aws-native.sagemaker.EndpointConfig

AWS Cloud Control v1.81.0, Sep 28 26

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

Viewing docs for AWS Cloud Control v1.81.0
published on Monday, Sep 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-aws-native

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

Viewing docs for AWS Cloud Control v1.81.0
published on Monday, Sep 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-aws-native

Create EndpointConfig Resource

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

Constructor syntax

new EndpointConfig(name: string, args: EndpointConfigArgs, opts?: CustomResourceOptions);

@overload
def EndpointConfig(resource_name: str,
                   args: EndpointConfigArgs,
                   opts: Optional[ResourceOptions] = None)

@overload
def EndpointConfig(resource_name: str,
                   opts: Optional[ResourceOptions] = None,
                   production_variants: Optional[Sequence[EndpointConfigProductionVariantArgs]] = None,
                   async_inference_config: Optional[EndpointConfigAsyncInferenceConfigArgs] = None,
                   data_capture_config: Optional[EndpointConfigDataCaptureConfigArgs] = None,
                   enable_network_isolation: Optional[bool] = None,
                   endpoint_config_name: Optional[str] = None,
                   execution_role_arn: Optional[str] = None,
                   explainer_config: Optional[EndpointConfigExplainerConfigArgs] = None,
                   kms_key_id: Optional[str] = None,
                   metrics_config: Optional[EndpointConfigMetricsConfigArgs] = None,
                   shadow_production_variants: Optional[Sequence[EndpointConfigProductionVariantArgs]] = None,
                   tags: Optional[Sequence[_root_inputs.TagArgs]] = None,
                   vpc_config: Optional[EndpointConfigVpcConfigArgs] = None)

func NewEndpointConfig(ctx *Context, name string, args EndpointConfigArgs, opts ...ResourceOption) (*EndpointConfig, error)

public EndpointConfig(string name, EndpointConfigArgs args, CustomResourceOptions? opts = null)

public EndpointConfig(String name, EndpointConfigArgs args)
public EndpointConfig(String name, EndpointConfigArgs args, CustomResourceOptions options)

type: aws-native:sagemaker:EndpointConfig
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.

resource "aws-native_sagemaker_endpoint_config" "name" {
    # resource properties
}

Parameters

name string: The unique name of the resource.
args EndpointConfigArgs: 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 EndpointConfigArgs: 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 EndpointConfigArgs: The arguments to resource properties.
opts ResourceOption: Bag of options to control resource's behavior.

name string: The unique name of the resource.
args EndpointConfigArgs: The arguments to resource properties.
opts CustomResourceOptions: Bag of options to control resource's behavior.

name String: The unique name of the resource.
args EndpointConfigArgs: The arguments to resource properties.
options CustomResourceOptions: Bag of options to control resource's behavior.

EndpointConfig 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 EndpointConfig resource accepts the following input properties:

ProductionVariants List<Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigProductionVariant>: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
AsyncInferenceConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigAsyncInferenceConfig: Specifies configuration for how an endpoint performs asynchronous inference.
DataCaptureConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigDataCaptureConfig: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
EnableNetworkIsolation bool: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
EndpointConfigName string: The name of the endpoint configuration.
ExecutionRoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
ExplainerConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigExplainerConfig: A parameter to activate explainers.
KmsKeyId string: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
MetricsConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigMetricsConfig: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
ShadowProductionVariants List<Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigProductionVariant>: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
Tags List<Pulumi.AwsNative.Inputs.Tag>: A list of key-value pairs to apply to this resource.
VpcConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigVpcConfig: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

ProductionVariants []EndpointConfigProductionVariantArgs: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
AsyncInferenceConfig EndpointConfigAsyncInferenceConfigArgs: Specifies configuration for how an endpoint performs asynchronous inference.
DataCaptureConfig EndpointConfigDataCaptureConfigArgs: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
EnableNetworkIsolation bool: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
EndpointConfigName string: The name of the endpoint configuration.
ExecutionRoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
ExplainerConfig EndpointConfigExplainerConfigArgs: A parameter to activate explainers.
KmsKeyId string: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
MetricsConfig EndpointConfigMetricsConfigArgs: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
ShadowProductionVariants []EndpointConfigProductionVariantArgs: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
Tags TagArgs: A list of key-value pairs to apply to this resource.
VpcConfig EndpointConfigVpcConfigArgs: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

production_variants list(object): A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
async_inference_config object: Specifies configuration for how an endpoint performs asynchronous inference.
data_capture_config object: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
enable_network_isolation bool: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
endpoint_config_name string: The name of the endpoint configuration.
execution_role_arn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
explainer_config object: A parameter to activate explainers.
kms_key_id string: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
metrics_config object: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
shadow_production_variants list(object): Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
tags list(object): A list of key-value pairs to apply to this resource.
vpc_config object: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

productionVariants List<EndpointConfigProductionVariant>: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
asyncInferenceConfig EndpointConfigAsyncInferenceConfig: Specifies configuration for how an endpoint performs asynchronous inference.
dataCaptureConfig EndpointConfigDataCaptureConfig: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
enableNetworkIsolation Boolean: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
endpointConfigName String: The name of the endpoint configuration.
executionRoleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
explainerConfig EndpointConfigExplainerConfig: A parameter to activate explainers.
kmsKeyId String: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
metricsConfig EndpointConfigMetricsConfig: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
shadowProductionVariants List<EndpointConfigProductionVariant>: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
tags List<Tag>: A list of key-value pairs to apply to this resource.
vpcConfig EndpointConfigVpcConfig: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

productionVariants EndpointConfigProductionVariant[]: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
asyncInferenceConfig EndpointConfigAsyncInferenceConfig: Specifies configuration for how an endpoint performs asynchronous inference.
dataCaptureConfig EndpointConfigDataCaptureConfig: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
enableNetworkIsolation boolean: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
endpointConfigName string: The name of the endpoint configuration.
executionRoleArn string: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
explainerConfig EndpointConfigExplainerConfig: A parameter to activate explainers.
kmsKeyId string: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
metricsConfig EndpointConfigMetricsConfig: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
shadowProductionVariants EndpointConfigProductionVariant[]: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
tags Tag[]: A list of key-value pairs to apply to this resource.
vpcConfig EndpointConfigVpcConfig: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

production_variants Sequence[EndpointConfigProductionVariantArgs]: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
async_inference_config EndpointConfigAsyncInferenceConfigArgs: Specifies configuration for how an endpoint performs asynchronous inference.
data_capture_config EndpointConfigDataCaptureConfigArgs: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
enable_network_isolation bool: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
endpoint_config_name str: The name of the endpoint configuration.
execution_role_arn str: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
explainer_config EndpointConfigExplainerConfigArgs: A parameter to activate explainers.
kms_key_id str: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
metrics_config EndpointConfigMetricsConfigArgs: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
shadow_production_variants Sequence[EndpointConfigProductionVariantArgs]: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
tags Sequence[TagArgs]: A list of key-value pairs to apply to this resource.
vpc_config EndpointConfigVpcConfigArgs: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

productionVariants List<Property Map>: A list of ProductionVariant objects, one for each model that you want to host at this endpoint.
asyncInferenceConfig Property Map: Specifies configuration for how an endpoint performs asynchronous inference.
dataCaptureConfig Property Map: Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.
enableNetworkIsolation Boolean: Sets whether all model containers deployed to the endpoint are isolated. If they are, no inbound or outbound network calls can be made to or from the model containers.
endpointConfigName String: The name of the endpoint configuration.
executionRoleArn String: The Amazon Resource Name (ARN) of an IAM role that Amazon SageMaker AI can assume to perform actions on your behalf.
explainerConfig Property Map: A parameter to activate explainers.
kmsKeyId String: The Amazon Resource Name (ARN) of an AWS Key Management Service key that Amazon SageMaker uses to encrypt data on the storage volume attached to the ML compute instance that hosts the endpoint.
metricsConfig Property Map: Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.
shadowProductionVariants List<Property Map>: Array of ProductionVariant objects. There is one for each model that you want to host at this endpoint in shadow mode with production traffic replicated from the model specified on ProductionVariants. If you use this field, you can only specify one variant for ProductionVariants and one variant for ShadowProductionVariants.
tags List<Property Map>: A list of key-value pairs to apply to this resource.
vpcConfig Property Map: Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

Outputs

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

EndpointConfigArn string: The Amazon Resource Name (ARN) of the endpoint configuration.
Id string: The provider-assigned unique ID for this managed resource.

EndpointConfigArn string: The Amazon Resource Name (ARN) of the endpoint configuration.
Id string: The provider-assigned unique ID for this managed resource.

endpoint_config_arn string: The Amazon Resource Name (ARN) of the endpoint configuration.
id string: The provider-assigned unique ID for this managed resource.

endpointConfigArn String: The Amazon Resource Name (ARN) of the endpoint configuration.
id String: The provider-assigned unique ID for this managed resource.

endpointConfigArn string: The Amazon Resource Name (ARN) of the endpoint configuration.
id string: The provider-assigned unique ID for this managed resource.

endpoint_config_arn str: The Amazon Resource Name (ARN) of the endpoint configuration.
id str: The provider-assigned unique ID for this managed resource.

endpointConfigArn String: The Amazon Resource Name (ARN) of the endpoint configuration.
id String: The provider-assigned unique ID for this managed resource.

Supporting Types

EndpointConfigAsyncInferenceClientConfig, EndpointConfigAsyncInferenceClientConfigArgs

Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

MaxConcurrentInvocationsPerInstance int: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

MaxConcurrentInvocationsPerInstance int: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

max_concurrent_invocations_per_instance number: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance Integer: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance number: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

max_concurrent_invocations_per_instance int: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

maxConcurrentInvocationsPerInstance Number: The maximum number of concurrent requests sent by the SageMaker client to the model container. If no value is provided, SageMaker will choose an optimal value for you.

EndpointConfigAsyncInferenceConfig, EndpointConfigAsyncInferenceConfigArgs

Specifies configuration for how an endpoint performs asynchronous inference.

OutputConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigAsyncInferenceOutputConfig: Specifies the configuration for asynchronous inference invocation outputs.
ClientConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigAsyncInferenceClientConfig: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

OutputConfig EndpointConfigAsyncInferenceOutputConfig: Specifies the configuration for asynchronous inference invocation outputs.
ClientConfig EndpointConfigAsyncInferenceClientConfig: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

output_config object: Specifies the configuration for asynchronous inference invocation outputs.
client_config object: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

outputConfig EndpointConfigAsyncInferenceOutputConfig: Specifies the configuration for asynchronous inference invocation outputs.
clientConfig EndpointConfigAsyncInferenceClientConfig: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

outputConfig EndpointConfigAsyncInferenceOutputConfig: Specifies the configuration for asynchronous inference invocation outputs.
clientConfig EndpointConfigAsyncInferenceClientConfig: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

output_config EndpointConfigAsyncInferenceOutputConfig: Specifies the configuration for asynchronous inference invocation outputs.
client_config EndpointConfigAsyncInferenceClientConfig: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

outputConfig Property Map: Specifies the configuration for asynchronous inference invocation outputs.
clientConfig Property Map: Configures the behavior of the client used by SageMaker to interact with the model container during asynchronous inference.

EndpointConfigAsyncInferenceNotificationConfig, EndpointConfigAsyncInferenceNotificationConfigArgs

Specifies the configuration for notifications of inference results for asynchronous inference.

ErrorTopic string: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
IncludeInferenceResponseIn List<string>: The Amazon SNS topics where you want the inference response to be included.
SuccessTopic string: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

ErrorTopic string: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
IncludeInferenceResponseIn []string: The Amazon SNS topics where you want the inference response to be included.
SuccessTopic string: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

error_topic string: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
include_inference_response_in list(string): The Amazon SNS topics where you want the inference response to be included.
success_topic string: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic String: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
includeInferenceResponseIn List<String>: The Amazon SNS topics where you want the inference response to be included.
successTopic String: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic string: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
includeInferenceResponseIn string[]: The Amazon SNS topics where you want the inference response to be included.
successTopic string: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

error_topic str: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
include_inference_response_in Sequence[str]: The Amazon SNS topics where you want the inference response to be included.
success_topic str: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

errorTopic String: Amazon SNS topic to post a notification to when an inference fails. If no topic is provided, no notification is sent on failure.
includeInferenceResponseIn List<String>: The Amazon SNS topics where you want the inference response to be included.
successTopic String: Amazon SNS topic to post a notification to when an inference completes successfully. If no topic is provided, no notification is sent on success.

EndpointConfigAsyncInferenceOutputConfig, EndpointConfigAsyncInferenceOutputConfigArgs

Specifies the configuration for asynchronous inference invocation outputs.

KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
NotificationConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigAsyncInferenceNotificationConfig: Specifies the configuration for notifications of inference results for asynchronous inference.
S3FailurePath string: The Amazon S3 location to upload failure inference responses to.
S3OutputPath string: The Amazon S3 location to upload inference responses to.

KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
NotificationConfig EndpointConfigAsyncInferenceNotificationConfig: Specifies the configuration for notifications of inference results for asynchronous inference.
S3FailurePath string: The Amazon S3 location to upload failure inference responses to.
S3OutputPath string: The Amazon S3 location to upload inference responses to.

kms_key_id string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
notification_config object: Specifies the configuration for notifications of inference results for asynchronous inference.
s3_failure_path string: The Amazon S3 location to upload failure inference responses to.
s3_output_path string: The Amazon S3 location to upload inference responses to.

kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
notificationConfig EndpointConfigAsyncInferenceNotificationConfig: Specifies the configuration for notifications of inference results for asynchronous inference.
s3FailurePath String: The Amazon S3 location to upload failure inference responses to.
s3OutputPath String: The Amazon S3 location to upload inference responses to.

kmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
notificationConfig EndpointConfigAsyncInferenceNotificationConfig: Specifies the configuration for notifications of inference results for asynchronous inference.
s3FailurePath string: The Amazon S3 location to upload failure inference responses to.
s3OutputPath string: The Amazon S3 location to upload inference responses to.

kms_key_id str: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
notification_config EndpointConfigAsyncInferenceNotificationConfig: Specifies the configuration for notifications of inference results for asynchronous inference.
s3_failure_path str: The Amazon S3 location to upload failure inference responses to.
s3_output_path str: The Amazon S3 location to upload inference responses to.

kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the asynchronous inference output in Amazon S3.
notificationConfig Property Map: Specifies the configuration for notifications of inference results for asynchronous inference.
s3FailurePath String: The Amazon S3 location to upload failure inference responses to.
s3OutputPath String: The Amazon S3 location to upload inference responses to.

EndpointConfigCapacityReservationConfig, EndpointConfigCapacityReservationConfigArgs

Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.

CapacityReservationPreference string: Options that you can choose for the capacity reservation.
MlReservationArn string: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

CapacityReservationPreference string: Options that you can choose for the capacity reservation.
MlReservationArn string: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

capacity_reservation_preference string: Options that you can choose for the capacity reservation.
ml_reservation_arn string: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

capacityReservationPreference String: Options that you can choose for the capacity reservation.
mlReservationArn String: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

capacityReservationPreference string: Options that you can choose for the capacity reservation.
mlReservationArn string: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

capacity_reservation_preference str: Options that you can choose for the capacity reservation.
ml_reservation_arn str: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

capacityReservationPreference String: Options that you can choose for the capacity reservation.
mlReservationArn String: The Amazon Resource Name (ARN) that uniquely identifies the ML capacity reservation that SageMaker AI applies when it deploys the endpoint.

EndpointConfigCaptureContentTypeHeader, EndpointConfigCaptureContentTypeHeaderArgs

Specifies the JSON and CSV content types of the data that the endpoint captures.

CsvContentTypes List<string>: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
JsonContentTypes List<string>: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

CsvContentTypes []string: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
JsonContentTypes []string: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

csv_content_types list(string): A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
json_content_types list(string): A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

csvContentTypes List<String>: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
jsonContentTypes List<String>: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

csvContentTypes string[]: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
jsonContentTypes string[]: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

csv_content_types Sequence[str]: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
json_content_types Sequence[str]: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

csvContentTypes List<String>: A list of the CSV content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.
jsonContentTypes List<String>: A list of the JSON content types of the data that the endpoint captures. For the endpoint to capture the data, you must also specify the content type when you invoke the endpoint.

EndpointConfigCaptureOption, EndpointConfigCaptureOptionArgs

Specifies whether the endpoint captures input data or output data.

CaptureMode string: Specifies whether the endpoint captures input data or output data.

CaptureMode string: Specifies whether the endpoint captures input data or output data.

capture_mode string: Specifies whether the endpoint captures input data or output data.

captureMode String: Specifies whether the endpoint captures input data or output data.

captureMode string: Specifies whether the endpoint captures input data or output data.

capture_mode str: Specifies whether the endpoint captures input data or output data.

captureMode String: Specifies whether the endpoint captures input data or output data.

EndpointConfigClarifyExplainerConfig, EndpointConfigClarifyExplainerConfigArgs

The configuration parameters for the SageMaker Clarify explainer.

ShapConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigClarifyShapConfig: The configuration for SHAP analysis.
EnableExplanations string: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
InferenceConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigClarifyInferenceConfig: The inference configuration parameter for the model container.

ShapConfig EndpointConfigClarifyShapConfig: The configuration for SHAP analysis.
EnableExplanations string: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
InferenceConfig EndpointConfigClarifyInferenceConfig: The inference configuration parameter for the model container.

shap_config object: The configuration for SHAP analysis.
enable_explanations string: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
inference_config object: The inference configuration parameter for the model container.

shapConfig EndpointConfigClarifyShapConfig: The configuration for SHAP analysis.
enableExplanations String: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
inferenceConfig EndpointConfigClarifyInferenceConfig: The inference configuration parameter for the model container.

shapConfig EndpointConfigClarifyShapConfig: The configuration for SHAP analysis.
enableExplanations string: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
inferenceConfig EndpointConfigClarifyInferenceConfig: The inference configuration parameter for the model container.

shap_config EndpointConfigClarifyShapConfig: The configuration for SHAP analysis.
enable_explanations str: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
inference_config EndpointConfigClarifyInferenceConfig: The inference configuration parameter for the model container.

shapConfig Property Map: The configuration for SHAP analysis.
enableExplanations String: A JMESPath boolean expression used to filter which records to explain. Explanations are activated by default.
inferenceConfig Property Map: The inference configuration parameter for the model container.

EndpointConfigClarifyInferenceConfig, EndpointConfigClarifyInferenceConfigArgs

The inference configuration parameter for the model container.

ContentTemplate string: A template string used to format a JSON record into an acceptable model container input.
FeatureHeaders List<string>: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
FeatureTypes List<string>: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
FeaturesAttribute string: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
LabelAttribute string: A JMESPath expression used to locate the list of label headers in the model container output.
LabelHeaders List<string>: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
LabelIndex int: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
MaxPayloadInMb int: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
MaxRecordCount int: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
ProbabilityAttribute string: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
ProbabilityIndex int: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

ContentTemplate string: A template string used to format a JSON record into an acceptable model container input.
FeatureHeaders []string: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
FeatureTypes []string: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
FeaturesAttribute string: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
LabelAttribute string: A JMESPath expression used to locate the list of label headers in the model container output.
LabelHeaders []string: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
LabelIndex int: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
MaxPayloadInMb int: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
MaxRecordCount int: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
ProbabilityAttribute string: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
ProbabilityIndex int: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

content_template string: A template string used to format a JSON record into an acceptable model container input.
feature_headers list(string): The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
feature_types list(string): A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
features_attribute string: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
label_attribute string: A JMESPath expression used to locate the list of label headers in the model container output.
label_headers list(string): For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
label_index number: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
max_payload_in_mb number: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
max_record_count number: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
probability_attribute string: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
probability_index number: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

contentTemplate String: A template string used to format a JSON record into an acceptable model container input.
featureHeaders List<String>: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
featureTypes List<String>: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
featuresAttribute String: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
labelAttribute String: A JMESPath expression used to locate the list of label headers in the model container output.
labelHeaders List<String>: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
labelIndex Integer: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
maxPayloadInMb Integer: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
maxRecordCount Integer: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
probabilityAttribute String: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
probabilityIndex Integer: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

contentTemplate string: A template string used to format a JSON record into an acceptable model container input.
featureHeaders string[]: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
featureTypes string[]: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
featuresAttribute string: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
labelAttribute string: A JMESPath expression used to locate the list of label headers in the model container output.
labelHeaders string[]: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
labelIndex number: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
maxPayloadInMb number: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
maxRecordCount number: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
probabilityAttribute string: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
probabilityIndex number: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

content_template str: A template string used to format a JSON record into an acceptable model container input.
feature_headers Sequence[str]: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
feature_types Sequence[str]: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
features_attribute str: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
label_attribute str: A JMESPath expression used to locate the list of label headers in the model container output.
label_headers Sequence[str]: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
label_index int: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
max_payload_in_mb int: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
max_record_count int: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
probability_attribute str: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
probability_index int: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

contentTemplate String: A template string used to format a JSON record into an acceptable model container input.
featureHeaders List<String>: The names of the features. If provided, these are included in the endpoint response payload to help readability of the InvokeEndpoint output.
featureTypes List<String>: A list of data types of the features (optional). Applicable only to NLP explainability. If provided, FeatureTypes must have at least one 'text' string (for example, ['text']). If FeatureTypes is not provided, the explainer infers the feature types based on the baseline data.
featuresAttribute String: Provides the JMESPath expression to extract the features from a model container input in JSON Lines format.
labelAttribute String: A JMESPath expression used to locate the list of label headers in the model container output.
labelHeaders List<String>: For multiclass classification problems, the label headers are the names of the classes. Otherwise, the label header is the name of the predicted label.
labelIndex Number: A zero-based index used to extract a label header or list of label headers from model container output in CSV format.
maxPayloadInMb Number: The maximum payload size (MB) allowed of a request from the explainer to the model container. Defaults to 6 MB.
maxRecordCount Number: The maximum number of records in a request that the model container can process when querying the model container for the predictions of a synthetic dataset. A record is a unit of input data that inference can be made on, for example, a single line in CSV data.
probabilityAttribute String: A JMESPath expression used to extract the probability (or score) from the model container output if the model container is in JSON Lines format.
probabilityIndex Number: A zero-based index used to extract a probability value (score) or list from model container output in CSV format. If this value is not provided, the entire model container output will be treated as a probability value (score) or list.

EndpointConfigClarifyShapBaselineConfig, EndpointConfigClarifyShapBaselineConfigArgs

The configuration for the SHAP baseline (also called the background or reference dataset) of the Kernal SHAP algorithm.

MimeType string: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
ShapBaseline string: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
ShapBaselineUri string: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

MimeType string: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
ShapBaseline string: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
ShapBaselineUri string: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

mime_type string: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
shap_baseline string: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
shap_baseline_uri string: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

mimeType String: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
shapBaseline String: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
shapBaselineUri String: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

mimeType string: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
shapBaseline string: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
shapBaselineUri string: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

mime_type str: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
shap_baseline str: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
shap_baseline_uri str: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

mimeType String: The MIME type of the baseline data. Choose from 'text/csv' or 'application/jsonlines'. Defaults to 'text/csv'.
shapBaseline String: The inline SHAP baseline data in string format. ShapBaseline can have one or multiple records to be used as the baseline dataset. The format of the SHAP baseline file should be the same format as the training dataset.
shapBaselineUri String: The uniform resource identifier (URI) of the S3 bucket where the SHAP baseline file is stored. The format of the SHAP baseline file should be the same format as the format of the training dataset.

EndpointConfigClarifyShapConfig, EndpointConfigClarifyShapConfigArgs

The configuration for SHAP analysis using SageMaker Clarify Explainer.

ShapBaselineConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigClarifyShapBaselineConfig: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
NumberOfSamples int: The number of samples to be used for analysis by the Kernal SHAP algorithm.
Seed int: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
TextConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigClarifyTextConfig: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
UseLogit bool: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

ShapBaselineConfig EndpointConfigClarifyShapBaselineConfig: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
NumberOfSamples int: The number of samples to be used for analysis by the Kernal SHAP algorithm.
Seed int: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
TextConfig EndpointConfigClarifyTextConfig: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
UseLogit bool: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

shap_baseline_config object: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
number_of_samples number: The number of samples to be used for analysis by the Kernal SHAP algorithm.
seed number: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
text_config object: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
use_logit bool: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

shapBaselineConfig EndpointConfigClarifyShapBaselineConfig: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
numberOfSamples Integer: The number of samples to be used for analysis by the Kernal SHAP algorithm.
seed Integer: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
textConfig EndpointConfigClarifyTextConfig: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
useLogit Boolean: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

shapBaselineConfig EndpointConfigClarifyShapBaselineConfig: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
numberOfSamples number: The number of samples to be used for analysis by the Kernal SHAP algorithm.
seed number: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
textConfig EndpointConfigClarifyTextConfig: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
useLogit boolean: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

shap_baseline_config EndpointConfigClarifyShapBaselineConfig: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
number_of_samples int: The number of samples to be used for analysis by the Kernal SHAP algorithm.
seed int: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
text_config EndpointConfigClarifyTextConfig: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
use_logit bool: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

shapBaselineConfig Property Map: The configuration for the SHAP baseline of the Kernal SHAP algorithm.
numberOfSamples Number: The number of samples to be used for analysis by the Kernal SHAP algorithm.
seed Number: The starting value used to initialize the random number generator in the explainer. Provide a value for this parameter to obtain a deterministic SHAP result.
textConfig Property Map: A parameter that indicates if text features are treated as text and explanations are provided for individual units of text. Required for natural language processing (NLP) explainability only.
useLogit Boolean: A Boolean toggle to indicate if you want to use the logit function (true) or log-odds units (false) for model predictions. Defaults to false.

EndpointConfigClarifyTextConfig, EndpointConfigClarifyTextConfigArgs

A parameter used to configure the SageMaker Clarify explainer to treat text features as text so that explanations are provided for individual units of text. Required only for natural language processing (NLP) explainability.

Granularity string: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
Language string: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

Granularity string: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
Language string: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

granularity string: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
language string: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

granularity String: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
language String: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

granularity string: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
language string: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

granularity str: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
language str: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

granularity String: The unit of granularity for the analysis of text features. For example, if the unit is 'token', then each token (like a word in English) of the text is treated as a feature. SHAP values are computed for each unit/feature.
language String: Specifies the language of the text features in ISO 639-1 or ISO 639-3 code of a supported language.

EndpointConfigCoreDumpConfig, EndpointConfigCoreDumpConfigArgs

Specifies where SageMaker writes core dumps from the model container when the process crashes, and how it encrypts them.

DestinationS3Uri string: The Amazon S3 bucket to send the core dump to.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

DestinationS3Uri string: The Amazon S3 bucket to send the core dump to.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

destination_s3_uri string: The Amazon S3 bucket to send the core dump to.
kms_key_id string: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

destinationS3Uri String: The Amazon S3 bucket to send the core dump to.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

destinationS3Uri string: The Amazon S3 bucket to send the core dump to.
kmsKeyId string: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

destination_s3_uri str: The Amazon S3 bucket to send the core dump to.
kms_key_id str: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

destinationS3Uri String: The Amazon S3 bucket to send the core dump to.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that SageMaker uses to encrypt the core dump data at rest using Amazon S3 server-side encryption. If you use a KMS key ID or an alias of your KMS key, the SageMaker execution role must include permissions to call kms:Encrypt.

EndpointConfigDataCaptureConfig, EndpointConfigDataCaptureConfigArgs

Specifies how to capture endpoint data for model monitor. The data capture configuration applies to all production variants hosted at the endpoint.

CaptureOptions List<Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigCaptureOption>: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
DestinationS3Uri string: The S3 bucket where model monitor stores captured data.
InitialSamplingPercentage int: The percentage of data to capture.
CaptureContentTypeHeader Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigCaptureContentTypeHeader: A list of the JSON and CSV content type that the endpoint captures.
EnableCapture bool: Set to True to enable data capture.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

CaptureOptions []EndpointConfigCaptureOption: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
DestinationS3Uri string: The S3 bucket where model monitor stores captured data.
InitialSamplingPercentage int: The percentage of data to capture.
CaptureContentTypeHeader EndpointConfigCaptureContentTypeHeader: A list of the JSON and CSV content type that the endpoint captures.
EnableCapture bool: Set to True to enable data capture.
KmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

capture_options list(object): Specifies whether the endpoint captures input data to your model, output data from your model, or both.
destination_s3_uri string: The S3 bucket where model monitor stores captured data.
initial_sampling_percentage number: The percentage of data to capture.
capture_content_type_header object: A list of the JSON and CSV content type that the endpoint captures.
enable_capture bool: Set to True to enable data capture.
kms_key_id string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

captureOptions List<EndpointConfigCaptureOption>: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
destinationS3Uri String: The S3 bucket where model monitor stores captured data.
initialSamplingPercentage Integer: The percentage of data to capture.
captureContentTypeHeader EndpointConfigCaptureContentTypeHeader: A list of the JSON and CSV content type that the endpoint captures.
enableCapture Boolean: Set to True to enable data capture.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

captureOptions EndpointConfigCaptureOption[]: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
destinationS3Uri string: The S3 bucket where model monitor stores captured data.
initialSamplingPercentage number: The percentage of data to capture.
captureContentTypeHeader EndpointConfigCaptureContentTypeHeader: A list of the JSON and CSV content type that the endpoint captures.
enableCapture boolean: Set to True to enable data capture.
kmsKeyId string: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

capture_options Sequence[EndpointConfigCaptureOption]: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
destination_s3_uri str: The S3 bucket where model monitor stores captured data.
initial_sampling_percentage int: The percentage of data to capture.
capture_content_type_header EndpointConfigCaptureContentTypeHeader: A list of the JSON and CSV content type that the endpoint captures.
enable_capture bool: Set to True to enable data capture.
kms_key_id str: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

captureOptions List<Property Map>: Specifies whether the endpoint captures input data to your model, output data from your model, or both.
destinationS3Uri String: The S3 bucket where model monitor stores captured data.
initialSamplingPercentage Number: The percentage of data to capture.
captureContentTypeHeader Property Map: A list of the JSON and CSV content type that the endpoint captures.
enableCapture Boolean: Set to True to enable data capture.
kmsKeyId String: The AWS Key Management Service (AWS KMS) key that Amazon SageMaker uses to encrypt the captured data at rest using Amazon S3 server-side encryption.

EndpointConfigExplainerConfig, EndpointConfigExplainerConfigArgs

A parameter to activate explainers.

ClarifyExplainerConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigClarifyExplainerConfig: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

ClarifyExplainerConfig EndpointConfigClarifyExplainerConfig: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

clarify_explainer_config object: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

clarifyExplainerConfig EndpointConfigClarifyExplainerConfig: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

clarifyExplainerConfig EndpointConfigClarifyExplainerConfig: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

clarify_explainer_config EndpointConfigClarifyExplainerConfig: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

clarifyExplainerConfig Property Map: A member of ExplainerConfig that contains configuration parameters for the SageMaker Clarify explainer.

EndpointConfigInstancePool, EndpointConfigInstancePoolArgs

Specifies an instance type and its priority for a heterogeneous endpoint. Use instance pools to configure a production variant with multiple instance types, enabling the endpoint to provision instances across different types based on priority.

InstanceType string: The ML compute instance type for the instance pool.
Priority int: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
ModelNameOverride string: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

InstanceType string: The ML compute instance type for the instance pool.
Priority int: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
ModelNameOverride string: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

instance_type string: The ML compute instance type for the instance pool.
priority number: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
model_name_override string: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

instanceType String: The ML compute instance type for the instance pool.
priority Integer: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
modelNameOverride String: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

instanceType string: The ML compute instance type for the instance pool.
priority number: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
modelNameOverride string: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

instance_type str: The ML compute instance type for the instance pool.
priority int: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
model_name_override str: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

instanceType String: The ML compute instance type for the instance pool.
priority Number: The priority for the instance pool. SageMaker attempts to provision instances in order of priority, starting with the lowest value. If instances for a higher-priority pool are unavailable, SageMaker attempts to provision from the next pool. Valid values: 1 to 5, where 1 is the highest priority.
modelNameOverride String: The name of a SageMaker model to use for this instance pool instead of the model specified for the production variant. Use this to deploy a different model optimized for the instance type in this pool.

EndpointConfigManagedInstanceScaling, EndpointConfigManagedInstanceScalingArgs

Settings that control the range in the number of instances that the endpoint provisions as it scales up or down to accommodate traffic.

MaxInstanceCount int: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
MinInstanceCount int: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
ScaleInPolicy Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigScaleInPolicy: Configures the scale-in behavior for managed instance scaling.
Status string: Indicates whether managed instance scaling is enabled.

MaxInstanceCount int: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
MinInstanceCount int: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
ScaleInPolicy EndpointConfigScaleInPolicy: Configures the scale-in behavior for managed instance scaling.
Status string: Indicates whether managed instance scaling is enabled.

max_instance_count number: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
min_instance_count number: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
scale_in_policy object: Configures the scale-in behavior for managed instance scaling.
status string: Indicates whether managed instance scaling is enabled.

maxInstanceCount Integer: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
minInstanceCount Integer: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
scaleInPolicy EndpointConfigScaleInPolicy: Configures the scale-in behavior for managed instance scaling.
status String: Indicates whether managed instance scaling is enabled.

maxInstanceCount number: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
minInstanceCount number: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
scaleInPolicy EndpointConfigScaleInPolicy: Configures the scale-in behavior for managed instance scaling.
status string: Indicates whether managed instance scaling is enabled.

max_instance_count int: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
min_instance_count int: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
scale_in_policy EndpointConfigScaleInPolicy: Configures the scale-in behavior for managed instance scaling.
status str: Indicates whether managed instance scaling is enabled.

maxInstanceCount Number: The maximum number of instances that the endpoint can provision when it scales up to accommodate an increase in traffic.
minInstanceCount Number: The minimum number of instances that the endpoint must retain when it scales down to accommodate a decrease in traffic.
scaleInPolicy Property Map: Configures the scale-in behavior for managed instance scaling.
status String: Indicates whether managed instance scaling is enabled.

EndpointConfigMetricsConfig, EndpointConfigMetricsConfigArgs

Specifies the metrics that the endpoint publishes to Amazon CloudWatch, the frequency of publication, and whether to enable enhanced or detailed observability metrics.

EnableDetailedObservability bool: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
EnableEnhancedMetrics bool: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
MetricPublishFrequencyInSeconds int: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

EnableDetailedObservability bool: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
EnableEnhancedMetrics bool: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
MetricPublishFrequencyInSeconds int: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

enable_detailed_observability bool: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
enable_enhanced_metrics bool: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
metric_publish_frequency_in_seconds number: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

enableDetailedObservability Boolean: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
enableEnhancedMetrics Boolean: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
metricPublishFrequencyInSeconds Integer: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

enableDetailedObservability boolean: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
enableEnhancedMetrics boolean: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
metricPublishFrequencyInSeconds number: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

enable_detailed_observability bool: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
enable_enhanced_metrics bool: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
metric_publish_frequency_in_seconds int: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

enableDetailedObservability Boolean: Specifies whether to enable detailed observability for the endpoint. When set to true, the endpoint publishes container-level inference metrics, per-GPU metrics, per-instance host metrics, and inference component placement metrics.
enableEnhancedMetrics Boolean: Specifies whether to enable enhanced metrics for the endpoint. Enhanced metrics provide utilization and invocation data at instance and container granularity.
metricPublishFrequencyInSeconds Number: The interval, in seconds, at which the endpoint publishes metrics to Amazon CloudWatch. Valid values are 10, 30, 60, 120, 180, 240, and 300. The default is 60.

EndpointConfigPrefixAwareRoutingConfig, EndpointConfigPrefixAwareRoutingConfigArgs

The configuration for prefix-aware routing on a SageMaker real-time inference endpoint. Specify PrefixLength and ConcurrencyThreshold to control routing behavior.

ConcurrencyThreshold int: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
PrefixLength int: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

ConcurrencyThreshold int: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
PrefixLength int: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

concurrency_threshold number: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
prefix_length number: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

concurrencyThreshold Integer: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
prefixLength Integer: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

concurrencyThreshold number: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
prefixLength number: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

concurrency_threshold int: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
prefix_length int: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

concurrencyThreshold Number: The maximum number of in-flight requests on the target instance before the endpoint routes to another instance. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1 to 1024.
prefixLength Number: The maximum length of the prefix used for routing decisions. Required when RoutingStrategy is PREFIX_AWARE. Valid values are 1024 to 65536.

EndpointConfigProductionVariant, EndpointConfigProductionVariantArgs

Specifies a model that you want to host and the resources to deploy for hosting it.

VariantName string: The name of the production variant.
CapacityReservationConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigCapacityReservationConfig: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
ContainerStartupHealthCheckTimeoutInSeconds int: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
CoreDumpConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigCoreDumpConfig: Specifies configuration for a core dump from the model container when the process crashes.
EnableSsmAccess bool: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
InferenceAmiVersion string: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
InitialInstanceCount int: Number of instances to launch initially.
InitialVariantWeight double: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
InstancePools List<Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigInstancePool>: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
InstanceType string: The ML compute instance type.
ManagedInstanceScaling Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigManagedInstanceScaling
ModelDataDownloadTimeoutInSeconds int: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
ModelName string: The name of the model that you want to host. This is the name that you specified when creating the model.
RoutingConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigRoutingConfig: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
ServerlessConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigServerlessConfig: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
VariantInstanceProvisionTimeoutInSeconds int: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
VolumeSizeInGb int: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

VariantName string: The name of the production variant.
CapacityReservationConfig EndpointConfigCapacityReservationConfig: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
ContainerStartupHealthCheckTimeoutInSeconds int: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
CoreDumpConfig EndpointConfigCoreDumpConfig: Specifies configuration for a core dump from the model container when the process crashes.
EnableSsmAccess bool: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
InferenceAmiVersion string: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
InitialInstanceCount int: Number of instances to launch initially.
InitialVariantWeight float64: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
InstancePools []EndpointConfigInstancePool: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
InstanceType string: The ML compute instance type.
ManagedInstanceScaling EndpointConfigManagedInstanceScaling
ModelDataDownloadTimeoutInSeconds int: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
ModelName string: The name of the model that you want to host. This is the name that you specified when creating the model.
RoutingConfig EndpointConfigRoutingConfig: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
ServerlessConfig EndpointConfigServerlessConfig: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
VariantInstanceProvisionTimeoutInSeconds int: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
VolumeSizeInGb int: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

variant_name string: The name of the production variant.
capacity_reservation_config object: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
container_startup_health_check_timeout_in_seconds number: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
core_dump_config object: Specifies configuration for a core dump from the model container when the process crashes.
enable_ssm_access bool: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
inference_ami_version string: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
initial_instance_count number: Number of instances to launch initially.
initial_variant_weight number: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
instance_pools list(object): A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
instance_type string: The ML compute instance type.
managed_instance_scaling object
model_data_download_timeout_in_seconds number: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
model_name string: The name of the model that you want to host. This is the name that you specified when creating the model.
routing_config object: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
serverless_config object: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
variant_instance_provision_timeout_in_seconds number: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
volume_size_in_gb number: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

variantName String: The name of the production variant.
capacityReservationConfig EndpointConfigCapacityReservationConfig: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
containerStartupHealthCheckTimeoutInSeconds Integer: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
coreDumpConfig EndpointConfigCoreDumpConfig: Specifies configuration for a core dump from the model container when the process crashes.
enableSsmAccess Boolean: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
inferenceAmiVersion String: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
initialInstanceCount Integer: Number of instances to launch initially.
initialVariantWeight Double: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
instancePools List<EndpointConfigInstancePool>: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
instanceType String: The ML compute instance type.
managedInstanceScaling EndpointConfigManagedInstanceScaling
modelDataDownloadTimeoutInSeconds Integer: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
modelName String: The name of the model that you want to host. This is the name that you specified when creating the model.
routingConfig EndpointConfigRoutingConfig: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
serverlessConfig EndpointConfigServerlessConfig: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
variantInstanceProvisionTimeoutInSeconds Integer: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
volumeSizeInGb Integer: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

variantName string: The name of the production variant.
capacityReservationConfig EndpointConfigCapacityReservationConfig: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
containerStartupHealthCheckTimeoutInSeconds number: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
coreDumpConfig EndpointConfigCoreDumpConfig: Specifies configuration for a core dump from the model container when the process crashes.
enableSsmAccess boolean: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
inferenceAmiVersion string: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
initialInstanceCount number: Number of instances to launch initially.
initialVariantWeight number: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
instancePools EndpointConfigInstancePool[]: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
instanceType string: The ML compute instance type.
managedInstanceScaling EndpointConfigManagedInstanceScaling
modelDataDownloadTimeoutInSeconds number: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
modelName string: The name of the model that you want to host. This is the name that you specified when creating the model.
routingConfig EndpointConfigRoutingConfig: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
serverlessConfig EndpointConfigServerlessConfig: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
variantInstanceProvisionTimeoutInSeconds number: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
volumeSizeInGb number: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

variant_name str: The name of the production variant.
capacity_reservation_config EndpointConfigCapacityReservationConfig: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
container_startup_health_check_timeout_in_seconds int: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
core_dump_config EndpointConfigCoreDumpConfig: Specifies configuration for a core dump from the model container when the process crashes.
enable_ssm_access bool: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
inference_ami_version str: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
initial_instance_count int: Number of instances to launch initially.
initial_variant_weight float: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
instance_pools Sequence[EndpointConfigInstancePool]: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
instance_type str: The ML compute instance type.
managed_instance_scaling EndpointConfigManagedInstanceScaling
model_data_download_timeout_in_seconds int: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
model_name str: The name of the model that you want to host. This is the name that you specified when creating the model.
routing_config EndpointConfigRoutingConfig: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
serverless_config EndpointConfigServerlessConfig: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
variant_instance_provision_timeout_in_seconds int: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
volume_size_in_gb int: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

variantName String: The name of the production variant.
capacityReservationConfig Property Map: Settings for the capacity reservation for the compute instances that SageMaker AI reserves for an endpoint.
containerStartupHealthCheckTimeoutInSeconds Number: The timeout value, in seconds, for your inference container to pass health check by SageMaker Hosting.
coreDumpConfig Property Map: Specifies configuration for a core dump from the model container when the process crashes.
enableSsmAccess Boolean: You can use this parameter to turn on native AWS Systems Manager (SSM) access for a production variant behind an endpoint. By default, SSM access is disabled for all production variants behind an endpoint.
inferenceAmiVersion String: Specifies an option from a collection of preconfigured Amazon Machine Image (AMI) images. Each image is configured by AWS with a set of software and driver versions. AWS optimizes these configurations for different machine learning workloads. By selecting an AMI version, you can ensure that your inference environment is compatible with specific software requirements, such as CUDA driver versions, Linux kernel versions, or AWS Neuron driver versions
initialInstanceCount Number: Number of instances to launch initially.
initialVariantWeight Number: Determines initial traffic distribution among all of the models that you specify in the endpoint configuration.
instancePools List<Property Map>: A list of instance pools for the production variant. Each instance pool specifies an instance type and its priority for provisioning. Use instance pools to configure heterogeneous endpoints that deploy models across multiple instance types.
instanceType String: The ML compute instance type.
managedInstanceScaling Property Map
modelDataDownloadTimeoutInSeconds Number: The timeout value, in seconds, to download and extract the model that you want to host from Amazon S3 to the individual inference instance associated with this production variant.
modelName String: The name of the model that you want to host. This is the name that you specified when creating the model.
routingConfig Property Map: Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.
serverlessConfig Property Map: The serverless configuration for an endpoint. Specifies a serverless endpoint configuration instead of an instance-based endpoint configuration.
variantInstanceProvisionTimeoutInSeconds Number: The timeout value, in seconds, for provisioning instances for the production variant. When SageMaker encounters an insufficient capacity error while provisioning instances, it retries with the next instance pool (if configured) or waits until the timeout expires. This timeout applies only to capacity provisioning and does not include the time for model download or container startup.
volumeSizeInGb Number: The size, in GB, of the ML storage volume attached to individual inference instance associated with the production variant. Currently only Amazon EBS gp2 storage volumes are supported.

EndpointConfigRoutingConfig, EndpointConfigRoutingConfigArgs

Settings that control how the endpoint routes incoming traffic to the instances that the endpoint hosts.

PrefixAwareRoutingConfig Pulumi.AwsNative.SageMaker.Inputs.EndpointConfigPrefixAwareRoutingConfig: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
RoutingStrategy string: Sets how the endpoint routes incoming traffic.

PrefixAwareRoutingConfig EndpointConfigPrefixAwareRoutingConfig: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
RoutingStrategy string: Sets how the endpoint routes incoming traffic.

prefix_aware_routing_config object: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
routing_strategy string: Sets how the endpoint routes incoming traffic.

prefixAwareRoutingConfig EndpointConfigPrefixAwareRoutingConfig: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
routingStrategy String: Sets how the endpoint routes incoming traffic.

prefixAwareRoutingConfig EndpointConfigPrefixAwareRoutingConfig: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
routingStrategy string: Sets how the endpoint routes incoming traffic.

prefix_aware_routing_config EndpointConfigPrefixAwareRoutingConfig: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
routing_strategy str: Sets how the endpoint routes incoming traffic.

prefixAwareRoutingConfig Property Map: The configuration for prefix-aware routing. Specify this property only when you set RoutingStrategy to PREFIX_AWARE.
routingStrategy String: Sets how the endpoint routes incoming traffic.

EndpointConfigScaleInPolicy, EndpointConfigScaleInPolicyArgs

Specifies how the endpoint releases instances when managed instance scaling scales in.

Strategy string: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
CooldownInMinutes int: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
MaximumStepSize int: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

Strategy string: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
CooldownInMinutes int: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
MaximumStepSize int: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

strategy string: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
cooldown_in_minutes number: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
maximum_step_size number: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

strategy String: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
cooldownInMinutes Integer: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
maximumStepSize Integer: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

strategy string: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
cooldownInMinutes number: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
maximumStepSize number: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

strategy str: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
cooldown_in_minutes int: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
maximum_step_size int: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

strategy String: The strategy for scaling in instances. IDLE_RELEASE releases instances that have no hosted inference component copies. CONSOLIDATION consolidates inference component copies onto fewer instances to release more instances.
cooldownInMinutes Number: The cooldown period, in minutes, after the last endpoint operation before the endpoint evaluates consolidation scale-in opportunities. Valid values are 5 to 1440. The default is 20.
maximumStepSize Number: The maximum number of instances that the endpoint can terminate at a time during a consolidation scale-in operation. Valid values are 1 to 100. The default is 1.

EndpointConfigServerlessConfig, EndpointConfigServerlessConfigArgs

Specifies the serverless configuration for an endpoint variant.

MaxConcurrency int: The maximum number of concurrent invocations your serverless endpoint can process.
MemorySizeInMb int: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
ProvisionedConcurrency int: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

MaxConcurrency int: The maximum number of concurrent invocations your serverless endpoint can process.
MemorySizeInMb int: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
ProvisionedConcurrency int: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

max_concurrency number: The maximum number of concurrent invocations your serverless endpoint can process.
memory_size_in_mb number: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisioned_concurrency number: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

maxConcurrency Integer: The maximum number of concurrent invocations your serverless endpoint can process.
memorySizeInMb Integer: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisionedConcurrency Integer: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

maxConcurrency number: The maximum number of concurrent invocations your serverless endpoint can process.
memorySizeInMb number: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisionedConcurrency number: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

max_concurrency int: The maximum number of concurrent invocations your serverless endpoint can process.
memory_size_in_mb int: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisioned_concurrency int: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

maxConcurrency Number: The maximum number of concurrent invocations your serverless endpoint can process.
memorySizeInMb Number: The memory size of your serverless endpoint. Valid values are in 1 GB increments: 1024 MB, 2048 MB, 3072 MB, 4096 MB, 5120 MB, or 6144 MB.
provisionedConcurrency Number: The amount of provisioned concurrency to allocate for the serverless endpoint. Should be less than or equal to MaxConcurrency.

EndpointConfigVpcConfig, EndpointConfigVpcConfigArgs

Specifies an Amazon Virtual Private Cloud (VPC) that your SageMaker jobs, hosted models, and compute resources have access to. You can control access to and from your resources by configuring a VPC.

SecurityGroupIds List<string>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
Subnets List<string>: The ID of the subnets in the VPC to which you want to connect your training job or model.

SecurityGroupIds []string: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
Subnets []string: The ID of the subnets in the VPC to which you want to connect your training job or model.

security_group_ids list(string): The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
subnets list(string): The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds List<String>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
subnets List<String>: The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds string[]: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
subnets string[]: The ID of the subnets in the VPC to which you want to connect your training job or model.

security_group_ids Sequence[str]: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
subnets Sequence[str]: The ID of the subnets in the VPC to which you want to connect your training job or model.

securityGroupIds List<String>: The VPC security group IDs, in the form sg-xxxxxxxx. Specify the security groups for the VPC that is specified in the Subnets field.
subnets List<String>: The ID of the subnets in the VPC to which you want to connect your training job or model.

Tag, TagArgs

A set of tags to apply to the resource.

Key string: The key name of the tag
Value string: The value of the tag

Key string: The key name of the tag
Value string: The value of the tag

key string: The key name of the tag
value string: The value of the tag

key String: The key name of the tag
value String: The value of the tag

key string: The key name of the tag
value string: The value of the tag

key str: The key name of the tag
value str: The value of the tag

key String: The key name of the tag
value String: The value of the tag

Package Details

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

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

Viewing docs for AWS Cloud Control v1.81.0
published on Monday, Sep 28, 2026 by Pulumi

Schema (JSON)

pulumi/pulumi-aws-native

aws-native.sagemaker.EndpointConfig

On this page

On this page

Create EndpointConfig Resource

Constructor syntax

Parameters

EndpointConfig Resource Properties

Inputs

Outputs

Supporting Types

EndpointConfigAsyncInferenceClientConfig, EndpointConfigAsyncInferenceClientConfigArgs

EndpointConfigAsyncInferenceConfig, EndpointConfigAsyncInferenceConfigArgs

EndpointConfigAsyncInferenceNotificationConfig, EndpointConfigAsyncInferenceNotificationConfigArgs

EndpointConfigAsyncInferenceOutputConfig, EndpointConfigAsyncInferenceOutputConfigArgs

EndpointConfigCapacityReservationConfig, EndpointConfigCapacityReservationConfigArgs

EndpointConfigCaptureContentTypeHeader, EndpointConfigCaptureContentTypeHeaderArgs

EndpointConfigCaptureOption, EndpointConfigCaptureOptionArgs

EndpointConfigClarifyExplainerConfig, EndpointConfigClarifyExplainerConfigArgs

EndpointConfigClarifyInferenceConfig, EndpointConfigClarifyInferenceConfigArgs

EndpointConfigClarifyShapBaselineConfig, EndpointConfigClarifyShapBaselineConfigArgs

EndpointConfigClarifyShapConfig, EndpointConfigClarifyShapConfigArgs

EndpointConfigClarifyTextConfig, EndpointConfigClarifyTextConfigArgs

EndpointConfigCoreDumpConfig, EndpointConfigCoreDumpConfigArgs

EndpointConfigDataCaptureConfig, EndpointConfigDataCaptureConfigArgs

EndpointConfigExplainerConfig, EndpointConfigExplainerConfigArgs

EndpointConfigInstancePool, EndpointConfigInstancePoolArgs

EndpointConfigManagedInstanceScaling, EndpointConfigManagedInstanceScalingArgs

EndpointConfigMetricsConfig, EndpointConfigMetricsConfigArgs

EndpointConfigPrefixAwareRoutingConfig, EndpointConfigPrefixAwareRoutingConfigArgs

EndpointConfigProductionVariant, EndpointConfigProductionVariantArgs

EndpointConfigRoutingConfig, EndpointConfigRoutingConfigArgs

EndpointConfigScaleInPolicy, EndpointConfigScaleInPolicyArgs

EndpointConfigServerlessConfig, EndpointConfigServerlessConfigArgs

EndpointConfigVpcConfig, EndpointConfigVpcConfigArgs

Tag, TagArgs

Package Details

On this page

On this page

Try Pulumi Cloud free.
Your team will thank you.

aws-native.sagemaker.EndpointConfig

On this page

On this page

Create EndpointConfig Resource

Constructor syntax

Parameters

EndpointConfig Resource Properties

Inputs

Outputs

Supporting Types

EndpointConfigAsyncInferenceClientConfig, EndpointConfigAsyncInferenceClientConfigArgs

EndpointConfigAsyncInferenceConfig, EndpointConfigAsyncInferenceConfigArgs

EndpointConfigAsyncInferenceNotificationConfig, EndpointConfigAsyncInferenceNotificationConfigArgs

EndpointConfigAsyncInferenceOutputConfig, EndpointConfigAsyncInferenceOutputConfigArgs

EndpointConfigCapacityReservationConfig, EndpointConfigCapacityReservationConfigArgs

EndpointConfigCaptureContentTypeHeader, EndpointConfigCaptureContentTypeHeaderArgs

EndpointConfigCaptureOption, EndpointConfigCaptureOptionArgs

EndpointConfigClarifyExplainerConfig, EndpointConfigClarifyExplainerConfigArgs

EndpointConfigClarifyInferenceConfig, EndpointConfigClarifyInferenceConfigArgs

EndpointConfigClarifyShapBaselineConfig, EndpointConfigClarifyShapBaselineConfigArgs

EndpointConfigClarifyShapConfig, EndpointConfigClarifyShapConfigArgs

EndpointConfigClarifyTextConfig, EndpointConfigClarifyTextConfigArgs

EndpointConfigCoreDumpConfig, EndpointConfigCoreDumpConfigArgs

EndpointConfigDataCaptureConfig, EndpointConfigDataCaptureConfigArgs

EndpointConfigExplainerConfig, EndpointConfigExplainerConfigArgs

EndpointConfigInstancePool, EndpointConfigInstancePoolArgs

EndpointConfigManagedInstanceScaling, EndpointConfigManagedInstanceScalingArgs

EndpointConfigMetricsConfig, EndpointConfigMetricsConfigArgs

EndpointConfigPrefixAwareRoutingConfig, EndpointConfigPrefixAwareRoutingConfigArgs

EndpointConfigProductionVariant, EndpointConfigProductionVariantArgs

EndpointConfigRoutingConfig, EndpointConfigRoutingConfigArgs

EndpointConfigScaleInPolicy, EndpointConfigScaleInPolicyArgs

EndpointConfigServerlessConfig, EndpointConfigServerlessConfigArgs

EndpointConfigVpcConfig, EndpointConfigVpcConfigArgs

Tag, TagArgs

Package Details

On this page

On this page

Try Pulumi Cloud free.Your team will thank you.

Try Pulumi Cloud free.
Your team will thank you.