GitHub Copilot’s context window varies by model, and most current models let you switch from the default size to an extended 1 million token context window, according to GitHub’s supported models documentation.
As of November 9, 2026, GitHub lists the 1 million token option for Claude Opus 5.5, Opus 5, Sonnet 5.5, Sonnet 5, Haiku 5.5, Fable 5.1, GPT-6.1 Sol, GPT-6 Astra, GPT-5.6 Sol, GPT-5.3-Codex and Kimi K3, among others. Claude Opus 4.8 fast mode does not support it. The extended window works only in Visual Studio Code and Copilot CLI.
GitHub does not publish a default size for every model. Its pricing table bills long-context rates above 272K input tokens for GPT-6 and GPT-5.6 Sol models, above 200K for Grok 4.7 and above 100K for Claude Haiku 5.5, and larger contexts use more AI credits. In Copilot CLI, type /context to see your model’s total capacity; compaction starts at about 80% full.
Related: GitHub Copilot CLI 1.0.105 power-user guide, How much does GitHub Copilot cost? and What is the Cursor context window?
Sources: GitHub Docs, Supported AI models in GitHub Copilot; GitHub Docs, Models and pricing for GitHub Copilot; GitHub Docs, Managing context for GitHub Copilot
Image: GitHub mark (Octicons) by GitHub, MIT license, via Wikimedia Commons. Placed on a white background and resized. GitHub and Copilot are trademarks of GitHub, Inc. FreeAnswers is not affiliated with or endorsed by GitHub.