Output only. DNS of the dedicated endpoint. Will only be populated if
dedicated_endpoint_enabled is true. Depending on the features enabled, uid
might be a random number or a string. For example, if fast_tryout is
enabled, uid will be fasttryout. Format:
https://{endpoint_id}.{region}-{uid}.prediction.vertexai.goog.
public bool DedicatedEndpointEnabled { get; set; }
If true, the endpoint will be exposed through a dedicated
DNS [Endpoint.dedicated_endpoint_dns]. Your request to the dedicated DNS
will be isolated from other users' traffic and will have better performance
and reliability.
Note: Once you enabled dedicated endpoint, you won't be able to send
request to the shared DNS {region}-aiplatform.googleapis.com. The
limitation will be removed soon.
public RepeatedField<DeployedModel> DeployedModels { get; }
Output only. The models deployed in this Endpoint.
To add or remove DeployedModels use
[EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel]
and
[EndpointService.UndeployModel][google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel]
respectively.
Deprecated: If true, expose the Endpoint via private service connect.
Only one of the fields,
[network][google.cloud.aiplatform.v1beta1.Endpoint.network] or
[enable_private_service_connect][google.cloud.aiplatform.v1beta1.Endpoint.enable_private_service_connect],
can be set.
public GenAiAdvancedFeaturesConfig GenAiAdvancedFeaturesConfig { get; set; }
Optional. Configuration for GenAiAdvancedFeatures. If the endpoint is
serving GenAI models, advanced features like native RAG integration can be
configured. Currently, only Model Garden models are supported.
The labels with user-defined metadata to organize your Endpoints.
Label keys and values can be no longer than 64 characters
(Unicode codepoints), can only contain lowercase letters, numeric
characters, underscores and dashes. International characters are allowed.
public string ModelDeploymentMonitoringJob { get; set; }
Output only. Resource name of the Model Monitoring job associated with this
Endpoint if monitoring is enabled by
[JobService.CreateModelDeploymentMonitoringJob][google.cloud.aiplatform.v1beta1.JobService.CreateModelDeploymentMonitoringJob].
Format:
projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}
Optional. The full name of the Google Compute Engine
network
to which the Endpoint should be peered.
Private services access must already be configured for the network. If left
unspecified, the Endpoint is not peered with any network.
Only one of the fields,
[network][google.cloud.aiplatform.v1beta1.Endpoint.network] or
[enable_private_service_connect][google.cloud.aiplatform.v1beta1.Endpoint.enable_private_service_connect],
can be set.
Format:
projects/{project}/global/networks/{network}.
Where {project} is a project number, as in 12345, and {network} is
network name.
public PrivateServiceConnectConfig PrivateServiceConnectConfig { get; set; }
Optional. Configuration for private service connect.
[network][google.cloud.aiplatform.v1beta1.Endpoint.network] and
[private_service_connect_config][google.cloud.aiplatform.v1beta1.Endpoint.private_service_connect_config]
are mutually exclusive.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThe \u003ccode\u003eEndpoint\u003c/code\u003e class in the Vertex AI v1beta1 API is used for deploying models and obtaining predictions and explanations.\u003c/p\u003e\n"],["\u003cp\u003eEndpoints can be configured with options for dedicated DNS, private service connect, and network peering to enhance performance and security.\u003c/p\u003e\n"],["\u003cp\u003eDeployed models within an Endpoint can have their traffic split managed, directing a percentage of traffic to each model.\u003c/p\u003e\n"],["\u003cp\u003eThe class includes properties for managing metadata like display name, description, labels, and timestamps for creation and updates.\u003c/p\u003e\n"],["\u003cp\u003eEndpoints support customer-managed encryption and can be monitored with model deployment monitoring jobs, including features for request-response logging.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class Endpoint (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.Endpoint) \n\n public sealed class Endpoint : IMessage\u003cEndpoint\u003e, IEquatable\u003cEndpoint\u003e, IDeepCloneable\u003cEndpoint\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class Endpoint.\n\nModels are deployed into it, and afterwards Endpoint is called to obtain\npredictions and explanations. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e Endpoint \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[Endpoint](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[Endpoint](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[Endpoint](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### Endpoint()\n\n public Endpoint()\n\n### Endpoint(Endpoint)\n\n public Endpoint(Endpoint other)\n\nProperties\n----------\n\n### ClientConnectionConfig\n\n public ClientConnectionConfig ClientConnectionConfig { get; set; }\n\nConfigurations that are applied to the endpoint for online prediction.\n\n### CreateTime\n\n public Timestamp CreateTime { get; set; }\n\nOutput only. Timestamp when this Endpoint was created.\n\n### DedicatedEndpointDns\n\n public string DedicatedEndpointDns { get; set; }\n\nOutput only. DNS of the dedicated endpoint. Will only be populated if\ndedicated_endpoint_enabled is true. Depending on the features enabled, uid\nmight be a random number or a string. For example, if fast_tryout is\nenabled, uid will be fasttryout. Format:\n`https://{endpoint_id}.{region}-{uid}.prediction.vertexai.goog`.\n\n### DedicatedEndpointEnabled\n\n public bool DedicatedEndpointEnabled { get; set; }\n\nIf true, the endpoint will be exposed through a dedicated\nDNS \\[Endpoint.dedicated_endpoint_dns\\]. Your request to the dedicated DNS\nwill be isolated from other users' traffic and will have better performance\nand reliability.\nNote: Once you enabled dedicated endpoint, you won't be able to send\nrequest to the shared DNS {region}-aiplatform.googleapis.com. The\nlimitation will be removed soon.\n\n### DeployedModels\n\n public RepeatedField\u003cDeployedModel\u003e DeployedModels { get; }\n\nOutput only. The models deployed in this Endpoint.\nTo add or remove DeployedModels use\n\\[EndpointService.DeployModel\\]\\[google.cloud.aiplatform.v1beta1.EndpointService.DeployModel\\]\nand\n\\[EndpointService.UndeployModel\\]\\[google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel\\]\nrespectively.\n\n### Description\n\n public string Description { get; set; }\n\nThe description of the Endpoint.\n\n### DisplayName\n\n public string DisplayName { get; set; }\n\nRequired. The display name of the Endpoint.\nThe name can be up to 128 characters long and can consist of any UTF-8\ncharacters.\n\n### EnablePrivateServiceConnect\n\n [Obsolete]\n public bool EnablePrivateServiceConnect { get; set; }\n\nDeprecated: If true, expose the Endpoint via private service connect.\n\nOnly one of the fields,\n\\[network\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.network\\] or\n\\[enable_private_service_connect\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.enable_private_service_connect\\],\ncan be set.\n\n### EncryptionSpec\n\n public EncryptionSpec EncryptionSpec { get; set; }\n\nCustomer-managed encryption key spec for an Endpoint. If set, this\nEndpoint and all sub-resources of this Endpoint will be secured by\nthis key.\n\n### EndpointName\n\n public EndpointName EndpointName { get; set; }\n\n[EndpointName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.EndpointName)-typed view over the [Name](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint#Google_Cloud_AIPlatform_V1Beta1_Endpoint_Name) resource name property.\n\n### Etag\n\n public string Etag { get; set; }\n\nUsed to perform consistent read-modify-write updates. If not set, a blind\n\"overwrite\" update happens.\n\n### GenAiAdvancedFeaturesConfig\n\n public GenAiAdvancedFeaturesConfig GenAiAdvancedFeaturesConfig { get; set; }\n\nOptional. Configuration for GenAiAdvancedFeatures. If the endpoint is\nserving GenAI models, advanced features like native RAG integration can be\nconfigured. Currently, only Model Garden models are supported.\n\n### Labels\n\n public MapField\u003cstring, string\u003e Labels { get; }\n\nThe labels with user-defined metadata to organize your Endpoints.\n\nLabel keys and values can be no longer than 64 characters\n(Unicode codepoints), can only contain lowercase letters, numeric\ncharacters, underscores and dashes. International characters are allowed.\n\nSee \u003chttps://goo.gl/xmQnxf\u003e for more information and examples of labels.\n\n### ModelDeploymentMonitoringJob\n\n public string ModelDeploymentMonitoringJob { get; set; }\n\nOutput only. Resource name of the Model Monitoring job associated with this\nEndpoint if monitoring is enabled by\n\\[JobService.CreateModelDeploymentMonitoringJob\\]\\[google.cloud.aiplatform.v1beta1.JobService.CreateModelDeploymentMonitoringJob\\].\nFormat:\n`projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{model_deployment_monitoring_job}`\n\n### ModelDeploymentMonitoringJobAsModelDeploymentMonitoringJobName\n\n public ModelDeploymentMonitoringJobName ModelDeploymentMonitoringJobAsModelDeploymentMonitoringJobName { get; set; }\n\n[ModelDeploymentMonitoringJobName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ModelDeploymentMonitoringJobName)-typed view over the\n[ModelDeploymentMonitoringJob](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint#Google_Cloud_AIPlatform_V1Beta1_Endpoint_ModelDeploymentMonitoringJob) resource name property.\n\n### Name\n\n public string Name { get; set; }\n\nOutput only. The resource name of the Endpoint.\n\n### Network\n\n public string Network { get; set; }\n\nOptional. The full name of the Google Compute Engine\n[network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks)\nto which the Endpoint should be peered.\n\nPrivate services access must already be configured for the network. If left\nunspecified, the Endpoint is not peered with any network.\n\nOnly one of the fields,\n\\[network\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.network\\] or\n\\[enable_private_service_connect\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.enable_private_service_connect\\],\ncan be set.\n\n[Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert):\n`projects/{project}/global/networks/{network}`.\nWhere `{project}` is a project number, as in `12345`, and `{network}` is\nnetwork name.\n\n### NetworkAsNetworkName\n\n public NetworkName NetworkAsNetworkName { get; set; }\n\n[NetworkName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.NetworkName)-typed view over the [Network](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.Endpoint#Google_Cloud_AIPlatform_V1Beta1_Endpoint_Network) resource name property.\n\n### PredictRequestResponseLoggingConfig\n\n public PredictRequestResponseLoggingConfig PredictRequestResponseLoggingConfig { get; set; }\n\nConfigures the request-response logging for online prediction.\n\n### PrivateServiceConnectConfig\n\n public PrivateServiceConnectConfig PrivateServiceConnectConfig { get; set; }\n\nOptional. Configuration for private service connect.\n\n\\[network\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.network\\] and\n\\[private_service_connect_config\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.private_service_connect_config\\]\nare mutually exclusive.\n\n### SatisfiesPzi\n\n public bool SatisfiesPzi { get; set; }\n\nOutput only. Reserved for future use.\n\n### SatisfiesPzs\n\n public bool SatisfiesPzs { get; set; }\n\nOutput only. Reserved for future use.\n\n### TrafficSplit\n\n public MapField\u003cstring, int\u003e TrafficSplit { get; }\n\nA map from a DeployedModel's ID to the percentage of this Endpoint's\ntraffic that should be forwarded to that DeployedModel.\n\nIf a DeployedModel's ID is not listed in this map, then it receives no\ntraffic.\n\nThe traffic percentage values must add up to 100, or map must be empty if\nthe Endpoint is to not accept any traffic at a moment.\n\n### UpdateTime\n\n public Timestamp UpdateTime { get; set; }\n\nOutput only. Timestamp when this Endpoint was last updated."]]
