DescribeEndpoint
Returns the description of an endpoint.
Request Syntax
{
"EndpointName": "string"
}
Request Parameters
For information about the parameters that are common to all actions, see Common Parameters.
The request accepts the following data in JSON format.
- EndpointName
-
The name of the endpoint.
Type: String
Length Constraints: Minimum length of 0. Maximum length of 63.
Pattern:
[a-zA-Z0-9](-*[a-zA-Z0-9]){0,62}Required: Yes
Response Syntax
{
"AsyncInferenceConfig": {
"ClientConfig": {
"MaxConcurrentInvocationsPerInstance": number
},
"OutputConfig": {
"KmsKeyId": "string",
"NotificationConfig": {
"ErrorTopic": "string",
"IncludeInferenceResponseIn": [ "string" ],
"SuccessTopic": "string"
},
"S3FailurePath": "string",
"S3OutputPath": "string"
}
},
"DataCaptureConfig": {
"CaptureStatus": "string",
"CurrentSamplingPercentage": number,
"DestinationS3Uri": "string",
"EnableCapture": boolean,
"KmsKeyId": "string"
},
"EndpointArn": "string",
"EndpointConfigName": "string",
"EndpointName": "string",
"EndpointStatus": "string",
"ExplainerConfig": {
"ClarifyExplainerConfig": {
"EnableExplanations": "string",
"InferenceConfig": {
"ContentTemplate": "string",
"FeatureHeaders": [ "string" ],
"FeaturesAttribute": "string",
"FeatureTypes": [ "string" ],
"LabelAttribute": "string",
"LabelHeaders": [ "string" ],
"LabelIndex": number,
"MaxPayloadInMB": number,
"MaxRecordCount": number,
"ProbabilityAttribute": "string",
"ProbabilityIndex": number
},
"ShapConfig": {
"NumberOfSamples": number,
"Seed": number,
"ShapBaselineConfig": {
"MimeType": "string",
"ShapBaseline": "string",
"ShapBaselineUri": "string"
},
"TextConfig": {
"Granularity": "string",
"Language": "string"
},
"UseLogit": boolean
}
}
},
"FailureReason": "string",
"LastDeploymentConfig": {
"AutoRollbackConfiguration": {
"Alarms": [
{
"AlarmName": "string"
}
]
},
"BlueGreenUpdatePolicy": {
"MaximumExecutionTimeoutInSeconds": number,
"TerminationWaitInSeconds": number,
"TrafficRoutingConfiguration": {
"CanarySize": {
"Type": "string",
"Value": number
},
"LinearStepSize": {
"Type": "string",
"Value": number
},
"Type": "string",
"WaitIntervalInSeconds": number
}
},
"RollingUpdatePolicy": {
"MaximumBatchSize": {
"Type": "string",
"Value": number
},
"MaximumExecutionTimeoutInSeconds": number,
"RollbackMaximumBatchSize": {
"Type": "string",
"Value": number
},
"WaitIntervalInSeconds": number
}
},
"MetricsConfig": {
"EnableDetailedObservability": boolean,
"EnableEnhancedMetrics": boolean,
"MetricPublishFrequencyInSeconds": number
},
"PendingDeploymentSummary": {
"EndpointConfigName": "string",
"ProductionVariants": [
{
"AcceleratorType": "string",
"CurrentInstanceCount": number,
"CurrentServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"CurrentWeight": number,
"DeployedImages": [
{
"ResolvedImage": "string",
"SpecifiedImage": "string"
}
],
"DesiredInstanceCount": number,
"DesiredServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"DesiredWeight": number,
"InstancePools": [
{
"CurrentInstanceCount": number,
"InstanceType": "string"
}
],
"InstanceType": "string",
"ManagedInstanceScaling": {
"MaxInstanceCount": number,
"MinInstanceCount": number,
"ScaleInPolicy": {
"CooldownInMinutes": number,
"MaximumStepSize": number,
"Strategy": "string"
},
"Status": "string"
},
"RoutingConfig": {
"PrefixAwareRoutingConfig": {
"ConcurrencyThreshold": number,
"PrefixLength": number
},
"RoutingStrategy": "string"
},
"VariantName": "string",
"VariantStatus": [
{
"Status": "string",
"StatusMessage": "string"
}
]
}
],
"ShadowProductionVariants": [
{
"AcceleratorType": "string",
"CurrentInstanceCount": number,
"CurrentServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"CurrentWeight": number,
"DeployedImages": [
{
"ResolvedImage": "string",
"SpecifiedImage": "string"
}
],
"DesiredInstanceCount": number,
"DesiredServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"DesiredWeight": number,
"InstancePools": [
{
"CurrentInstanceCount": number,
"InstanceType": "string"
}
],
"InstanceType": "string",
"ManagedInstanceScaling": {
"MaxInstanceCount": number,
"MinInstanceCount": number,
"ScaleInPolicy": {
"CooldownInMinutes": number,
"MaximumStepSize": number,
"Strategy": "string"
},
"Status": "string"
},
"RoutingConfig": {
"PrefixAwareRoutingConfig": {
"ConcurrencyThreshold": number,
"PrefixLength": number
},
"RoutingStrategy": "string"
},
"VariantName": "string",
"VariantStatus": [
{
"Status": "string",
"StatusMessage": "string"
}
]
}
]
},
"ProductionVariants": [
{
"CapacityReservationConfig": {
"AvailableInstanceCount": number,
"CapacityReservationPreference": "string",
"Ec2CapacityReservations": [
{
"AvailableInstanceCount": number,
"Ec2CapacityReservationId": "string",
"TotalInstanceCount": number,
"UsedByCurrentEndpoint": number
}
],
"MlReservationArn": "string",
"TotalInstanceCount": number,
"UsedByCurrentEndpoint": number
},
"CurrentInstanceCount": number,
"CurrentServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"CurrentWeight": number,
"DeployedImages": [
{
"ResolvedImage": "string",
"SpecifiedImage": "string"
}
],
"DesiredInstanceCount": number,
"DesiredServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"DesiredWeight": number,
"InstancePools": [
{
"CurrentInstanceCount": number,
"InstanceType": "string"
}
],
"ManagedInstanceScaling": {
"MaxInstanceCount": number,
"MinInstanceCount": number,
"ScaleInPolicy": {
"CooldownInMinutes": number,
"MaximumStepSize": number,
"Strategy": "string"
},
"Status": "string"
},
"RoutingConfig": {
"PrefixAwareRoutingConfig": {
"ConcurrencyThreshold": number,
"PrefixLength": number
},
"RoutingStrategy": "string"
},
"VariantName": "string",
"VariantStatus": [
{
"Status": "string",
"StatusMessage": "string"
}
]
}
],
"ShadowProductionVariants": [
{
"CapacityReservationConfig": {
"AvailableInstanceCount": number,
"CapacityReservationPreference": "string",
"Ec2CapacityReservations": [
{
"AvailableInstanceCount": number,
"Ec2CapacityReservationId": "string",
"TotalInstanceCount": number,
"UsedByCurrentEndpoint": number
}
],
"MlReservationArn": "string",
"TotalInstanceCount": number,
"UsedByCurrentEndpoint": number
},
"CurrentInstanceCount": number,
"CurrentServerlessConfig": {
"MaxConcurrency": number,
"MemorySizeInMB": number,
"ProvisionedConcurrency": number
},
"CurrentWeight": number,
"DeployedImages": [
{
"ResolvedImage": "