{"version":"2.0.24","anchor":"experimental-model-defaults-for-pro-plan","canonical_anchor":"experimental-model-defaults-for-pro-plan","heading":"Experimental Model Defaults for Pro Plan","tier":null,"area":null,"scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.0.24\/e\/experimental-model-defaults-for-pro-plan","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.0.24","markdown":"### Experimental Model Defaults for Pro Plan\n\nPro plan users may be assigned to experiments that change default model selection:\n\n- **Haiku default**: Some Pro users may see Haiku 4.5 as default instead of Sonnet 4.5 (cost optimization)\n- **Sonnet 1M default**: Users with 1M context access may default to Sonnet 4.5 [1M] instead of [200K]\n\nThese are A\/B tests controlled by feature flags and not visible to all users.\n\n**Evidence**\n\nNew functions `r_1()` at line 144169 and `QH0()` at line 144180 in pretty-v2.0.24.js"}