Vertex Gemini setup

Port's vertex-gemini provider connects to Google Vertex AI Gemini models. You register the model IDs your project exposes, then authenticate with either a GCP service account or Vertex AI Express Mode (API key). Complete the steps below before Step 2: store API keys in secrets in the main setup guide.

Step 1: Prepare your GCP project

1. Enable the Vertex AI API for your GCP project.
2. Confirm the Gemini models you need are available in your chosen region.
3. Create a service account (skip this if you use Express Mode only):
   • In the Google Cloud console, go to IAM & Admin → Service accounts and create a service account for Port.
   • Grant the service account the Vertex AI User role (roles/aiplatform.user), or a custom role that includes aiplatform.endpoints.predict for the models you use.
   • Create a JSON key for the service account. You will store client_email and private_key from this file as separate Port secrets.

Express Mode vs service account

Use either Express Mode (apiKeySecretName) or the full service-account fields (clientEmailSecretName, privateKeySecretName, project, location). Port rejects configurations that mix both auth modes or leave either mode incomplete.

Step 2: Store credentials in Port secrets

Follow store API keys in secrets in the main guide. Secret names are flexible; reference the same names in your provider config.

Service account authentication

Secret purpose	Example secret name	Value
Service account email	VERTEX_SA_CLIENT_EMAIL	client_email from the JSON key
Service account private key	VERTEX_SA_PRIVATE_KEY	private_key from the JSON key (PEM, including -----BEGIN PRIVATE KEY-----)

Private key formatting

If you paste the private key with literal \n characters instead of real line breaks, Port normalizes them when calling Vertex AI.

Express Mode authentication

Secret purpose	Example secret name	Value
Vertex AI API key	VERTEX_EXPRESS_API_KEY	API key from Vertex AI Express Mode

Step 3: Register with the Port API

Call Create or connect an LLM provider with validate_connection=true while testing. Set provider to "vertex-gemini" and list at least one model in config.models. Each name must be at least three characters and must match the model ID you invoke on Vertex AI (for example gemini-2.5-flash).

Service account example

{
  "provider": "vertex-gemini",
  "enabled": true,
  "config": {
    "clientEmailSecretName": "VERTEX_SA_CLIENT_EMAIL",
    "privateKeySecretName": "VERTEX_SA_PRIVATE_KEY",
    "project": "my-gcp-project",
    "location": "us-central1",
    "models": [
      {
        "name": "gemini-2.5-flash",
        "displayName": "Gemini 2.5 Flash",
        "contextWindow": 1000000,
        "supportedFeatures": {
          "temperature": true
        }
      }
    ]
  }
}

Express Mode example

{
  "provider": "vertex-gemini",
  "enabled": true,
  "config": {
    "apiKeySecretName": "VERTEX_EXPRESS_API_KEY",
    "models": [
      {
        "name": "gemini-2.5-flash",
        "displayName": "Gemini 2.5 Flash"
      }
    ]
  }
}

Optional fields on each model entry include displayName, contextWindow, and supportedFeatures. See the API reference for the full schema.

After registration

• Set organization defaults in the Builder UI or with Change default LLM provider and model.
• Or pass provider: "vertex-gemini" and the registered model name on individual general-purpose AI interactions or invoke a specific agent calls.

For validation flow, default selection, and common failures, use Setup & configuration alongside your Vertex AI quotas and Cloud Logging.