Welcome
Amazon SageMaker Service
Provides APIs for creating and managing SageMaker resources.
Other Resources:
Amazon SageMaker Runtime
The Amazon SageMaker AI runtime API.
Amazon Sagemaker Edge Manager
SageMaker Edge Manager dataplane service for communicating with active agents.
Amazon SageMaker Feature Store Runtime
Contains all data plane API operations and data types for the Amazon SageMaker Feature Store. Use this API to put, delete, and retrieve (get) features from a feature store.
Use the following operations to configure your OnlineStore and
OfflineStore features, and to create and manage feature groups:
Amazon SageMaker geospatial capabilities
Provides APIs for creating and managing SageMaker geospatial resources.
Amazon SageMaker Inference Router Runtime
Amazon SageMaker Inference Router Runtime is the runtime API for Amazon SageMaker AI inference routers. An inference router sends each request that you make to one of the destinations of a routing target. A destination is a SageMaker AI endpoint or inference component, in your account or in another account, in the router's AWS Region or in another Region in the same AWS partition. The router chooses a healthy destination with capacity, and prefers destinations in its own Region.
Use InvokeInferenceRouter to get an inference in real time. Use InvokeInferenceRouterAsync to submit a request whose input and response are stored in Amazon S3.
The inference router runtime endpoint supports HTTP/1.1 only. HTTP/2 isn't supported. If you use the AWS SDKs or the AWS CLI, you don't need to change anything.
Amazon SageMaker Metrics Service
Contains all data plane API operations and data types for Amazon SageMaker Metrics. Use these APIs to put and retrieve (get) features related to your training run.
Amazon SageMaker Job Runtime Service
Amazon SageMaker Job Runtime provides APIs that enable communication between your agent and the policy model during multi-turn reinforcement learning jobs. These APIs support inference requests to the policy model, rollout lifecycle management, and reward submission.
Amazon SageMaker Training Session Runtime
Amazon SageMaker Training Session Runtime provides APIs for executing training operations and sampling operations against a running training session. Use these APIs to submit asynchronous training steps (such as forward-backward passes, optimizer steps, and checkpoint saves) and to generate text samples from the model being trained.