An OpenAI key belongs to a project inside an organisation, and that choice is made at creation - it decides the model set and the budget.
OpenAI Supported Models ->Every OpenAI key belongs to one project inside one organisation, and you pick that project while creating it. The project decides which models the key reaches and which budget it charges. It is an API platform account, billing separately from any ChatGPT plan on the same email.
An organisation runs on a prepaid credit balance. Top up the balance; requests draw it down. Enabling auto-recharge refills the balance on its own, which removes the ceiling the deposit gave you.
Open Models with Ctrl + Shift + M. Should the Setup AI Models wizard appear, press More Services. Then Add -> OpenAI, paste into API Key, press Models, and watch the list build below the panel (add and manage your keys).
Limits live at Settings -> Limits, on the organisation and again per project if you keep work apart. Fill Organization ID under Advanced only when the account holds more than one organisation.
Direct Connection can be turned on once a key or a custom API Host is set - a host by itself is enough here. It starts off.
Direct Connection works only with your API key stored in the browser, and with an AI service that permits direct browser calls (CORS). Where it cannot be used, requests route through the Big-AGI fast edge servers instead - everything still works, within the standard upload size and time limits.
BIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego