A map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel.
If a DeployedModel's id is not listed in this map, then it receives no traffic.
The traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.
endpoint.etagstring
Used to perform consistent read-modify-write updates. If not set, a blind "overwrite" update happens.
endpoint.labelsmap (key: string, value: string)
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.
Output only. timestamp when this Endpoint was created.
Uses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples:"2014-10-02T15:01:23Z","2014-10-02T15:01:23.045123456Z"or"2014-10-02T15:01:23+05:30".
Output only. timestamp when this Endpoint was last updated.
Uses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than "Z" are also accepted. Examples:"2014-10-02T15:01:23Z","2014-10-02T15:01:23.045123456Z"or"2014-10-02T15:01:23+05:30".
Output only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled byJobService.CreateModelDeploymentMonitoringJob. Format:projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{modelDeploymentMonitoringJob}
Configures the request-response logging for online prediction.
endpoint.dedicatedEndpointEnabledboolean
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.
endpoint.dedicatedEndpointDnsstring
Output only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled 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://{endpointId}.{region}-{uid}.prediction.vertexai.goog.
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.
Response body
If successful, the response body contains an instance ofOperation.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-01 UTC."],[],[],null,["# Method: endpoints.update\n\n**Full name**: projects.locations.endpoints.update\n\nUpdates an Endpoint with a long running operation. \n\n### Endpoint\n\npost `https:``/``/{service-endpoint}``/v1beta1``/{endpoint.name}:update` \nWhere `{service-endpoint}` is one of the [supported service endpoints](/vertex-ai/docs/reference/rest#rest_endpoints).\n\n### Path parameters\n\n`endpoint.name` `string` \nOutput only. The resource name of the Endpoint.\n\n### Request body\n\nThe request body contains data with the following structure:\nFields `endpoint.displayName` `string` \nRequired. The display name of the Endpoint. The name can be up to 128 characters long and can consist of any UTF-8 characters.\n`endpoint.description` `string` \nThe description of the Endpoint.\n`endpoint.deployedModels[]` `object (`[DeployedModel](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#DeployedModel)`)` \nOutput only. The models deployed in this Endpoint. To add or remove DeployedModels use [EndpointService.DeployModel](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints/deployModel#google.cloud.aiplatform.v1beta1.EndpointService.DeployModel) and [EndpointService.UndeployModel](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints/undeployModel#google.cloud.aiplatform.v1beta1.EndpointService.UndeployModel) respectively.\n`endpoint.trafficSplit` `map (key: string, value: integer)` \nA map from a DeployedModel's id to the percentage of this Endpoint's traffic that should be forwarded to that DeployedModel.\n\nIf a DeployedModel's id is not listed in this map, then it receives no traffic.\n\nThe traffic percentage values must add up to 100, or map must be empty if the Endpoint is to not accept any traffic at a moment.\n`endpoint.etag` `string` \nUsed to perform consistent read-modify-write updates. If not set, a blind \"overwrite\" update happens.\n`endpoint.labels` `map (key: string, value: string)` \nThe labels with user-defined metadata to organize your endpoints.\n\nlabel 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.\n\nSee \u003chttps://goo.gl/xmQnxf\u003e for more information and examples of labels.\n`endpoint.createTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this Endpoint was created.\n\nUses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than \"Z\" are also accepted. Examples: `\"2014-10-02T15:01:23Z\"`, `\"2014-10-02T15:01:23.045123456Z\"` or `\"2014-10-02T15:01:23+05:30\"`.\n`endpoint.updateTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this Endpoint was last updated.\n\nUses RFC 3339, where generated output will always be Z-normalized and uses 0, 3, 6 or 9 fractional digits. Offsets other than \"Z\" are also accepted. Examples: `\"2014-10-02T15:01:23Z\"`, `\"2014-10-02T15:01:23.045123456Z\"` or `\"2014-10-02T15:01:23+05:30\"`.\n`endpoint.encryptionSpec` `object (`[EncryptionSpec](/vertex-ai/docs/reference/rest/v1beta1/EncryptionSpec)`)` \nCustomer-managed encryption key spec for an Endpoint. If set, this Endpoint and all sub-resources of this Endpoint will be secured by this key.\n`endpoint.network` `string` \nOptional. The full name of the Google Compute Engine [network](https://cloud.google.com//compute/docs/networks-and-firewalls#networks) to which the Endpoint should be peered.\n\nPrivate services access must already be configured for the network. If left unspecified, the Endpoint is not peered with any network.\n\nOnly one of the fields, [network](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.network) or [enablePrivateServiceConnect](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.enable_private_service_connect), can be set.\n\n[Format](https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert): `projects/{project}/global/networks/{network}`. Where `{project}` is a project number, as in `12345`, and `{network}` is network name.\n`endpoint.enablePrivateServiceConnect` \n**(deprecated)** `boolean` \nDeprecated: If true, expose the Endpoint via private service connect.\n\nOnly one of the fields, [network](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.network) or [enablePrivateServiceConnect](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.enable_private_service_connect), can be set.\n`endpoint.privateServiceConnectConfig` `object (`[PrivateServiceConnectConfig](/vertex-ai/docs/reference/rest/v1beta1/PrivateServiceConnectConfig)`)` \nOptional. Configuration for private service connect.\n\n[network](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.network) and [privateServiceConnectConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#Endpoint.FIELDS.private_service_connect_config) are mutually exclusive.\n`endpoint.modelDeploymentMonitoringJob` `string` \nOutput only. Resource name of the Model Monitoring job associated with this Endpoint if monitoring is enabled by [JobService.CreateModelDeploymentMonitoringJob](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelDeploymentMonitoringJobs/create#google.cloud.aiplatform.v1beta1.JobService.CreateModelDeploymentMonitoringJob). Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{modelDeploymentMonitoringJob}`\n`endpoint.predictRequestResponseLoggingConfig` `object (`[PredictRequestResponseLoggingConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#PredictRequestResponseLoggingConfig)`)` \nConfigures the request-response logging for online prediction.\n`endpoint.dedicatedEndpointEnabled` `boolean` \nIf 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.\n`endpoint.dedicatedEndpointDns` `string` \nOutput only. DNS of the dedicated endpoint. Will only be populated if dedicatedEndpointEnabled 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://{endpointId}.{region}-{uid}.prediction.vertexai.goog`.\n`endpoint.clientConnectionConfig` `object (`[ClientConnectionConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#ClientConnectionConfig)`)` \nConfigurations that are applied to the endpoint for online prediction.\n`endpoint.satisfiesPzs` `boolean` \nOutput only. reserved for future use.\n`endpoint.satisfiesPzi` `boolean` \nOutput only. reserved for future use.\n`endpoint.genAiAdvancedFeaturesConfig` `object (`[GenAiAdvancedFeaturesConfig](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints#GenAiAdvancedFeaturesConfig)`)` \nOptional. 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. \n\n### Response body\n\nIf successful, the response body contains an instance of [Operation](/vertex-ai/docs/reference/rest/Shared.Types/ListOperationsResponse#Operation)."]]
