Skip to main content

​
Google

WednesdayAI supports Google’s Gemini family. Authenticate with an AI Studio API key (easiest) or Vertex AI (for GCP-native deployments).

​
AI Studio API key

Create a key at aistudio.google.com and onboard:
Or set the key on the gateway host:
Rotation variables (GEMINI_API_KEYS, GEMINI_API_KEY_1, GEMINI_API_KEY_2) are honoured, and the bare GOOGLE_API_KEY is included as a fallback.
GOOGLE_API_KEY fallback support may vary by version — verify it is still recognised in your deployment by checking the core release notes.

​
Gemini CLI (OAuth)

WednesdayAI supports OAuth authentication via the Gemini CLI. This is an active primary auth path — no API key required:
This opens a browser for the OAuth flow and stores the token in the auth profile store. The Gemini CLI must be installed first (npm install -g @google/gemini-cli).
Some users have reported Google account restrictions when using third-party clients. Review Google’s terms of service and consider using a non-critical account.

​
Vertex AI

For production GCP deployments, use Application Default Credentials (ADC) via the google-vertex provider. Preferred — user ADC:
Alternative — service account:
The service account needs the Vertex AI User (roles/aiplatform.user) role.
GOOGLE_CLOUD_PROJECT is optional — it defaults to the project in your service account credentials or your active gcloud configuration.

​
Selecting a model

Use the google/ prefix for AI Studio and google-vertex/ for Vertex. Run openclaw models list --all for the catalog and openclaw models status for what your auth can reach.
WednesdayAI also bundles google-antigravity as an unofficial OAuth provider. Some users have reported Google account restrictions when using third-party clients — review Google’s terms and use a non-critical account if you enable it.

​
Environment variables

​
Troubleshooting

Ensure the key was created in AI Studio and that the Generative Language API is enabled for the project.
The service account is missing the Vertex AI User role. Add it in IAM and Admin.
Not all Gemini models are available in all regions. On Vertex, try a different region or check the Vertex AI model availability table.