Copilot code completion now uses the GPT-4.1 Copilot model

GitHub Copilot code completion now uses the GPT-4.1 Copilot model.

The new model expands on GPT-4.1’s coding capabilities and extends its knowledge cutoff with additional high-quality training data. It has been refined with reinforcement learning to improve suggestion relevance based on your feedback.

The model will automatically become available to users on all plans. You’ll see it in the code completion model picker. To learn more about working with code completion, see the code suggestions documentation.

Let us know your feedback on the new model in the GitHub Community.