Add manual reasoning-depth control for Brain/Max
completed
Log In
Zeb
updated the status to
completed
Thanks for asking for this. You can now set how hard Brain thinks: open the model picker, choose a reasoning model, and pick Auto or a specific thinking level.
Which levels you get depends on your plan, and Max unlocks the deepest one. Tell us how it works for you.
J
James Birney
Thanks for the suggestion. A manual control over Brain/Max reasoning depth could help users balance response quality and speed for different tasks. I’ve added this to our team’s backlog. Good news: this means it’s on the roadmap, but I don’t have an ETA yet.