OpenAI (GPT)

Bring the business's own OpenAI (GPT) key.

What it is

GPT models, using the business's own OpenAI key. The key belongs to the project, so the usage is billed to whoever owns that project rather than to you.

When to reach for it

Reach for it when a client already runs on OpenAI and wants their agents on the same account, or when a specific GPT model does something you have tested and preferred.

What you need

An API key from OpenAI (GPT), 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

gpt-5.2
gpt-5.2-mini

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 OpenAI (GPT) 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

The key is refused. Check it is the project's own key and that the OpenAI account has credit — an account at zero balance returns an authentication-shaped error that reads like a bad key.