Model allow-list

A model allow-list defines which AI models a person, team or application may call. Requests for any other model are rejected.

Why it matters for companies

It keeps cost in check, with expensive models only where they are needed, and it keeps unreviewed models out of production.

It also gives each application a stable, known set of models, which makes testing and review simpler.

Example

A customer-service app may use one approved model. The research team may use five, including an open-weight model for experiments.

How Standard Compute handles it

Decide which models each key can use, so every app and every team member gets exactly the models you approve.

See pricing

Standard Compute is an AI gateway for companies, with frontier and open-source models through one API. Your admins decide where requests are processed, which providers and models are allowed and what each person and app can spend.

Create a company workspaceor write to contact@standardcompute.com