xAI (Grok)
Bring the business's own xAI (Grok) key.
What it is
Grok models, using the business's own xAI key.
When to reach for it
A niche choice — pick it when a client asks for it by name, or when you have tested it against your own prompts and preferred the result.
What you need
An API key from xAI (Grok), 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.
- 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
grok-4grok-4-fast
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 xAI (Grok) 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
Rate limits arrive early on new accounts. If runs fail in bursts rather than individually, that is usually why.
See also
- Models & LLM connections — choosing a model per agent
- Designing agents — role, goal and when judgement is needed
- Running agents — quotas, traces and failed runs

