REST Resource: publishers.models Stay organized with collections Save and categorize content based on your preferences.
Resource: PublisherModel
A Model Garden Publisher Model.
namestringOutput only. The resource name of the PublisherModel.
versionIdstringOutput only. Immutable. The version id of the PublisherModel. A new version is committed when a new model version is uploaded under an existing model id. It is an auto-incrementing decimal number in string representation.
openSourceCategoryenum (OpenSourceCategory)Required. Indicates the open source category of the publisher model.
parentobject (Parent)Optional. The parent that this model was customized from. E.g., Vision API, Natural Language API, LaMDA, T5, etc. Foundation models don't have parents.
supportedActionsobject (CallToAction)Optional. Supported call-to-action options.
frameworks[]stringOptional. Additional information about the model's Frameworks.
launchStageenum (LaunchStage)Optional. Indicates the launch stage of the model.
versionStateenum (VersionState)Optional. Indicates the state of the model version.
publisherModelTemplatestringOptional. Output only. Immutable. Used to indicate this model has a publisher model and provide the template of the publisher model resource name.
predictSchemataobject (PredictSchemata)Optional. The schemata that describes formats of the PublisherModel's predictions and explanations as given and returned viaPredictionService.Predict.
| JSON representation |
|---|
{"name":string,"versionId":string,"openSourceCategory":enum ( |
OpenSourceCategory
An enum representing the open source category of a PublisherModel.
| Enums | |
|---|---|
OPEN_SOURCE_CATEGORY_UNSPECIFIED | The open source category is unspecified, which should not be used. |
PROPRIETARY | Used to indicate the PublisherModel is not open sourced. |
GOOGLE_OWNED_OSS_WITH_GOOGLE_CHECKPOINT | Used to indicate the PublisherModel is a Google-owned open source model w/ Google checkpoint. |
THIRD_PARTY_OWNED_OSS_WITH_GOOGLE_CHECKPOINT | Used to indicate the PublisherModel is a 3p-owned open source model w/ Google checkpoint. |
GOOGLE_OWNED_OSS | Used to indicate the PublisherModel is a Google-owned pure open source model. |
THIRD_PARTY_OWNED_OSS | Used to indicate the PublisherModel is a 3p-owned pure open source model. |
Parent
The information about the parent of a model.
displayNamestringRequired. The display name of the parent. E.g., LaMDA, T5, Vision API, Natural Language API.
referenceobject (ResourceReference)Optional. The Google Cloud resource name or the URI reference.
| JSON representation |
|---|
{"displayName":string,"reference":{object ( |
ResourceReference
Reference to a resource.
referenceUnion typereference can be only one of the following:uristringThe URI of the resource.
resourceNamestringThe resource name of the Google Cloud resource.
useCase
(deprecated)stringdescription
(deprecated)string| JSON representation |
|---|
{// reference"uri":string,"resourceName":string,"useCase":string,"description":string// Union type} |
CallToAction
Actions could take on this Publisher Model.
viewRestApiobject (ViewRestApi)Optional. To view Rest API docs.
openNotebookobject (RegionalResourceReferences)Optional. Open notebook of the PublisherModel.
createApplicationobject (RegionalResourceReferences)Optional. Create application using the PublisherModel.
openFineTuningPipelineobject (RegionalResourceReferences)Optional. Open fine-tuning pipeline of the PublisherModel.
openPromptTuningPipelineobject (RegionalResourceReferences)Optional. Open prompt-tuning pipeline of the PublisherModel.
openGenieobject (RegionalResourceReferences)Optional. Open Genie / Playground.
deployobject (Deploy)Optional. Deploy the PublisherModel to Vertex Endpoint.
multiDeployVertexobject (DeployVertex)Optional. Multiple setups to deploy the PublisherModel to Vertex Endpoint.
deployGkeobject (DeployGke)Optional. Deploy PublisherModel to Google Kubernetes Engine.
openGenerationAiStudioobject (RegionalResourceReferences)Optional. Open in Generation AI Studio.
requestAccessobject (RegionalResourceReferences)Optional. Request for access.
openEvaluationPipelineobject (RegionalResourceReferences)Optional. Open evaluation pipeline of the PublisherModel.
openNotebooksobject (OpenNotebooks)Optional. Open notebooks of the PublisherModel.
openFineTuningPipelinesobject (OpenFineTuningPipelines)Optional. Open fine-tuning pipelines of the PublisherModel.
| JSON representation |
|---|
{"viewRestApi":{object ( |
ViewRestApi
Rest API docs.
documentations[]object (Documentation)Required.
titlestringRequired. The title of the view rest API.
| JSON representation |
|---|
{"documentations":[{object ( |
Documentation
A named piece of documentation.
titlestringRequired. E.g., OVERVIEW, USE CASES, DOCUMENTATION, SDK & SAMPLES, JAVA, NODE.JS, etc..
contentstringRequired. Content of this piece of document (in Markdown format).
| JSON representation |
|---|
{"title":string,"content":string} |
RegionalResourceReferences
The regional resource name or the URI. Key is region, e.g., us-central1, europe-west2, global, etc..
referencesmap (key: string, value: object (ResourceReference))Required.
titlestringRequired.
resourceTitlestringOptional. title of the resource.
resourceUseCasestringOptional. Use case (CUJ) of the resource.
resourceDescriptionstringOptional. description of the resource.
| JSON representation |
|---|
{"references":{string:{object ( |
OpenNotebooks
Open notebooks.
notebooks[]object (RegionalResourceReferences)Required. Regional resource references to notebooks.
| JSON representation |
|---|
{"notebooks":[{object ( |
OpenFineTuningPipelines
Open fine tuning pipelines.
fineTuningPipelines[]object (RegionalResourceReferences)Required. Regional resource references to fine tuning pipelines.
| JSON representation |
|---|
{"fineTuningPipelines":[{object ( |
Deploy
Model metadata that is needed for UploadModel or DeployModel/CreateEndpoint requests.
modelDisplayNamestringOptional. Default model display name.
largeModelReferenceobject (LargeModelReference)Optional. Large model reference. When this is set, modelArtifactSpec is not needed.
containerSpecobject (ModelContainerSpec)Optional. The specification of the container that is to be used when deploying this Model in Vertex AI. Not present for Large Models.
artifactUristringOptional. The path to the directory containing the Model artifact and any of its supporting files.
titlestringRequired. The title of the regional resource reference.
publicArtifactUristringOptional. The signed URI for ephemeral Cloud Storage access to model artifact.
prediction_resourcesUnion typeprediction_resources can be only one of the following:dedicatedResourcesobject (DedicatedResources)A description of resources that are dedicated to the DeployedModel, and that need a higher degree of manual configuration.
automaticResourcesobject (AutomaticResources)A description of resources that to large degree are decided by Vertex AI, and require only a modest additional configuration.
sharedResourcesstringThe resource name of the shared DeploymentResourcePool to deploy on. Format:projects/{project}/locations/{location}/deploymentResourcePools/{deploymentResourcePool}
deployTaskNamestringOptional. The name of the deploy task (e.g., "text to image generation").
deployMetadataobject (DeployMetadata)Optional. metadata information about this deployment config.
| JSON representation |
|---|
{"modelDisplayName":string,"largeModelReference":{object ( |
LargeModelReference
Contains information about the Large Model.
namestringRequired. The unique name of the large Foundation or pre-built model. Like "chat-bison", "text-bison". Or model name with version id, like "chat-bison@001", "text-bison@005", etc.
| JSON representation |
|---|
{"name":string} |
DeployMetadata
metadata information about the deployment for managing deployment config.
labelsmap (key: string, value: string)Optional. Labels for the deployment config. For managing deployment config like verifying, source of deployment config, etc.
sampleRequeststringOptional. Sample request for deployed endpoint.
| JSON representation |
|---|
{"labels":{string:string,...},"sampleRequest":string} |
DeployVertex
DeployGke
Configurations for PublisherModel GKE deployment
gkeYamlConfigs[]stringOptional. GKE deployment configuration in yaml format.
| JSON representation |
|---|
{"gkeYamlConfigs":[string]} |
LaunchStage
An enum representing the launch stage of a PublisherModel.
| Enums | |
|---|---|
LAUNCH_STAGE_UNSPECIFIED | The model launch stage is unspecified. |
EXPERIMENTAL | Used to indicate the PublisherModel is at Experimental launch stage, available to a small set of customers. |
PRIVATE_PREVIEW | Used to indicate the PublisherModel is at Private Preview launch stage, only available to a small set of customers, although a larger set of customers than an Experimental launch. Previews are the first launch stage used to get feedback from customers. |
PUBLIC_PREVIEW | Used to indicate the PublisherModel is at Public Preview launch stage, available to all customers, although not supported for production workloads. |
GA | Used to indicate the PublisherModel is at GA launch stage, available to all customers and ready for production workload. |
VersionState
An enum representing the state of the PublicModelVersion.
| Enums | |
|---|---|
VERSION_STATE_UNSPECIFIED | The version state is unspecified. |
VERSION_STATE_STABLE | Used to indicate the version is stable. |
VERSION_STATE_UNSTABLE | Used to indicate the version is unstable. |
Methods | |
|---|---|
| Gets a Model Garden publisher model. |
| Lists publisher models in Model Garden. |
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-06-27 UTC.