InvokeEndpointCommand

Suggest an Edit

After you deploy a model into production using Amazon SageMaker hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint.

For an overview of Amazon SageMaker, see How It Works .

Amazon SageMaker strips all POST headers except those supported by the API. Amazon SageMaker might add additional headers. You should not rely on the behavior of headers outside those enumerated in the request syntax.

Calls to InvokeEndpoint are authenticated by using Amazon Web Services Signature Version 4. For information, see Authenticating Requests (Amazon Web Services Signature Version 4)  in the Amazon S3 API Reference.

A customer's model containers must respond to requests within 60 seconds. The model itself can have a maximum processing time of 60 seconds before responding to invocations. If your model is going to take 50-60 seconds of processing time, the SDK socket timeout should be set to be 70 seconds.

Endpoints are scoped to an individual account, and are not public. The URL does not contain the account ID, but Amazon SageMaker determines the account ID from the authentication token that is supplied by the caller.

Example Syntax

Use a bare-bones client and the command you need to make an API call.

import { SageMakerRuntimeClient, InvokeEndpointCommand } from "@aws-sdk/client-sagemaker-runtime"; // ES Modules import
// const { SageMakerRuntimeClient, InvokeEndpointCommand } = require("@aws-sdk/client-sagemaker-runtime"); // CommonJS import
const client = new SageMakerRuntimeClient(config);
const input = { // InvokeEndpointInput
  EndpointName: "STRING_VALUE", // required
  Body: new Uint8Array(), // e.g. Buffer.from("") or new TextEncoder().encode("")   // required
  ContentType: "STRING_VALUE",
  Accept: "STRING_VALUE",
  CustomAttributes: "STRING_VALUE",
  TargetModel: "STRING_VALUE",
  TargetVariant: "STRING_VALUE",
  TargetContainerHostname: "STRING_VALUE",
  InferenceId: "STRING_VALUE",
  EnableExplanations: "STRING_VALUE",
  InferenceComponentName: "STRING_VALUE",
  SessionId: "STRING_VALUE",
};
const command = new InvokeEndpointCommand(input);
const response = await client.send(command);
// { // InvokeEndpointOutput
//   Body: new Uint8Array(), // required
//   ContentType: "STRING_VALUE",
//   InvokedProductionVariant: "STRING_VALUE",
//   CustomAttributes: "STRING_VALUE",
//   NewSessionId: "STRING_VALUE",
//   ClosedSessionId: "STRING_VALUE",
// };

InvokeEndpointCommand Input

See InvokeEndpointCommandInput for more details
InvokeEndpointCommandInput extends InvokeEndpointCommandInputType

InvokeEndpointCommand Output

See InvokeEndpointCommandOutput for details

Parameter
Type
Description
$metadata
Required
ResponseMetadata
Metadata pertaining to this request.

Throws

Name
Fault
Details
InternalDependencyException
server

Your request caused an exception with an internal dependency. Contact customer support.

InternalFailure
server

An internal failure occurred.

ModelError
client

Model (owned by the customer in the container) returned 4xx or 5xx error code.

ModelNotReadyException
client

Either a serverless endpoint variant's resources are still being provisioned, or a multi-model endpoint is still downloading or loading the target model. Wait and try your request again.

ServiceUnavailable
server

The service is unavailable. Try your call again.

ValidationError
client

Inspect your request and try again.

SageMakerRuntimeServiceException
Base exception class for all service exceptions from SageMakerRuntime service.