Sign in

v1

latestOpenAPI 3.0.0Apache 2.0 License2026-07-1484423422.2 KB

Creates a model-specific endpoint for synchronous inference for a previously trained custom model For information about endpoints, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/manage-endpoints.html">Managing endpoints</a>.

post/#X-Amz-Target=Comprehend_20171127.CreateEndpoint

Headers

X-Amz-Target'Comprehend_20171127.CreateEndpoint' required

Request body

EndpointNamestring required

This is the descriptive suffix that becomes part of the <code>EndpointArn</code> used for all subsequent requests to this resource.

ModelArnstring

The Amazon Resource Number (ARN) of the model to which the endpoint will be attached.

DesiredInferenceUnitsinteger required

The desired number of inference units to be used by the model using this endpoint. Each inference unit represents of a throughput of 100 characters per second.

ClientRequestTokenstring

An idempotency token provided by the customer. If this token matches a previous endpoint creation request, Amazon Comprehend will not return a <code>ResourceInUseException</code>.

DataAccessRoleArnstring

The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to trained custom models encrypted with a customer managed key (ModelKmsKeyId).

FlywheelArnstring

The Amazon Resource Number (ARN) of the flywheel to which the endpoint will be attached.

Response

Success

EndpointArnstring

The Amazon Resource Number (ARN) of the endpoint being created.

ModelArnstring

The Amazon Resource Number (ARN) of the model to which the endpoint is attached.