Docs Home Pulumi IaC Pulumi ESC Pulumi Insights Pulumi Cloud Packages Tutorials
  1. Packages
  2. AWS
  3. API Docs
  4. sagemaker
  5. Endpoint
AWS v6.74.0 published on Wednesday, Mar 26, 2025 by Pulumi
pulumi/pulumi-aws

aws.sagemaker.Endpoint

Explore with Pulumi AI

aws logo
AWS v6.74.0 published on Wednesday, Mar 26, 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",
    },
});

    import pulumi
import pulumi_aws as aws

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

    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
	})
}

    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" },
        },
    });

});

    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());

    }
}

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

    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 string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    resource_name str
    The unique name of the resource.
    args 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 string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts ResourceOption
    Bag of options to control resource's behavior.
    name string
    The unique name of the resource.
    args EndpointArgs
    The arguments to resource properties.
    opts CustomResourceOptions
    Bag of options to control resource's behavior.
    name String
    The unique name of the resource.
    args 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" },
    },
});

    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"),
	},
})

    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());

    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",
    })

    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",
    },
});

    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

    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 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 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 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 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 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 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 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 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 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 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 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 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
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    The unique provider ID of the resource to lookup.
    name
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    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
    The unique name of the resulting resource.
    id
    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 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 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 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 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 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 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 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 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 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 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 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 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 string
    The name of a CloudWatch alarm in your account.
    AlarmName string
    The name of a CloudWatch alarm in your account.
    alarmName String
    The name of a CloudWatch alarm in your account.
    alarmName string
    The name of a CloudWatch alarm in your account.
    alarm_name str
    The name of a CloudWatch alarm in your account.
    alarmName String
    The name of a CloudWatch alarm in your account.

    EndpointDeploymentConfigBlueGreenUpdatePolicy, EndpointDeploymentConfigBlueGreenUpdatePolicyArgs

    TrafficRoutingConfiguration 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 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 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 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 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 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 string
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    WaitIntervalInSeconds 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 string
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    WaitIntervalInSeconds 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 String
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    waitIntervalInSeconds 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 string
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    waitIntervalInSeconds 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 str
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    wait_interval_in_seconds 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 String
    Traffic routing strategy type. Valid values are: ALL_AT_ONCE, CANARY, and LINEAR.
    waitIntervalInSeconds 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 string
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    Value int
    Defines the capacity size, either as a number of instances or a capacity percentage.
    Type string
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    Value int
    Defines the capacity size, either as a number of instances or a capacity percentage.
    type String
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    value Integer
    Defines the capacity size, either as a number of instances or a capacity percentage.
    type string
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    value number
    Defines the capacity size, either as a number of instances or a capacity percentage.
    type str
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    value int
    Defines the capacity size, either as a number of instances or a capacity percentage.
    type String
    Specifies the endpoint capacity type. Valid values are: INSTANCE_COUNT, or CAPACITY_PERCENT.
    value Number
    Defines the capacity size, either as a number of instances or a capacity percentage.

    EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSize, EndpointDeploymentConfigBlueGreenUpdatePolicyTrafficRoutingConfigurationLinearStepSizeArgs

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

    EndpointDeploymentConfigRollingUpdatePolicy, EndpointDeploymentConfigRollingUpdatePolicyArgs

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

    EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSize, EndpointDeploymentConfigRollingUpdatePolicyRollbackMaximumBatchSizeArgs

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

    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 logo
    AWS v6.74.0 published on Wednesday, Mar 26, 2025 by Pulumi
    pulumi/pulumi-aws