On 19 October 2026 GitHub announced a Copilot model policy API. Enterprise and organisation administrators can now read and change, through code, which AI models are available in Copilot. The read and update endpoints are generally available at four levels: the whole enterprise, enterprise teams, agent apps, and individual organisations.
What changed
Until now, controlling which models developers could pick generally meant clicking through settings screens. An API means a company can set a policy once, apply it across hundreds of teams, and check that it has not drifted. GitHub describes two ways to delegate: control can sit with each organisation, or with enterprise teams and agent apps.
The context
Copilot has been adding models quickly, and GitHub has also flagged that some models were deprecated on 19 October, with more to follow in mid-November. We covered the rapid model additions in an earlier signal on choice overload. Both facts point the same way: the model your developers used last month may not exist next month, and nobody wants that decision made ad hoc.
GitHub’s post does not say which plans the API needs and says nothing about pricing, so check before assuming it applies to you.
So what
The interesting point for buyers is governance, not the API. Model choice affects cost, quality, and where your code and data are processed. Large organisations are now building central control over it. If you are commissioning software, expect to be asked, and ask your supplier in return: which AI models touch our code, who approved them, and what happens when one is retired?
A supplier who can answer that clearly is running AI development as a managed process. That is how we approach AI-assisted development at BuildApps, and starting a project is the way to test it.