Stay organized with collections
Save and categorize content based on your preferences.
Resource: ModelMonitor
Vertex AI Model Monitoring service serves as a central hub for the analysis and visualization of data quality and performance related to models. ModelMonitor stands as a top level resource for overseeing your model monitoring tasks.
Fields
name
string
Immutable. Resource name of the ModelMonitor. Format: projects/{project}/locations/{location}/modelMonitors/{modelMonitor}.
displayName
string
The display name of the ModelMonitor. The name can be up to 128 characters long and can consist of any UTF-8.
The entity that is subject to analysis. Currently only models in Vertex AI Model Registry are supported. If you want to analyze the model which is outside the Vertex AI, you could register a model in Vertex AI Model Registry using just a display name.
Optional default monitoring metrics/logs export spec, it can be overridden in the ModelMonitoringJob output spec. If not specified, a default Google Cloud Storage bucket will be created under your project.
Monitoring Schema is to specify the model's features, prediction outputs and ground truth properties. It is used to extract pertinent data from the dataset and to process features based on their properties. Make sure that the schema aligns with your dataset, if it does not, we will be unable to extract data from the dataset. It is required for most models, but optional for Vertex AI AutoML Tables unless the schem information is not available.
Customer-managed encryption key spec for a ModelMonitor. If set, this ModelMonitor and all sub-resources of this ModelMonitor will be secured by this key.
Output only. timestamp when this ModelMonitor 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 ModelMonitor was updated most recently.
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".
satisfiesPzs
boolean
Output only. reserved for future use.
satisfiesPzi
boolean
Output only. reserved for future use.
default_objective
Union type
Optional default monitoring objective, it can be overridden in the ModelMonitoringJob objective spec. default_objective can be only one of the following:
feature names of the model. Vertex AI will try to match the features from your dataset as follows: * For 'csv' files, the header names are required, and we will extract the corresponding feature values when the header names align with the feature names. * For 'jsonl' files, we will extract the corresponding feature values if the key names match the feature names. Note: Nested features are not supported, so please ensure your features are flattened. Ensure the feature values are scalar or an array of scalars. * For 'bigquery' dataset, we will extract the corresponding feature values if the column names match the feature names. Note: The column type can be a scalar or an array of scalars. STRUCT or JSON types are not supported. You may use SQL queries to select or aggregate the relevant features from your original table. However, ensure that the 'schema' of the query results meets our requirements. * For the Vertex AI Endpoint Request Response Logging table or Vertex AI Batch Prediction Job results. If the instanceType is an array, ensure that the sequence in featureFields matches the order of features in the prediction instance. We will match the feature with the array in the order specified in [featureFields].
Prediction output names of the model. The requirements are the same as the featureFields. For AutoML Tables, the prediction output name presented in schema will be: predicted_{targetColumn}, the targetColumn is the one you specified when you train the model. For Prediction output drift analysis: * AutoML Classification, the distribution of the argmax label will be analyzed. * AutoML Regression, the distribution of the value will be analyzed.
[[["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 2025-06-27 UTC."],[],[],null,["# REST Resource: projects.locations.modelMonitors\n\nResource: ModelMonitor\n----------------------\n\nVertex AI Model Monitoring service serves as a central hub for the analysis and visualization of data quality and performance related to models. ModelMonitor stands as a top level resource for overseeing your model monitoring tasks.\nFields `name` `string` \nImmutable. Resource name of the ModelMonitor. Format: `projects/{project}/locations/{location}/modelMonitors/{modelMonitor}`.\n`displayName` `string` \nThe display name of the ModelMonitor. The name can be up to 128 characters long and can consist of any UTF-8.\n`modelMonitoringTarget` `object (`[ModelMonitoringTarget](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#ModelMonitoringTarget)`)` \nThe entity that is subject to analysis. Currently only models in Vertex AI Model Registry are supported. If you want to analyze the model which is outside the Vertex AI, you could register a model in Vertex AI Model Registry using just a display name.\n`trainingDataset` `object (`[ModelMonitoringInput](/vertex-ai/docs/reference/rest/v1beta1/ModelMonitoringInput)`)` \nOptional training dataset used to train the model. It can serve as a reference dataset to identify changes in production.\n`notificationSpec` `object (`[ModelMonitoringNotificationSpec](/vertex-ai/docs/reference/rest/v1beta1/ModelMonitoringNotificationSpec)`)` \nOptional default notification spec, it can be overridden in the ModelMonitoringJob notification spec.\n`outputSpec` `object (`[ModelMonitoringOutputSpec](/vertex-ai/docs/reference/rest/v1beta1/ModelMonitoringOutputSpec)`)` \nOptional default monitoring metrics/logs export spec, it can be overridden in the ModelMonitoringJob output spec. If not specified, a default Google Cloud Storage bucket will be created under your project.\n`explanationSpec` `object (`[ExplanationSpec](/vertex-ai/docs/reference/rest/v1beta1/ExplanationSpec)`)` \nOptional model explanation spec. It is used for feature attribution monitoring.\n`modelMonitoringSchema` `object (`[ModelMonitoringSchema](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#ModelMonitoringSchema)`)` \nMonitoring Schema is to specify the model's features, prediction outputs and ground truth properties. It is used to extract pertinent data from the dataset and to process features based on their properties. Make sure that the schema aligns with your dataset, if it does not, we will be unable to extract data from the dataset. It is required for most models, but optional for Vertex AI AutoML Tables unless the schem information is not available.\n`encryptionSpec` `object (`[EncryptionSpec](/vertex-ai/docs/reference/rest/v1beta1/EncryptionSpec)`)` \nCustomer-managed encryption key spec for a ModelMonitor. If set, this ModelMonitor and all sub-resources of this ModelMonitor will be secured by this key.\n`createTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this ModelMonitor 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`updateTime` `string (`[Timestamp](https://protobuf.dev/reference/protobuf/google.protobuf/#timestamp)` format)` \nOutput only. timestamp when this ModelMonitor was updated most recently.\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`satisfiesPzs` `boolean` \nOutput only. reserved for future use.\n`satisfiesPzi` `boolean` \nOutput only. reserved for future use. \n`default_objective` `Union type` \nOptional default monitoring objective, it can be overridden in the ModelMonitoringJob objective spec. `default_objective` can be only one of the following:\n`tabularObjective` `object (`[TabularObjective](/vertex-ai/docs/reference/rest/v1beta1/TabularObjective)`)` \nOptional default tabular model monitoring objective. \n\nModelMonitoringTarget\n---------------------\n\nThe monitoring target refers to the entity that is subject to analysis. e.g. Vertex AI Model version.\nFields \n`source` `Union type` \n`source` can be only one of the following:\n`vertexModel` `object (`[VertexModelSource](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#VertexModelSource)`)` \nModel in Vertex AI Model Registry. \n\nVertexModelSource\n-----------------\n\nModel in Vertex AI Model Registry.\nFields `model` `string` \nModel resource name. Format: projects/{project}/locations/{location}/models/{model}.\n`modelVersionId` `string` \nModel version id. \n\nModelMonitoringSchema\n---------------------\n\nThe Model Monitoring Schema definition.\nFields `featureFields[]` `object (`[FieldSchema](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#FieldSchema)`)` \nfeature names of the model. Vertex AI will try to match the features from your dataset as follows: \\* For 'csv' files, the header names are required, and we will extract the corresponding feature values when the header names align with the feature names. \\* For 'jsonl' files, we will extract the corresponding feature values if the key names match the feature names. Note: Nested features are not supported, so please ensure your features are flattened. Ensure the feature values are scalar or an array of scalars. \\* For 'bigquery' dataset, we will extract the corresponding feature values if the column names match the feature names. Note: The column type can be a scalar or an array of scalars. STRUCT or JSON types are not supported. You may use SQL queries to select or aggregate the relevant features from your original table. However, ensure that the 'schema' of the query results meets our requirements. \\* For the Vertex AI Endpoint Request Response Logging table or Vertex AI Batch Prediction Job results. If the `instanceType` is an array, ensure that the sequence in [featureFields](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#ModelMonitoringSchema.FIELDS.feature_fields) matches the order of features in the prediction instance. We will match the feature with the array in the order specified in \\[featureFields\\].\n`predictionFields[]` `object (`[FieldSchema](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#FieldSchema)`)` \nPrediction output names of the model. The requirements are the same as the [featureFields](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#ModelMonitoringSchema.FIELDS.feature_fields). For AutoML Tables, the prediction output name presented in schema will be: `predicted_{targetColumn}`, the `targetColumn` is the one you specified when you train the model. For Prediction output drift analysis: \\* AutoML Classification, the distribution of the argmax label will be analyzed. \\* AutoML Regression, the distribution of the value will be analyzed.\n`groundTruthFields[]` `object (`[FieldSchema](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.modelMonitors#FieldSchema)`)` \nTarget /ground truth names of the model. \n\nFieldSchema\n-----------\n\nSchema field definition.\nFields `name` `string` \nField name.\n`dataType` `string` \nSupported data types are: `float` `integer` `boolean` `string` `categorical`\n`repeated` `boolean` \nDescribes if the schema field is an array of given data type."]]