Auto reasons one level deeper on every tier

Auto now asks its models to think harder before they act. Fast, Balanced, and Max each run every one of their models one reasoning level higher than before, and so does every tier when Auto runs on a subscription you connected. The tiers still choose the same models in the same order. Each model spends more time reasoning before it answers, so replies and each step of a workflow are more thorough and can take a little longer to start. Read how Auto chooses models on the models page.

How it works

• Fast runs GPT-6.1 Terra, Claude Haiku 5.5, Gemini 3.8 Flash, and Grok 4.7 at high, up from medium.
• Balanced runs Claude Sonnet 5.5, GPT-6.1 Sol, Gemini 3.8 Flash, and Grok 4.7 at high, up from medium.
• Max runs Claude Opus 5.5, Grok 4.7, and Gemini 3.8 Flash at high, up from medium, and GPT-6.1 Sol at extra high, up from high.
• Your own subscriptions go up a level too. When Auto runs on a Claude, ChatGPT, Grok, or Gemini subscription you connected through Token Tunnel, Fast and Balanced now reason at high and Max at extra high. Gemini 3.8 Flash runs at high on every tier, the most it offers.
• Picking a model directly is unchanged. It keeps its own default, and the reasoning picker beside the model still sets any level for a conversation or workflow.