Google AI Studio
Google AI Studio (Gemini) keys are stored under the `google-ai` provider. The registry alias map resolves `google-ai-studio`, `google_ai_studio`, and `gemini` to `google-ai`.
Purpose
Configure Google AI Studio access through the authenticated integration routes. Then use Environment monitoring, secret storage, and usage-ingestion features in the product.
Prerequisites
- A signed-in Supabase session.
- A CSRF token for POST and PATCH requests.
- A Google AI Studio (Gemini) API key.
Setup
1
Create the credential with POST /api/integrations using provider `google-ai` (or the alias `google-ai-studio`).
2
Use Integrations settings to attach the credential to the target Environment.
3
Send usage events through /api/v1/costs/usage-events or /api/llm/log when your backend makes Gemini calls.
API & contracts
| Field | Type | Description |
|---|---|---|
| google-ai | api_key | Aliases `google-ai-studio` and `gemini` both resolve here. |
- The verifier expects a non-empty `api_key`.
- Environment connector bindings accept the `google-ai` connector type.
- The agentic connector registry uses a generic API-key connector for `google-ai`.
Failure modes
| 400 | when the API key is missing or invalid. |
| 401 | without a session and 403 for unauthorized Environment references. |
| 403 | when the CSRF token is missing on mutation routes. |
Partial
Credential storage, verification, connector binding, and usage ingestion are implemented. Google AI Studio specific resource fetching and webhook handling are not implemented in the current codebase.