Claude (RAiN provided)

Included with RAiN — no key, no setup.

What it is

Claude, included with RAiN. Nothing to connect, no key to hold, no separate bill — every project can use these models from the moment it exists.

When to reach for it

This is the default and the right starting point for almost everything. Build with the fast model while you are iterating, and move a step up only where you can see the judgement is not good enough. A watcher that compares two numbers needs no model at all; an agent drafting a reply to an angry customer does.

What you need

Nothing. These models are included with RAiN.

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.

Open the project and stay on the Visual Editor tab.
Open an agent and choose one of these models.
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

claude-haiku-4-5
claude-sonnet-5
claude-opus-4-8

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

Included. There is no separate bill and no key to hold — the daily run quota is what bounds usage, not a balance somewhere.

When it goes wrong

A run says the daily limit is reached. That is the run quota, not the model — see Running agents.