Google Cloud connection
One Google Cloud project, for AI steps to run Gemini on through Vertex AI. In the connection picker it is Google Cloud.
Powers these nodes
No Google-specific nodes yet. It serves the built-in AI Agent action, the AI Judgment condition, and your default model—anywhere a Provider Account is chosen.
Fields
| Field | Required | Description |
|---|---|---|
| Name | Yes | A name for the account. It labels the account everywhere it is offered, so say whose account it is. |
| Project ID | Yes | The Google Cloud project whose quota is spent. |
| Location | No | The region requests are routed to. Availability varies by region. Leave it blank for the default. |
| Credentials | Yes | Service Account Key or Server Identity—see below. |
Credentials
| Type | What it takes |
|---|---|
| Service Account Key | The service account's JSON key, pasted whole. Stored encrypted and never logged. |
| Server Identity | Nothing. It signs with the Google Cloud identity the server already runs as. Whether it works depends on how the server was provisioned, and it is offered only where the deployment allows accounts to authenticate this way. |
Even with Server Identity, this is still an account record of its own, with its own project and location—which is what separates it from a step falling back to the deployment's configuration.
Connecting
Credential-based: there is no Connect button. Fill in the project, location, and credentials and save.
Not the same as Gemini
A Gemini connection holds an AI Studio key, which is a different product with its own endpoint, quotas, and terms—not a smaller version of this one.