Claude Code runs current Claude models with a 1 million token context window by default, according to Anthropic’s Claude Code model configuration docs.
As of November 9, 2026, the Fable models, Sonnet 5 and later, Haiku 5.5, and Opus 4.7 and later use the 1M window natively, with no [1m] suffix needed. Opus 4.6 and Sonnet 4.6 reach 1M only through their [1m] variants: Opus 4.6 with 1M context is included on Max, Ultra, Team and Enterprise plans, while Sonnet 4.6 with 1M context requires usage credits on every plan. A model ID that Claude Code does not recognize is assumed to have a 200K window.
Claude Code compacts the conversation automatically, and on native 1M models it does so at about 967K tokens by default. You can compact earlier with a command such as /autocompact 500k, or keep sessions at 200K by setting CLAUDE_CODE_DISABLE_1M_CONTEXT=1. The status line can show how much of the window is in use.
Related: What is the Claude context window?, Claude Code usage limits on each plan and How much does Claude Code cost?
Sources: Claude Code docs, Model configuration; Claude Code docs, Explore the context window; Claude Code docs, Status line
Image: Claude logo by Anthropic, public domain (trademarked), via Wikimedia Commons. Placed on a white background and resized. Claude and Claude Code are trademarks of Anthropic. FreeAnswers is not affiliated with or endorsed by Anthropic.