Integrations · Category
AI & Models integrations
62 AI & Models connectors your customers can activate inside your product, configured to their own account and maintained by fastn.
These tools expose models, requests, outputs and more. Teams use them to give your product and your agents a model call each customer pays for themselves. The part that costs time is that per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed, which is the work fastn takes on rather than leaving in your backlog.
All 62 AI & Models connectors
Teams that use these
AI & Models integration FAQ
What can my product do with AI & Models integrations?
Your customers connect their own account, and your product reads and writes their models, requests, outputs through one governed connection. Give your product and your agents a model call each customer pays for themselves.
What is hardest about integrating AI & Models tools?
Per-customer keys, quotas and cost attribution matter more than schema here, because every call is billed. fastn owns the auth, token refresh, rate limits, pagination and breaking-change fixes across every connector in this category, so that work does not land in your backlog.
Do my customers each connect their own account?
Yes. Every connection is scoped to the individual customer, so each authorises their own account and only ever reaches their own models, requests, outputs. That per-tenant isolation is the point of an embedded integration: you support the long tail of customer setups without maintaining an integration per customer.
Which AI & Models tool should I support first?
Start with whichever your customers already run, not with the largest vendor. All 62 connectors here share one interface in your product, so adding a second is configuration rather than another integration project, and the order you add them in does not lock anything in.
Can AI agents use AI & Models integrations?
Yes. Every connector here is exposed to your agents through the fastn MCP gateway, with permissions scoped per tenant and every call audited, so an agent reaches exactly what that customer authorised and nothing else.