GPT-5.4 mini General Availability

OpenAI's GPT-5.4 mini is now generally available in GitHub Copilot. Early testing shows it's the company's highest-performing mini model to date, delivering the fastest time to first token and stronger performance at codebase exploration tasks.

Key Performance Characteristics

• Speed: Fastest time to first token among mini models
• Codebase Exploration: Significantly improved at understanding and navigating codebases
• Tool Integration: Especially effective with grep-style and command-line tools
• Pricing: Launching at 0.33x request multiplier (note: pricing remains tentative and subject to change)

Availability and Access

The model is available to all GitHub Copilot tiers: Pro, Pro+, Business, and Enterprise users. You can select it from the model picker in:

• Visual Studio Code, Visual Studio, JetBrains, Xcode, and Eclipse IDEs
• github.com and GitHub Mobile (iOS/Android)
• GitHub CLI

Important: The model works best with the latest versions of each IDE and GitHub product. Administrators managing Business or Enterprise instances must enable the GPT-5.4 mini policy in Copilot settings before users can access it.

Getting Started

For individual developers and Pro users, the model will appear automatically in your model picker once available. Enterprise and Business administrators should review GitHub's documentation to enable access. Users bringing their own API keys can select GPT-5.4 mini from the model picker and authenticate with their credentials.

Action item: Update to the latest IDE versions to fully leverage the new model's capabilities and ensure optimal prompting performance.