{"version":"2.1.305","anchor":"context-window-resolution-changes-for-models-without-opt-in","canonical_anchor":"context-window-resolution-changes-for-models-without-opt-in","heading":"Context window size worked out differently for models without 1M opt-in","tier":"notice","area":"Models","scope":"individual","heads_up":true,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305\/e\/context-window-resolution-changes-for-models-without-opt-in","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.305","markdown":"### Context window size worked out differently for models without 1M opt-in\n\nClaude Code no longer treats models billed past 200K tokens as having a 1M window and uses new checks for long windows without opt-in\n\n**Unclear.** It is not clear which models get a different context size.\n\n**What**\n\nThe context window is how much text a model can take in at once, counted in tokens (small chunks of words). Claude Code no longer assumes a 1 million token window for models that are billed past 200,000 tokens without a limit. It now uses new checks on the window the service reports and on the long window available without opting in.\n\n**Why**\n\nThe context size Claude Code shows for some models may change.\n\n- Area: Models\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: yes"}