{"version":"2.1.301","anchor":"1m-context-window-logic-reworked-for-models-needing-opt-in","canonical_anchor":"1m-context-window-logic-reworked-for-models-needing-opt-in","heading":"Models with only beta 1M context support are capped unless you opt in","tier":"notice","area":"Context Window","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301\/e\/1m-context-window-logic-reworked-for-models-needing-opt-in","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.301","markdown":"### Models with only beta 1M context support are capped unless you opt in\n\nModels whose 1M-token window is only a beta now get the default window unless the 1M opt-in applies\n\n**Unclear.** Which models are affected is not stated.\n\n**What**\n\nThe context window is how much conversation, code and other text a model can hold at once. Claude Code has reworked how it decides the size of that window:\n\n- When your opt-in to the 1-million-token window is honored, the window is 1 million tokens.\n\n- A model that supports 1 million tokens only as a beta, and not natively, is capped at the default size unless there is an opt-in or another override.\n\n- When Claude Code tidies up a model name, it adds the `[1m]` marker only if the model supports 1 million tokens natively.\n\n**Why**\n\nFor some models this can change how much context is available and how soon Claude Code compacts the conversation. Compacting means summarizing older parts of the conversation to free up space.\n\n- Area: Context Window\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: yes"}