# Microsoft AI brings MAI-Code-1.1-Flash to GitHub Copilot for local execution

Developers will be able to run agentic coding tasks on-device using MAI-Code-1.1-Flash inside GitHub Copilot without paying inference fees for local model calls.

Language: en
Time zone: America/Los_Angeles

HTML: https://didcodexreset.com/news/e1c591c1a6de43ff863fe52e.html

Content language: en
Localization state: sameLanguage

Source: Microsoft AI · Published 10/7/2026, 13:35:03

Microsoft AI announced that MAI-Code-1.1-Flash will run locally through on-device model calls inside GitHub Copilot, providing local agentic coding support directly on user devices.

Model calls executed locally via MAI-Code-1.1-Flash will carry no inference charges.

Tags: Microsoft AI, GitHub Copilot, On-Device AI, MAI-Code

[View original post](https://x.com/MicrosoftAI/status/2107926901150908483)