property will trigger replacement. String
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Map<String,String>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
endpointConfigName This property is required. string
The name of the endpoint configuration to use.
deploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags {[key: string]: string}
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
endpoint_config_name This property is required. str
The name of the endpoint configuration to use.
deployment_config EndpointDeploymentConfigArgs
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
name Changes to this property will trigger replacement. str
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Mapping[str, str]
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
endpointConfigName This property is required. String
The name of the endpoint configuration to use.
deploymentConfig Property Map
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
name Changes to this property will trigger replacement. String
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Map<String>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.

Outputs

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

Arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
Id string
The provider-assigned unique ID for this managed resource.
TagsAll Dictionary<string, string>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
Id string
The provider-assigned unique ID for this managed resource.
TagsAll map[string]string
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn String
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
id String
The provider-assigned unique ID for this managed resource.
tagsAll Map<String,String>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
id string
The provider-assigned unique ID for this managed resource.
tagsAll {[key: string]: string}
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn str
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
id str
The provider-assigned unique ID for this managed resource.
tags_all Mapping[str, str]
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn String
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
id String
The provider-assigned unique ID for this managed resource.
tagsAll Map<String>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Look up Existing Endpoint Resource

Get an existing Endpoint resource’s state with the given name, ID, and optional extra properties used to qualify the lookup.

public static get(name: string, id: Input<ID>, state?: EndpointState, opts?: CustomResourceOptions): Endpoint
@staticmethod
def get(resource_name: str,
        id: str,
        opts: Optional[ResourceOptions] = None,
        arn: Optional[str] = None,
        deployment_config: Optional[EndpointDeploymentConfigArgs] = None,
        endpoint_config_name: Optional[str] = None,
        name: Optional[str] = None,
        tags: Optional[Mapping[str, str]] = None,
        tags_all: Optional[Mapping[str, str]] = None) -> Endpoint
func GetEndpoint(ctx *Context, name string, id IDInput, state *EndpointState, opts ...ResourceOption) (*Endpoint, error)
public static Endpoint Get(string name, Input<string> id, EndpointState? state, CustomResourceOptions? opts = null)
public static Endpoint get(String name, Output<String> id, EndpointState state, CustomResourceOptions options)
resources:  _:    type: aws:sagemaker:Endpoint    get:      id: ${id}
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
resource_name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
name This property is required.
The unique name of the resulting resource.
id This property is required.
The unique provider ID of the resource to lookup.
state
Any extra arguments used during the lookup.
opts
A bag of options that control this resource's behavior.
The following state arguments are supported:
Arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
DeploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
EndpointConfigName string
The name of the endpoint configuration to use.
Name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
Tags Dictionary<string, string>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll Dictionary<string, string>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
DeploymentConfig EndpointDeploymentConfigArgs
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
EndpointConfigName string
The name of the endpoint configuration to use.
Name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
Tags map[string]string
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
TagsAll map[string]string
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn String
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
deploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
endpointConfigName String
The name of the endpoint configuration to use.
name Changes to this property will trigger replacement. String
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Map<String,String>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String,String>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn string
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
deploymentConfig EndpointDeploymentConfig
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
endpointConfigName string
The name of the endpoint configuration to use.
name Changes to this property will trigger replacement. string
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags {[key: string]: string}
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll {[key: string]: string}
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn str
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
deployment_config EndpointDeploymentConfigArgs
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
endpoint_config_name str
The name of the endpoint configuration to use.
name Changes to this property will trigger replacement. str
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Mapping[str, str]
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tags_all Mapping[str, str]
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

arn String
The Amazon Resource Name (ARN) assigned by AWS to this endpoint.
deploymentConfig Property Map
The deployment configuration for an endpoint, which contains the desired deployment strategy and rollback configurations. See Deployment Config.
endpointConfigName String
The name of the endpoint configuration to use.
name Changes to this property will trigger replacement. String
The name of the endpoint. If omitted, the provider will assign a random, unique name.
tags Map<String>
A map of tags to assign to the resource. If configured with a provider default_tags configuration block present, tags with matching keys will overwrite those defined at the provider-level.
tagsAll Map<String>
A map of tags assigned to the resource, including those inherited from the provider default_tags configuration block.

Deprecated: Please use tags instead.

Supporting Types

EndpointDeploymentConfig
, EndpointDeploymentConfigArgs

AutoRollbackConfiguration Changes to this property will trigger replacement. EndpointDeploymentConfigAutoRollbackConfiguration
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
BlueGreenUpdatePolicy EndpointDeploymentConfigBlueGreenUpdatePolicy
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
RollingUpdatePolicy EndpointDeploymentConfigRollingUpdatePolicy
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.
AutoRollbackConfiguration Changes to this property will trigger replacement. EndpointDeploymentConfigAutoRollbackConfiguration
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
BlueGreenUpdatePolicy EndpointDeploymentConfigBlueGreenUpdatePolicy
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
RollingUpdatePolicy EndpointDeploymentConfigRollingUpdatePolicy
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.
autoRollbackConfiguration Changes to this property will trigger replacement. EndpointDeploymentConfigAutoRollbackConfiguration
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
blueGreenUpdatePolicy EndpointDeploymentConfigBlueGreenUpdatePolicy
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
rollingUpdatePolicy EndpointDeploymentConfigRollingUpdatePolicy
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.
autoRollbackConfiguration Changes to this property will trigger replacement. EndpointDeploymentConfigAutoRollbackConfiguration
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
blueGreenUpdatePolicy EndpointDeploymentConfigBlueGreenUpdatePolicy
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
rollingUpdatePolicy EndpointDeploymentConfigRollingUpdatePolicy
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.
auto_rollback_configuration Changes to this property will trigger replacement. EndpointDeploymentConfigAutoRollbackConfiguration
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
blue_green_update_policy EndpointDeploymentConfigBlueGreenUpdatePolicy
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
rolling_update_policy EndpointDeploymentConfigRollingUpdatePolicy
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.
autoRollbackConfiguration Changes to this property will trigger replacement. Property Map
Automatic rollback configuration for handling endpoint deployment failures and recovery. See Auto Rollback Configuration.
blueGreenUpdatePolicy Property Map
Update policy for a blue/green deployment. If this update policy is specified, SageMaker AI creates a new fleet during the deployment while maintaining the old fleet. SageMaker AI flips traffic to the new fleet according to the specified traffic routing configuration. Only one update policy should be used in the deployment configuration. If no update policy is specified, SageMaker AI uses a blue/green deployment strategy with all at once traffic shifting by default. See Blue Green Update Config.
rollingUpdatePolicy Property Map
Specifies a rolling deployment strategy for updating a SageMaker AI endpoint. See Rolling Update Policy.

EndpointDeploymentConfigAutoRollbackConfiguration
, EndpointDeploymentConfigAutoRollbackConfigurationArgs

Alarms List<EndpointDeploymentConfigAutoRollbackConfigurationAlarm>
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.
Alarms []EndpointDeploymentConfigAutoRollbackConfigurationAlarm
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.
alarms List<EndpointDeploymentConfigAutoRollbackConfigurationAlarm>
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.
alarms EndpointDeploymentConfigAutoRollbackConfigurationAlarm[]
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.
alarms Sequence[EndpointDeploymentConfigAutoRollbackConfigurationAlarm]
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.
alarms List<Property Map>
List of CloudWatch alarms in your account that are configured to monitor metrics on an endpoint. If any alarms are tripped during a deployment, SageMaker AI rolls back the deployment. See Alarms.

EndpointDeploymentConfigAutoRollbackConfigurationAlarm
, EndpointDeploymentConfigAutoRollbackConfigurationAlarmArgs

AlarmName This property is required. string
The name of a CloudWatch alarm in your account.
AlarmName This property is required. string
The name of a CloudWatch alarm in your account.
alarmName This property is required. String
The name of a CloudWatch alarm in your account.
alarmName This property is required. string
The name of a CloudWatch alarm in your account.
alarm_name This property is required. str
The name of a CloudWatch alarm in your account.
alarmName This property is required. String
The name of a CloudWatch alarm in your account.

EndpointDeploymentConfigBlueGreenUpdatePolicy
, EndpointDeploymentConfigBlueGreenUpdatePolicyArgs

TrafficRoutingConfiguration This property is required. EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
MaximumExecutionTimeoutInSeconds int
TerminationWaitInSeconds int
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.
TrafficRoutingConfiguration This property is required. EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
MaximumExecutionTimeoutInSeconds int
TerminationWaitInSeconds int
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.
trafficRoutingConfiguration This property is required. EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
maximumExecutionTimeoutInSeconds Integer
terminationWaitInSeconds Integer
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.
trafficRoutingConfiguration This property is required. EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
maximumExecutionTimeoutInSeconds number
terminationWaitInSeconds number
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.
traffic_routing_configuration This property is required. EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
maximum_execution_timeout_in_seconds int
termination_wait_in_seconds int
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.
trafficRoutingConfiguration This property is required. Property Map
Defines the traffic routing strategy to shift traffic from the old fleet to the new fleet during an endpoint deployment. See Traffic Routing Configuration.
maximumExecutionTimeoutInSeconds Number
terminationWaitInSeconds Number
Additional waiting time in seconds after the completion of an endpoint deployment before terminating the old endpoint fleet. Default is 0. Valid values are between 0 and 3600.

EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfiguration
, EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationArgs

Type This property is required. string
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
WaitIntervalInSeconds This property is required. int
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
CanarySize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
LinearStepSize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.
Type This property is required. string
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
WaitIntervalInSeconds This property is required. int
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
CanarySize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
LinearStepSize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.
type This property is required. String
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
waitIntervalInSeconds This property is required. Integer
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
canarySize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
linearStepSize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.
type This property is required. string
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
waitIntervalInSeconds This property is required. number
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
canarySize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
linearStepSize EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.
type This property is required. str
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
wait_interval_in_seconds This property is required. int
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
canary_size EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
linear_step_size EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.
type This property is required. String
Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
waitIntervalInSeconds This property is required. Number
The waiting time (in seconds) between incremental steps to turn on traffic on the new endpoint fleet. Valid values are between 0 and 3600.
canarySize Property Map
Batch size for the first step to turn on traffic on the new endpoint fleet. Value must be less than or equal to 50% of the variant's total instance count. See Canary Size.
linearStepSize Property Map
Batch size for each step to turn on traffic on the new endpoint fleet. Value must be 10-50% of the variant's total instance count. See Linear Step Size.

EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySize
, EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationCanarySizeArgs

Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Integer
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. number
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. str
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Number
Defines the capacity size, either as a number of instances or a capacity percentage.

EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize
, EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSizeArgs

Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Integer
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. number
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. str
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Number
Defines the capacity size, either as a number of instances or a capacity percentage.

EndpointDeploymentConfigRollingUpdatePolicy
, EndpointDeploymentConfigRollingUpdatePolicyArgs

MaximumBatchSize This property is required. EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
WaitIntervalInSeconds This property is required. int
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
MaximumExecutionTimeoutInSeconds int
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
RollbackMaximumBatchSize EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.
MaximumBatchSize This property is required. EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
WaitIntervalInSeconds This property is required. int
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
MaximumExecutionTimeoutInSeconds int
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
RollbackMaximumBatchSize EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.
maximumBatchSize This property is required. EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
waitIntervalInSeconds This property is required. Integer
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
maximumExecutionTimeoutInSeconds Integer
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
rollbackMaximumBatchSize EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.
maximumBatchSize This property is required. EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
waitIntervalInSeconds This property is required. number
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
maximumExecutionTimeoutInSeconds number
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
rollbackMaximumBatchSize EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.
maximum_batch_size This property is required. EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
wait_interval_in_seconds This property is required. int
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
maximum_execution_timeout_in_seconds int
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
rollback_maximum_batch_size EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.
maximumBatchSize This property is required. Property Map
Batch size for each rolling step to provision capacity and turn on traffic on the new endpoint fleet, and terminate capacity on the old endpoint fleet. Value must be between 5% to 50% of the variant's total instance count. See Maximum Batch Size.
waitIntervalInSeconds This property is required. Number
The length of the baking period, during which SageMaker AI monitors alarms for each batch on the new fleet. Valid values are between 0 and 3600.
maximumExecutionTimeoutInSeconds Number
The time limit for the total deployment. Exceeding this limit causes a timeout. Valid values are between 600 and 14400.
rollbackMaximumBatchSize Property Map
Batch size for rollback to the old endpoint fleet. Each rolling step to provision capacity and turn on traffic on the old endpoint fleet, and terminate capacity on the new endpoint fleet. If this field is absent, the default value will be set to 100% of total capacity which means to bring up the whole capacity of the old fleet at once during rollback. See Rollback Maximum Batch Size.

EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSize
, EndpointDeploymentConfigRollingUpdatePolicyMaximumBatchSizeArgs

Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Integer
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. number
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. str
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Number
Defines the capacity size, either as a number of instances or a capacity percentage.

EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize
, EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs

Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
Type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
Value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Integer
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. string
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. number
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. str
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. int
Defines the capacity size, either as a number of instances or a capacity percentage.
type This property is required. String
Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
value This property is required. Number
Defines the capacity size, either as a number of instances or a capacity percentage.

Import

Using pulumi import, import endpoints using the name. For example:

$ pulumi import aws:sagemaker/endpoint:Endpoint test_endpoint my-endpoint
Copy

To learn more about importing existing cloud resources, see Importing resources.

Package Details

Repository
AWS Classic pulumi/pulumi-aws
License
Apache-2.0
Notes
This Pulumi package is based on the aws Terraform Provider.
AWS v6.77.0 published on Wednesday, Apr 9, 2025 by Pulumi
pulumi/pulumi-aws