Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.wednesdayai.dev/llms.txt

Use this file to discover all available pages before exploring further.

​
Google

WednesdayAI supports Google’s Gemini model family. You can authenticate with an AI Studio API key (easiest) or a Vertex AI service account (for GCP-native deployments).

​
AI Studio API key

Obtain a key from aistudio.google.com → Get API key. 
openclaw login
# choose: Google
# enter your API key when prompted
Or set the environment variable: 
export GOOGLE_API_KEY=AIza...
Lookup order:
SourceKey / path
Environment variableGOOGLE_API_KEY
Stored credential~/.openclaw/credentials/google

​
Vertex AI

For production GCP deployments, use a service account instead of an API key.
  1. Create a service account in IAM & Admin with the Vertex AI User role.
  2. Download a JSON key file.
  3. Set the environment variable:
export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
export GOOGLE_CLOUD_PROJECT=my-project-id
When GOOGLE_APPLICATION_CREDENTIALS is set, the gateway uses Vertex AI authentication automatically. The GOOGLE_API_KEY variable is ignored.

​
Selecting a model

{
  agents: {
    defaults: {
      model: "gemini-2.0-flash",
    }
  }
}
Common model IDs:
ModelID
Gemini 2.0 Flashgemini-2.0-flash
Gemini 2.5 Progemini-2.5-pro
Gemini 1.5 Flashgemini-1.5-flash
Run openclaw status --providers to list models available on your key.

​
Troubleshooting

Ensure the key was created in AI Studio (not Cloud Console) and has the Generative Language API enabled. Visit console.cloud.google.com/apis and enable Generative Language API.
The service account is missing the Vertex AI User (roles/aiplatform.user) role. Add it in IAM & Admin.
Not all Gemini models are available in all regions. If using Vertex AI, try a different GOOGLE_CLOUD_REGION or check the Vertex AI model availability table.