GitHub Copilot model policy API: companies can now control which AI models developers use

GitHub made its Copilot model policy API generally available on 19 October 2026, letting enterprises set which AI models each organisation, team or agent app may use. Here is what AI coding tool governance means for buyers of software.

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.

← All research

More research.

GitHub secret scanning cuts false alarms for AWS, Google and Alibaba cloud keys and adds a SpaceX detector

GitHub's 5 November 2026 secret scanning update tightens detectors for AWS, Google Cloud and Alibaba keys, relevant to teams building software with AI coding tools that can paste credentials into code.

Read ›

GitHub's Copilot code review can now be managed by API, with review effort levels and AI credit costs shown

GitHub's 6 November 2026 update lets organisations manage Copilot code review by API and see the review effort and AI credits each AI code review used, a sign AI-assisted development is becoming auditable.

Read ›

GitHub's Copilot impact dashboard now counts chat and VS Code agent use, and drops the 'passive users' label

On 6 November 2026 GitHub added Copilot Chat and the VS Code Agents window to its Copilot impact dashboard, bringing it to nine tracked experiences, and renamed 'Passive users' to 'Chat-first users'.

Read ›

Claude Code 2.1.319: a setting that denies permission prompts so AI agent runs don't stall

Claude Code 2.1.319 (6 November 2026) adds a permissions.denyInsteadOfPrompting setting and moves long MCP tool calls to the background, a sign AI-assisted development is being built for unattended runs.

Read ›

GitHub now reports how often developers act on Copilot code review comments

On 5 November 2026 GitHub added code review metrics, including an addressed rate, to the Copilot usage metrics API. For AI software development buyers, it is the first first-party number for how much AI review feedback is acted on.

Read ›

Dependabot can now keep AI agent skills and prompts up to date

GitHub's Dependabot gained Agent Package Manager (APM) support on 3 November 2026, treating AI agent skills, prompts and instructions as dependencies that need updating like any other software.

Read ›

Start a project

Building with AI? Let's talk.

Tell us what you are building. We'll give you an honest view of the right approach.

Start a projectSee our work