Skip to main content
Configure Google Cloud Vertex AI to access Google’s foundation models through Braintrust.

​
Authentication

Choose between two authentication methods:
  • Access token: Use a Vertex AI access token for authentication
  • Service account key: Use a service account key JSON file for authentication

​
Configuration

FieldDescription
Project
String		Required. Your Google Cloud Project ID where Vertex AI is enabled.
Location
String		Optional. Vertex region to send requests to (for example us-central1 or us-east5). If omitted, Braintrust keeps defaults: us-east5 for Vertex Anthropic models and us-central1 for other Vertex routes.
Authentication type
access_token | service_account_key		Required. Choose between access token or service account key authentication. Documentation
Secret
JSON String		Required if using service_account_key auth type. The service account key JSON content. Documentation
API base
URL String		Optional. Custom API endpoint URL if using a different Vertex AI endpoint. Documentation. Default is https://{location}-aiplatform.googleapis.com.

​
Models

Popular Vertex AI models include:
  • Gemini 1.5 Pro (gemini-1.5-pro)
  • Gemini 1.5 Flash (gemini-1.5-flash)
  • PaLM 2 (text-bison)
  • Codey (code-bison)

​
Setup requirements

  1. Enable Vertex AI API: Ensure the Vertex AI API is enabled in your Google Cloud project
  2. Service account permissions: If using service account authentication, ensure the service account has the AI Platform Developer role
  3. Quotas: Check your project’s Vertex AI quotas and limits

​
Additional resources