sagemaker:InvokeEndpoint
Literal appearances in AWS managed IAM policies. Statements that use wildcards (for example s3:*) are not counted here. This is not an IAM authorization simulation.
Policies (any)
12
Allow (Action)
12
Deny (Action)
0
NotAction
1
Index generated 4/7/2026, 3:29:24 AM. 559 policies include at least one wildcard action string (any service).
Action reference
SAR-style (unofficial)Service: Amazon SageMaker
Access level
ReadDescription
Grants permission to invoke an endpoint. 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
Resource types
- endpoint*
- inference-component
Allow (Action)
- AmazonBedrockFullAccess
- AmazonBedrockMarketplaceAccess
- AmazonCognitoUnAuthedIdentitiesSessionPolicy
- AmazonRedshiftAllCommandsFullAccess
- AmazonSageMakerCanvasDirectDeployAccess
- AmazonSageMakerCanvasFullAccess
- AmazonSageMakerPartnerServiceCatalogProductsApiGatewayServiceRolePolicy
- AmazonSageMakerServiceCatalogProductsCloudformationServiceRolePolicy
- AmazonSageMakerServiceCatalogProductsCodeBuildServiceRolePolicy
- AmazonSageMakerServiceCatalogProductsLambdaServiceRolePolicy
- SageMakerStudioProjectRoleMachineLearningPolicy
- SageMakerStudioProjectUserRolePermissionsBoundary
Deny (Action)
Thanks to Ian McKay for iam-dataset (MIT), structured data derived from the AWS Service Authorization Reference. Not maintained by AWS and not guaranteed current. IAMTrail's managed policy archive is separate.
Definitions bundle generated 4/7/2026, 3:29:24 AM