If true, deploy the model without explainable feature, regardless the
existence of
[Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec]
or
[explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec].
If true, online prediction access logs are sent to Cloud
Logging.
These logs are like standard server access logs, containing
information like timestamp and latency for each prediction request.
Note that logs may incur a cost, especially if your project
receives prediction requests at a high queries per second rate (QPS).
Estimate your costs before enabling this option.
public ExplanationSpec ExplanationSpec { get; set; }
Explanation configuration for this DeployedModel.
When deploying a Model using
[EndpointService.DeployModel][google.cloud.aiplatform.v1beta1.EndpointService.DeployModel],
this value overrides the value of
[Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec].
All fields of
[explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec]
are optional in the request. If a field of
[explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec]
is not populated, the value of the same field of
[Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec]
is inherited. If the corresponding
[Model.explanation_spec][google.cloud.aiplatform.v1beta1.Model.explanation_spec]
is not populated, all fields of the
[explanation_spec][google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec]
will be used for the explanation configuration.
The resource name of the Model that this is the deployment of. Note that
the Model may be in a different location than the DeployedModel's Endpoint.
The resource name may contain version id or version alias to specify the
version.
Example: projects/{project}/locations/{location}/models/{model}@2
or
projects/{project}/locations/{location}/models/{model}@golden
if no version is specified, the default version will be deployed.
public PrivateEndpoints PrivateEndpoints { get; set; }
Output only. Provide paths for users to send predict/explain/health
requests directly to the deployed model services running on Cloud via
private services access. This field is populated if
[network][google.cloud.aiplatform.v1beta1.Endpoint.network] is configured.
The service account that the DeployedModel's container runs as. Specify the
email address of the service account. If this service account is not
specified, the container runs as a service account that doesn't have access
to the resource project.
Users deploying the Model must have the iam.serviceAccounts.actAs
permission on this service account.
The resource name of the shared DeploymentResourcePool to deploy on.
Format:
projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}
[[["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\u003eDeployedModel\u003c/code\u003e class in the Vertex AI v1beta1 API represents a deployment of a machine learning model, with endpoints containing one or more \u003ccode\u003eDeployedModels\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003e\u003ccode\u003eDeployedModel\u003c/code\u003e includes properties to configure deployment resources, such as \u003ccode\u003eAutomaticResources\u003c/code\u003e and \u003ccode\u003eDedicatedResources\u003c/code\u003e, offering options for both Vertex AI-managed and custom-configured resources.\u003c/p\u003e\n"],["\u003cp\u003eKey settings include options for enabling access and container logging, with \u003ccode\u003eEnableAccessLogging\u003c/code\u003e and \u003ccode\u003eEnableContainerLogging\u003c/code\u003e, for monitoring and debugging deployed models.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eDeployedModel\u003c/code\u003e allows specification of the deployed model's ID, display name, and associated service account, supporting custom configurations and security settings.\u003c/p\u003e\n"],["\u003cp\u003eThe class also provides information on the model's creation time, version ID, and runtime status via properties such as \u003ccode\u003eCreateTime\u003c/code\u003e, \u003ccode\u003eModelVersionId\u003c/code\u003e, and \u003ccode\u003eStatus\u003c/code\u003e, respectively.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class DeployedModel (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.DeployedModel)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.DeployedModel) \n\n public sealed class DeployedModel : IMessage\u003cDeployedModel\u003e, IEquatable\u003cDeployedModel\u003e, IDeepCloneable\u003cDeployedModel\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class DeployedModel.\n\nA deployment of a Model. Endpoints contain one or more DeployedModels. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e DeployedModel \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[DeployedModel](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeployedModel), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[DeployedModel](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeployedModel), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[DeployedModel](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeployedModel), [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### DeployedModel()\n\n public DeployedModel()\n\n### DeployedModel(DeployedModel)\n\n public DeployedModel(DeployedModel other)\n\nProperties\n----------\n\n### AutomaticResources\n\n public AutomaticResources AutomaticResources { get; set; }\n\nA description of resources that to large degree are decided by Vertex\nAI, and require only a modest additional configuration.\n\n### CheckpointId\n\n public string CheckpointId { get; set; }\n\nThe checkpoint id of the model.\n\n### CreateTime\n\n public Timestamp CreateTime { get; set; }\n\nOutput only. Timestamp when the DeployedModel was created.\n\n### DedicatedResources\n\n public DedicatedResources DedicatedResources { get; set; }\n\nA description of resources that are dedicated to the DeployedModel, and\nthat need a higher degree of manual configuration.\n\n### DisableExplanations\n\n public bool DisableExplanations { get; set; }\n\nIf true, deploy the model without explainable feature, regardless the\nexistence of\n\\[Model.explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.Model.explanation_spec\\]\nor\n\\[explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec\\].\n\n### DisplayName\n\n public string DisplayName { get; set; }\n\nThe display name of the DeployedModel. If not provided upon creation,\nthe Model's display_name is used.\n\n### EnableAccessLogging\n\n public bool EnableAccessLogging { get; set; }\n\nIf true, online prediction access logs are sent to Cloud\nLogging.\nThese logs are like standard server access logs, containing\ninformation like timestamp and latency for each prediction request.\n\nNote that logs may incur a cost, especially if your project\nreceives prediction requests at a high queries per second rate (QPS).\nEstimate your costs before enabling this option.\n\n### EnableContainerLogging\n\n public bool EnableContainerLogging { get; set; }\n\nIf true, the container of the DeployedModel instances will send `stderr`\nand `stdout` streams to Cloud Logging.\n\nOnly supported for custom-trained Models and AutoML Tabular Models.\n\n### ExplanationSpec\n\n public ExplanationSpec ExplanationSpec { get; set; }\n\nExplanation configuration for this DeployedModel.\n\nWhen deploying a Model using\n\\[EndpointService.DeployModel\\]\\[google.cloud.aiplatform.v1beta1.EndpointService.DeployModel\\],\nthis value overrides the value of\n\\[Model.explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.Model.explanation_spec\\].\nAll fields of\n\\[explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec\\]\nare optional in the request. If a field of\n\\[explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec\\]\nis not populated, the value of the same field of\n\\[Model.explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.Model.explanation_spec\\]\nis inherited. If the corresponding\n\\[Model.explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.Model.explanation_spec\\]\nis not populated, all fields of the\n\\[explanation_spec\\]\\[google.cloud.aiplatform.v1beta1.DeployedModel.explanation_spec\\]\nwill be used for the explanation configuration.\n\n### FasterDeploymentConfig\n\n public FasterDeploymentConfig FasterDeploymentConfig { get; set; }\n\nConfiguration for faster model deployment.\n\n### HasSharedResources\n\n public bool HasSharedResources { get; }\n\nGets whether the \"shared_resources\" field is set\n\n### Id\n\n public string Id { get; set; }\n\nImmutable. The ID of the DeployedModel. If not provided upon deployment,\nVertex AI will generate a value for this ID.\n\nThis value should be 1-10 characters, and valid characters are `/[0-9]/`.\n\n### Model\n\n public string Model { get; set; }\n\nThe resource name of the Model that this is the deployment of. Note that\nthe Model may be in a different location than the DeployedModel's Endpoint.\n\nThe resource name may contain version id or version alias to specify the\nversion.\nExample: `projects/{project}/locations/{location}/models/{model}@2`\nor\n`projects/{project}/locations/{location}/models/{model}@golden`\nif no version is specified, the default version will be deployed.\n\n### ModelAsModelName\n\n public ModelName ModelAsModelName { get; set; }\n\n[ModelName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.ModelName)-typed view over the [Model](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeployedModel#Google_Cloud_AIPlatform_V1Beta1_DeployedModel_Model) resource name property.\n\n### ModelVersionId\n\n public string ModelVersionId { get; set; }\n\nOutput only. The version ID of the model that is deployed.\n\n### PredictionResourcesCase\n\n public DeployedModel.PredictionResourcesOneofCase PredictionResourcesCase { get; }\n\n### PrivateEndpoints\n\n public PrivateEndpoints PrivateEndpoints { get; set; }\n\nOutput only. Provide paths for users to send predict/explain/health\nrequests directly to the deployed model services running on Cloud via\nprivate services access. This field is populated if\n\\[network\\]\\[google.cloud.aiplatform.v1beta1.Endpoint.network\\] is configured.\n\n### RolloutOptions\n\n public RolloutOptions RolloutOptions { get; set; }\n\nOptions for configuring rolling deployments.\n\n### ServiceAccount\n\n public string ServiceAccount { get; set; }\n\nThe service account that the DeployedModel's container runs as. Specify the\nemail address of the service account. If this service account is not\nspecified, the container runs as a service account that doesn't have access\nto the resource project.\n\nUsers deploying the Model must have the `iam.serviceAccounts.actAs`\npermission on this service account.\n\n### SharedResources\n\n public string SharedResources { get; set; }\n\nThe resource name of the shared DeploymentResourcePool to deploy on.\nFormat:\n`projects/{project}/locations/{location}/deploymentResourcePools/{deployment_resource_pool}`\n\n### SharedResourcesAsDeploymentResourcePoolName\n\n public DeploymentResourcePoolName SharedResourcesAsDeploymentResourcePoolName { get; set; }\n\n[DeploymentResourcePoolName](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeploymentResourcePoolName)-typed view over the [SharedResources](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.DeployedModel#Google_Cloud_AIPlatform_V1Beta1_DeployedModel_SharedResources) resource name\nproperty.\n\n### SpeculativeDecodingSpec\n\n public SpeculativeDecodingSpec SpeculativeDecodingSpec { get; set; }\n\nOptional. Spec for configuring speculative decoding.\n\n### Status\n\n public DeployedModel.Types.Status Status { get; set; }\n\nOutput only. Runtime status of the deployed model.\n\n### SystemLabels\n\n public MapField\u003cstring, string\u003e SystemLabels { get; }\n\nSystem labels to apply to Model Garden deployments.\nSystem labels are managed by Google for internal use only."]]
