Skip to main content
Vertex AI, Google’s fully managed AI development platform, can be seamlessly integrated with orq.ai. By connecting your Google Vertex AI account to Orq.ai, all model calls will utilize your API keys and custom Vertex configuration settings, ensuring consistency and control.

​
Integrate Vertex AI with orq.ai

To start integration, you first need to create a Service Account with only two permissions: Service Account Token Creator and Vertex AI user. Head to the Providers tab in the Model Garden and select Google Vertex AI > Set up your own API Key.

This modal opens when setting up your Vertex AI Provider.

​
Import a Vertex AI Model

Head to the **Model Garden > Models **page and select Add Model.
Model Garden Add Vertex Ai

Select Vertex AI

Then configure the following fields: Name A name for your integration within orq.ai. Example: orq-vertex. Deployment JSON The JSON payload holding credentials and model configuration for the choosen model to import . Example: 
{
  "projectId": "my-project-123456",
  "location": "europe-west1",
  "serviceAccount": {
    "type": "service_account",
    "project_id": "my-project-123456",
    "private_key_id": "afd17083ecd5184b5ca880e70eb84c2e4c382f14",
    "private_key": "-----BEGIN PRIVATE KEY-----\n...=\n-----END PRIVATE KEY-----\n",
    "client_email": "[email protected]",
    "client_id": "000000000000000000000",
    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
    "token_uri": "https://oauth2.googleapis.com/token",
    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
    "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/vertex-ai%40my-project-123456.iam.gserviceaccount.com",
    "universe_domain": "googleapis.com"
  },
  "modelConfiguration": {
    "id": "gemini-2.0-flash-001",
    "inputCost": 0.0001,
    "outputCost": 0.0002,
    "parameters": {
      "temperature": {
        "min": 0,
        "max": 1
      },
      "maxTokens": {
        "min": 1,
        "max": 8192
      },
      "topP": {
        "min": 0,
        "max": 1
      }
    },
    "capabilities": {
      "supportToolCalling": true,
      "structuredOutput": false,
      "vision": true
    }
  }
}
The Google Cloud Project name for your Vertex AI, example: orquestadev. Usually shown at the top of your Google Page.
Once fields are entered, select Save Changes, your credentials will now be used in Playground, Experiment, Deployment, and Agent using Vertex AI models.