RAiN — Rivium AI Network
Back to Help

Google (Gemini)

Bring the business's own Google (Gemini) key.

What it is

Gemini models, using the business's own Google AI key.

When to reach for it

Useful where a client is already inside Google's ecosystem, and for very long inputs where Gemini's context is the cheapest way to hold a lot of text at once.

What you need

An API key from Google (Gemini), belonging to the business this project is for. It is encrypted at rest and only ever used to run that project's agents.

Connecting it

Model keys belong to one project, like every other credential in RAiN AI Studio. A package delivered to a business runs on that business's key and bills that business — not the expert who built it, and not RAiN.

  1. Open the project and stay on the Visual Editor tab.
  2. Open an agent and choose one of these models.
  3. If the project has no key for it yet, the form asks for one there and then.

The workspace-level LLM Connections page lists what exists and links here. It does not connect anything, because there is no project standing outside a project to connect it to.

Models available

  • gemini-3-flash
  • gemini-3-pro

Choose per agent. A sequence can mix them — a cheap model for classification and a stronger one for the step that writes to a customer.

What it costs

Billed by Google (Gemini) to the account the key belongs to. RAiN adds nothing and sees nothing beyond the tokens each run used, which the Execution tab shows.

When it goes wrong

It refuses a key that works elsewhere. Google issues different keys for Google AI Studio and for Vertex on Google Cloud. This takes the Google AI Studio one.

See also