GPT-5.4 mini, OpenAI’s latest fast version of their agentic coding model GPT-5.4, is now rolling out in GitHub Copilot. In early tests, GPT‑5.4 mini appears to be OpenAI’s highest-performing mini model yet. It delivers the fastest time to first token, is stronger at codebase exploration, and is especially effective when using grep-style tools.

Note, while this model is launching with a .33x premium request multiplier, pricing is tentative and subject to change

Availability in GitHub Copilot

GPT-5.4 will be available to Copilot Pro, Pro+, Business, and Enterprise users.

You’ll be able to select the model in the model picker in:

  • Visual Studio Code and later in all modes: chat, ask, edit, agent
  • Visual Studio version and later in all modes: agent, ask
  • JetBrains versions and later, in all modes: ask, edit, agent
  • Xcode versions and later in all modes: ask, agent
  • Eclipse versions and later in all modes: ask, agent
  • github.com
  • GitHub Mobile iOS and Android
  • GitHub CLI

While the model appears in all versions above, prompting and model parameters work best in the most recent versions of each product, so we highly encourage you to upgrade to the latest version.

Enabling access

  • Enterprise & Business plans: Administrators must enable the GPT-5.4 mini policy in Copilot settings. Once enabled, users in that organization will see GPT-5.4 mini in the model picker in Visual Studio Code.  

  • Bring Your Own Key: Select Manage Models from the picker, choose GPT-5.4 mini, and enter your API key when prompted.

Learn more

To explore all models available in GitHub Copilot, see our documentation on models and get started with Copilot.

Share your feedback

Join the GitHub Community to share your feedback.