We recommend new projects start with resources from the AWS provider.
published on Monday, Apr 20, 2026 by Pulumi
We recommend new projects start with resources from the AWS provider.
published on Monday, Apr 20, 2026 by Pulumi
Resource type definition for AWS::SageMaker::Model
Create Model Resource
Resources are created with functions called constructors. To learn more about declaring and configuring resources, see Resources.
Constructor syntax
new Model(name: string, args?: ModelArgs, opts?: CustomResourceOptions);@overload
def Model(resource_name: str,
args: Optional[ModelArgs] = None,
opts: Optional[ResourceOptions] = None)
@overload
def Model(resource_name: str,
opts: Optional[ResourceOptions] = None,
containers: Optional[Sequence[ModelContainerDefinitionArgs]] = None,
enable_network_isolation: Optional[bool] = None,
execution_role_arn: Optional[str] = None,
inference_execution_config: Optional[ModelInferenceExecutionConfigArgs] = None,
model_name: Optional[str] = None,
primary_container: Optional[ModelContainerDefinitionArgs] = None,
tags: Optional[Sequence[_root_inputs.TagArgs]] = None,
vpc_config: Optional[ModelVpcConfigArgs] = None)func NewModel(ctx *Context, name string, args *ModelArgs, opts ...ResourceOption) (*Model, error)public Model(string name, ModelArgs? args = null, CustomResourceOptions? opts = null)type: aws-native:sagemaker:Model
properties: # The arguments to resource properties.
options: # Bag of options to control resource's behavior.
Parameters
- name string
- The unique name of the resource.
- args ModelArgs
- 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 ModelArgs
- 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 ModelArgs
- The arguments to resource properties.
- opts ResourceOption
- Bag of options to control resource's behavior.
- name string
- The unique name of the resource.
- args ModelArgs
- The arguments to resource properties.
- opts CustomResourceOptions
- Bag of options to control resource's behavior.
- name String
- The unique name of the resource.
- args ModelArgs
- The arguments to resource properties.
- options CustomResourceOptions
- Bag of options to control resource's behavior.
Model 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 Model resource accepts the following input properties:
- Containers
List<Pulumi.
Aws Native. Sage Maker. Inputs. Model Container Definition> - Specifies the containers in the inference pipeline.
- Enable
Network boolIsolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- Execution
Role stringArn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- Inference
Execution Pulumi.Config Aws Native. Sage Maker. Inputs. Model Inference Execution Config - Specifies details of how containers in a multi-container endpoint are called.
- Model
Name string - The name of the new model.
- Primary
Container Pulumi.Aws Native. Sage Maker. Inputs. Model Container Definition - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
-
List<Pulumi.
Aws Native. Inputs. Tag> - An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- Vpc
Config Pulumi.Aws Native. Sage Maker. Inputs. Model Vpc Config - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
- Containers
[]Model
Container Definition Args - Specifies the containers in the inference pipeline.
- Enable
Network boolIsolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- Execution
Role stringArn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- Inference
Execution ModelConfig Inference Execution Config Args - Specifies details of how containers in a multi-container endpoint are called.
- Model
Name string - The name of the new model.
- Primary
Container ModelContainer Definition Args - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
-
Tag
Args - An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- Vpc
Config ModelVpc Config Args - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
- containers
List<Model
Container Definition> - Specifies the containers in the inference pipeline.
- enable
Network BooleanIsolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- execution
Role StringArn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- inference
Execution ModelConfig Inference Execution Config - Specifies details of how containers in a multi-container endpoint are called.
- model
Name String - The name of the new model.
- primary
Container ModelContainer Definition - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
- List<Tag>
- An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- vpc
Config ModelVpc Config - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
- containers
Model
Container Definition[] - Specifies the containers in the inference pipeline.
- enable
Network booleanIsolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- execution
Role stringArn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- inference
Execution ModelConfig Inference Execution Config - Specifies details of how containers in a multi-container endpoint are called.
- model
Name string - The name of the new model.
- primary
Container ModelContainer Definition - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
- Tag[]
- An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- vpc
Config ModelVpc Config - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
- containers
Sequence[Model
Container Definition Args] - Specifies the containers in the inference pipeline.
- enable_
network_ boolisolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- execution_
role_ strarn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- inference_
execution_ Modelconfig Inference Execution Config Args - Specifies details of how containers in a multi-container endpoint are called.
- model_
name str - The name of the new model.
- primary_
container ModelContainer Definition Args - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
-
Sequence[Tag
Args] - An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- vpc_
config ModelVpc Config Args - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
- containers List<Property Map>
- Specifies the containers in the inference pipeline.
- enable
Network BooleanIsolation - Isolates the model container. No inbound or outbound network calls can be made to or from the model container.
- execution
Role StringArn - The Amazon Resource Name (ARN) of the IAM role that you specified for the model.
- inference
Execution Property MapConfig - Specifies details of how containers in a multi-container endpoint are called.
- model
Name String - The name of the new model.
- primary
Container Property Map - The location of the primary docker image containing inference code, associated artifacts, and custom environment map that the inference code uses when the model is deployed for predictions.
- List<Property Map>
- An array of key-value pairs. You can use tags to categorize your AWS resources in different ways, for example, by purpose, owner, or environment. For more information, see Tagging AWS Resources.
- vpc
Config Property Map - A VpcConfig object that specifies the VPC that you want your model to connect to. Control access to and from your model container by configuring the VPC.
VpcConfigis used in hosting services and in batch transform. For more information, see Protect Endpoints by Using an Amazon Virtual Private Cloud and Protect Data in Batch Transform Jobs by Using an Amazon Virtual Private Cloud .
Outputs
All input properties are implicitly available as output properties. Additionally, the Model resource produces the following output properties:
Supporting Types
ModelAccessConfig, ModelAccessConfigArgs
The access configuration file to control access to the ML model. You can explicitly accept the model end-user license agreement (EULA) within the ModelAccessConfig.- Accept
Eula bool - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
- Accept
Eula bool - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
- accept
Eula Boolean - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
- accept
Eula boolean - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
- accept_
eula bool - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
- accept
Eula Boolean - Specifies agreement to the model end-user license agreement (EULA). The
AcceptEulavalue must be explicitly defined asTruein order to accept the EULA that this model requires. You are responsible for reviewing and complying with any applicable license terms and making sure they are acceptable for your use case before downloading or using a model.
ModelContainerDefinition, ModelContainerDefinitionArgs
Describes the container, as part of model definition.- Container
Hostname string This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- Environment object
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- Image string
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- Image
Config Pulumi.Aws Native. Sage Maker. Inputs. Model Image Config Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- Inference
Specification stringName - The inference specification name in the model package version.
- Mode
Pulumi.
Aws Native. Sage Maker. Model Container Definition Mode - Whether the container hosts a single model or multiple models.
- Model
Data Pulumi.Source Aws Native. Sage Maker. Inputs. Model Data Source Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- Model
Data stringUrl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- Model
Package stringName - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- Multi
Model Pulumi.Config Aws Native. Sage Maker. Inputs. Model Multi Model Config - Specifies additional configuration for multi-model endpoints.
- Container
Hostname string This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- Environment interface{}
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- Image string
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- Image
Config ModelImage Config Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- Inference
Specification stringName - The inference specification name in the model package version.
- Mode
Model
Container Definition Mode - Whether the container hosts a single model or multiple models.
- Model
Data ModelSource Data Source Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- Model
Data stringUrl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- Model
Package stringName - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- Multi
Model ModelConfig Multi Model Config - Specifies additional configuration for multi-model endpoints.
- container
Hostname String This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- environment Object
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- image String
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- image
Config ModelImage Config Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- inference
Specification StringName - The inference specification name in the model package version.
- mode
Model
Container Definition Mode - Whether the container hosts a single model or multiple models.
- model
Data ModelSource Data Source Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- model
Data StringUrl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- model
Package StringName - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- multi
Model ModelConfig Multi Model Config - Specifies additional configuration for multi-model endpoints.
- container
Hostname string This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- environment any
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- image string
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- image
Config ModelImage Config Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- inference
Specification stringName - The inference specification name in the model package version.
- mode
Model
Container Definition Mode - Whether the container hosts a single model or multiple models.
- model
Data ModelSource Data Source Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- model
Data stringUrl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- model
Package stringName - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- multi
Model ModelConfig Multi Model Config - Specifies additional configuration for multi-model endpoints.
- container_
hostname str This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- environment Any
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- image str
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- image_
config ModelImage Config Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- inference_
specification_ strname - The inference specification name in the model package version.
- mode
Model
Container Definition Mode - Whether the container hosts a single model or multiple models.
- model_
data_ Modelsource Data Source Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- model_
data_ strurl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- model_
package_ strname - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- multi_
model_ Modelconfig Multi Model Config - Specifies additional configuration for multi-model endpoints.
- container
Hostname String This parameter is ignored for models that contain only a PrimaryContainer.
When a ContainerDefinition is part of an inference pipeline, the value of the parameter uniquely identifies the container for the purposes of logging and metrics. For information, see Use Logs and Metrics to Monitor an Inference Pipeline. If you don't specify a value for this parameter for a ContainerDefinition that is part of an inference pipeline, a unique name is automatically assigned based on the position of the ContainerDefinition in the pipeline. If you specify a value for the ContainerHostName for any ContainerDefinition that is part of an inference pipeline, you must specify a value for the ContainerHostName parameter of every ContainerDefinition in that pipeline.
- environment Any
The environment variables to set in the Docker container. Don't include any sensitive data in your environment variables.
The maximum length of each key and value in the Environment map is 1024 bytes. The maximum length of all keys and values in the map, combined, is 32 KB. If you pass multiple containers to a CreateModel request, then the maximum length of all of their maps, combined, is also 32 KB.
- image String
- The path where inference code is stored. This can be either in Amazon EC2 Container Registry or in a Docker registry that is accessible from the same VPC that you configure for your endpoint. If you are using your own custom algorithm instead of an algorithm provided by SageMaker, the inference code must meet SageMaker requirements. SageMaker supports both registry/repository[:tag] and registry/repository[@digest] image path formats. For more information, see Using Your Own Algorithms with Amazon SageMaker.
- image
Config Property Map Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC). For information about storing containers in a private Docker registry, see Use a Private Docker Registry for Real-Time Inference Containers .
The model artifacts in an Amazon S3 bucket and the Docker image for inference container in Amazon EC2 Container Registry must be in the same region as the model or endpoint you are creating.
- inference
Specification StringName - The inference specification name in the model package version.
- mode
"Single
Model" | "Multi Model" - Whether the container hosts a single model or multiple models.
- model
Data Property MapSource Specifies the location of ML model data to deploy.
Currently you cannot use
ModelDataSourcein conjunction with SageMaker batch transform, SageMaker serverless endpoints, SageMaker multi-model endpoints, and SageMaker Marketplace.- model
Data StringUrl The S3 path where the model artifacts, which result from model training, are stored. This path must point to a single gzip compressed tar archive (.tar.gz suffix). The S3 path is required for SageMaker built-in algorithms, but not if you use your own algorithms. For more information on built-in algorithms, see Common Parameters.
If you provide a value for this parameter, SageMaker uses AWS Security Token Service to download model artifacts from the S3 path you provide. AWS STS is activated in your AWS account by default. If you previously deactivated AWS STS for a region, you need to reactivate AWS STS for that region. For more information, see Activating and Deactivating AWS STS in an AWS Region in the AWS Identity and Access Management User Guide
- model
Package StringName - The name or Amazon Resource Name (ARN) of the model package to use to create the model.
- multi
Model Property MapConfig - Specifies additional configuration for multi-model endpoints.
ModelContainerDefinitionMode, ModelContainerDefinitionModeArgs
- Single
Model SingleModel- Multi
Model MultiModel
- Model
Container Definition Mode Single Model SingleModel- Model
Container Definition Mode Multi Model MultiModel
- Single
Model SingleModel- Multi
Model MultiModel
- Single
Model SingleModel- Multi
Model MultiModel
- SINGLE_MODEL
SingleModel- MULTI_MODEL
MultiModel
- "Single
Model" SingleModel- "Multi
Model" MultiModel
ModelDataSource, ModelDataSourceArgs
Specifies the location of ML model data to deploy. If specified, you must specify one and only one of the available data sources.- S3Data
Source Pulumi.Aws Native. Sage Maker. Inputs. Model S3Data Source - Specifies the S3 location of ML model data to deploy.
- S3Data
Source ModelS3Data Source - Specifies the S3 location of ML model data to deploy.
- s3Data
Source ModelS3Data Source - Specifies the S3 location of ML model data to deploy.
- s3Data
Source ModelS3Data Source - Specifies the S3 location of ML model data to deploy.
- s3_
data_ Modelsource S3Data Source - Specifies the S3 location of ML model data to deploy.
- s3Data
Source Property Map - Specifies the S3 location of ML model data to deploy.
ModelHubAccessConfig, ModelHubAccessConfigArgs
Configuration information specifying which hub contents have accessible deployment options.- Hub
Content stringArn - The ARN of the hub content for which deployment access is allowed.
- Hub
Content stringArn - The ARN of the hub content for which deployment access is allowed.
- hub
Content StringArn - The ARN of the hub content for which deployment access is allowed.
- hub
Content stringArn - The ARN of the hub content for which deployment access is allowed.
- hub_
content_ strarn - The ARN of the hub content for which deployment access is allowed.
- hub
Content StringArn - The ARN of the hub content for which deployment access is allowed.
ModelImageConfig, ModelImageConfigArgs
Specifies whether the model container is in Amazon ECR or a private Docker registry accessible from your Amazon Virtual Private Cloud (VPC).- Repository
Access Pulumi.Mode Aws Native. Sage Maker. Model Image Config Repository Access Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- Repository
Auth Pulumi.Config Aws Native. Sage Maker. Inputs. Model Repository Auth Config - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
- Repository
Access ModelMode Image Config Repository Access Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- Repository
Auth ModelConfig Repository Auth Config - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
- repository
Access ModelMode Image Config Repository Access Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- repository
Auth ModelConfig Repository Auth Config - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
- repository
Access ModelMode Image Config Repository Access Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- repository
Auth ModelConfig Repository Auth Config - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
- repository_
access_ Modelmode Image Config Repository Access Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- repository_
auth_ Modelconfig Repository Auth Config - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
- repository
Access "Platform" | "Vpc"Mode - Set this to one of the following values: Platform - The model image is hosted in Amazon ECR. Vpc - The model image is hosted in a private Docker registry in your VPC.
- repository
Auth Property MapConfig - (Optional) Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified
Vpcas the value for theRepositoryAccessModefield, and the private Docker registry where the model image is hosted requires authentication.
ModelImageConfigRepositoryAccessMode, ModelImageConfigRepositoryAccessModeArgs
- Platform
Platform- Vpc
Vpc
- Model
Image Config Repository Access Mode Platform Platform- Model
Image Config Repository Access Mode Vpc Vpc
- Platform
Platform- Vpc
Vpc
- Platform
Platform- Vpc
Vpc
- PLATFORM
Platform- VPC
Vpc
- "Platform"
Platform- "Vpc"
Vpc
ModelInferenceExecutionConfig, ModelInferenceExecutionConfigArgs
Specifies details about how containers in a multi-container endpoint are run.- Mode
Pulumi.
Aws Native. Sage Maker. Model Inference Execution Config Mode - How containers in a multi-container are run.
- Mode
Model
Inference Execution Config Mode - How containers in a multi-container are run.
- mode
Model
Inference Execution Config Mode - How containers in a multi-container are run.
- mode
Model
Inference Execution Config Mode - How containers in a multi-container are run.
- mode
Model
Inference Execution Config Mode - How containers in a multi-container are run.
- mode "Serial" | "Direct"
- How containers in a multi-container are run.
ModelInferenceExecutionConfigMode, ModelInferenceExecutionConfigModeArgs
- Serial
Serial- Direct
Direct
- Model
Inference Execution Config Mode Serial Serial- Model
Inference Execution Config Mode Direct Direct
- Serial
Serial- Direct
Direct
- Serial
Serial- Direct
Direct
- SERIAL
Serial- DIRECT
Direct
- "Serial"
Serial- "Direct"
Direct
ModelMultiModelConfig, ModelMultiModelConfigArgs
Specifies additional configuration for multi-model endpoints.- Model
Cache Pulumi.Setting Aws Native. Sage Maker. Model Multi Model Config Model Cache Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
- Model
Cache ModelSetting Multi Model Config Model Cache Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
- model
Cache ModelSetting Multi Model Config Model Cache Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
- model
Cache ModelSetting Multi Model Config Model Cache Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
- model_
cache_ Modelsetting Multi Model Config Model Cache Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
- model
Cache "Enabled" | "Disabled"Setting - Whether to cache models for a multi-model endpoint. By default, multi-model endpoints cache models so that a model does not have to be loaded into memory each time it is invoked. Some use cases do not benefit from model caching. For example, if an endpoint hosts a large number of models that are each invoked infrequently, the endpoint might perform better if you disable model caching. To disable model caching, set the value of this parameter to
Disabled.
ModelMultiModelConfigModelCacheSetting, ModelMultiModelConfigModelCacheSettingArgs
- Enabled
Enabled- Disabled
Disabled
- Model
Multi Model Config Model Cache Setting Enabled Enabled- Model
Multi Model Config Model Cache Setting Disabled Disabled
- Enabled
Enabled- Disabled
Disabled
- Enabled
Enabled- Disabled
Disabled
- ENABLED
Enabled- DISABLED
Disabled
- "Enabled"
Enabled- "Disabled"
Disabled
ModelRepositoryAuthConfig, ModelRepositoryAuthConfigArgs
Specifies an authentication configuration for the private docker registry where your model image is hosted. Specify a value for this property only if you specified Vpc as the value for the RepositoryAccessMode field of the ImageConfig object that you passed to a call to CreateModel and the private Docker registry where the model image is hosted requires authentication.- Repository
Credentials stringProvider Arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
- Repository
Credentials stringProvider Arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
- repository
Credentials StringProvider Arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
- repository
Credentials stringProvider Arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
- repository_
credentials_ strprovider_ arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
- repository
Credentials StringProvider Arn - The Amazon Resource Name (ARN) of an AWS Lambda function that provides credentials to authenticate to the private Docker registry where your model image is hosted. For information about how to create an AWS Lambda function, see Create a Lambda function with the console in the AWS Lambda Developer Guide
ModelS3DataSource, ModelS3DataSourceArgs
Specifies the S3 location of ML model data to deploy.- Compression
Type Pulumi.Aws Native. Sage Maker. Model S3Data Source Compression Type - Specifies how the ML model data is prepared.
- S3Data
Type Pulumi.Aws Native. Sage Maker. Model S3Data Source S3Data Type - Specifies the type of ML model data to deploy.
- S3Uri string
- Specifies the S3 path of ML model data to deploy.
- Hub
Access Pulumi.Config Aws Native. Sage Maker. Inputs. Model Hub Access Config - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- Model
Access Pulumi.Config Aws Native. Sage Maker. Inputs. Model Access Config
- Compression
Type ModelS3Data Source Compression Type - Specifies how the ML model data is prepared.
- S3Data
Type ModelS3Data Source S3Data Type - Specifies the type of ML model data to deploy.
- S3Uri string
- Specifies the S3 path of ML model data to deploy.
- Hub
Access ModelConfig Hub Access Config - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- Model
Access ModelConfig Access Config
- compression
Type ModelS3Data Source Compression Type - Specifies how the ML model data is prepared.
- s3Data
Type ModelS3Data Source S3Data Type - Specifies the type of ML model data to deploy.
- s3Uri String
- Specifies the S3 path of ML model data to deploy.
- hub
Access ModelConfig Hub Access Config - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- model
Access ModelConfig Access Config
- compression
Type ModelS3Data Source Compression Type - Specifies how the ML model data is prepared.
- s3Data
Type ModelS3Data Source S3Data Type - Specifies the type of ML model data to deploy.
- s3Uri string
- Specifies the S3 path of ML model data to deploy.
- hub
Access ModelConfig Hub Access Config - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- model
Access ModelConfig Access Config
- compression_
type ModelS3Data Source Compression Type - Specifies how the ML model data is prepared.
- s3_
data_ Modeltype S3Data Source S3Data Type - Specifies the type of ML model data to deploy.
- s3_
uri str - Specifies the S3 path of ML model data to deploy.
- hub_
access_ Modelconfig Hub Access Config - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- model_
access_ Modelconfig Access Config
- compression
Type "None" | "Gzip" - Specifies how the ML model data is prepared.
- s3Data
Type "S3Prefix" | "S3Object" - Specifies the type of ML model data to deploy.
- s3Uri String
- Specifies the S3 path of ML model data to deploy.
- hub
Access Property MapConfig - The configuration for a private hub model reference that points to a SageMaker JumpStart public hub model.
- model
Access Property MapConfig
ModelS3DataSourceCompressionType, ModelS3DataSourceCompressionTypeArgs
- None
None- Gzip
Gzip
- Model
S3Data Source Compression Type None None- Model
S3Data Source Compression Type Gzip Gzip
- None
None- Gzip
Gzip
- None
None- Gzip
Gzip
- NONE
None- GZIP
Gzip
- "None"
None- "Gzip"
Gzip
ModelS3DataSourceS3DataType, ModelS3DataSourceS3DataTypeArgs
- S3Prefix
S3Prefix- S3Object
S3Object
- Model
S3Data Source S3Data Type S3Prefix S3Prefix- Model
S3Data Source S3Data Type S3Object S3Object
- S3Prefix
S3Prefix- S3Object
S3Object
- S3Prefix
S3Prefix- S3Object
S3Object
- S3_PREFIX
S3Prefix- S3_OBJECT
S3Object
- "S3Prefix"
S3Prefix- "S3Object"
S3Object
ModelVpcConfig, ModelVpcConfigArgs
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. For more information, see Give SageMaker Access to Resources in your Amazon VPC.- Security
Group List<string>Ids - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - Subnets List<string>
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
- Security
Group []stringIds - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - Subnets []string
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
- security
Group List<String>Ids - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - subnets List<String>
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
- security
Group string[]Ids - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - subnets string[]
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
- security_
group_ Sequence[str]ids - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - subnets Sequence[str]
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
- security
Group List<String>Ids - The VPC security group IDs, in the form
sg-xxxxxxxx. Specify the security groups for the VPC that is specified in theSubnetsfield. - subnets List<String>
- The ID of the subnets in the VPC to which you want to connect your training job or model. For information about the availability of specific instance types, see Supported Instance Types and Availability Zones.
Tag, TagArgs
A set of tags to apply to the resource.Package Details
- Repository
- AWS Native pulumi/pulumi-aws-native
- License
- Apache-2.0
We recommend new projects start with resources from the AWS provider.
published on Monday, Apr 20, 2026 by Pulumi
