{"version":"2.1.295","anchor":"1m-context-beta-rejection-is-now-handled-per-model","canonical_anchor":"1m-context-beta-rejection-is-now-handled-per-model","heading":"Models that reject the 1M-token context option stop failing every request","tier":"notice","area":"Long Context","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295\/e\/1m-context-beta-rejection-is-now-handled-per-model","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295","markdown":"### Models that reject the 1M-token context option stop failing every request\n\nIf a model rejects the 1M-token context option, Claude Code leaves it out for that model and tries again after `\/clear`, compaction, resume or provider change\n\n**What**\n\nClaude Code can ask for a 1-million-token context window (how much conversation the model can hold at once) by sending a beta header, a marker on the request that turns on a trial feature.\n\nIf the service rejects a request with that header and the same request works without it, Claude Code now leaves the header out for that model and logs a warning. It sizes the context window without the 1M option. It tries the header again after any of these:\n\n- `\/clear`\n\n- A compaction (summarising the conversation to free space)\n\n- A resume\n\n- A change of provider\n\n**Why**\n\nA model or provider that does not accept the 1M option no longer makes every request fail.\n\n- Area: Long Context\n- Tier: You'll notice\n- Useful: 3\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}