Vertex AI
Configure Google Cloud Vertex AI as an LLM provider in agentgateway.
Authentication
Before you can use Vertex AI as an LLM provider, you must authenticate by using Google Cloud’s Application Default Credentials. Choose from one of the three methods:
GOOGLE_APPLICATION_CREDENTIALS
application_default_credentials.json
- metadata server
Configuration
Review the following example configuration.binds:
- port: 3000
listeners:
- routes:
- backends:
- ai:
name: vertex
provider:
vertex:
projectId: my-project-id
# Optional: defaults to 'global'
region: us-west2
# Optional; overrides the model in requests
model: google/gemini-2.5-flash-lite-preview-06-17
Setting | Description |
---|---|
ai.name |
The name of the LLM provider for this AI backend. |
vertex.projectId |
The Google Cloud project ID. |
vertex.region |
The Google Cloud region. Defaults to global . |
vertex.model |
Optionally set the model to use for requests. If set, any models in the request are overwritten. If not set, the request must include the model to use. |