← Back
GitHub
OpenAI's GPT-5.4 now available in GitHub Copilot with improved agentic reasoning
GitHub Copilot · releasemodelfeature · github.blog ↗

GPT-5.4 Now Available in GitHub Copilot

OpenAI's latest agentic coding model, GPT-5.4, is now generally available in GitHub Copilot. Based on early testing, the model shows improved success rates for real-world coding tasks and demonstrates enhanced logical reasoning and task execution capabilities for intricate, multi-step, tool-dependent processes.

Availability

GPT-5.4 is available to all GitHub Copilot plan tiers:

  • Copilot Pro
  • Copilot Pro+
  • Copilot Business
  • Copilot Enterprise

You can select the model from the model picker in the following environments:

  • Visual Studio Code (v1.104.1+) — chat, ask, edit, and agent modes
  • Visual Studio (17.14.19+) — agent and ask modes
  • JetBrains (1.5.66+) — ask, edit, and agent modes
  • Xcode (0.48.0+) — ask and agent modes
  • Eclipse (0.15.1+) — ask and agent modes
  • github.com
  • GitHub Mobile (iOS and Android)
  • GitHub CLI
  • GitHub Copilot Coding Agent

What Developers Need to Know

While GPT-5.4 appears in all supported versions, prompting and model parameters work best in the most recent versions of each IDE and tool. Upgrading to the latest versions of your development environment is strongly recommended for optimal performance.

For Copilot Enterprise and Business plan administrators, GPT-5.4 must be enabled in Copilot settings before users can access it.

Refer to the GitHub Copilot documentation on supported models to explore all available models and learn how to get started.