TokenXWhich parts of this need deep reasoning, and which don't?TokenXSplit this across cheap agents wherever the work is independent.TokenXKeep this on the cheapest model that can do it correctly.

By default, every task in a Codex session runs on whichever model you picked - the same deep reasoning for a one-line typo fix as for a concurrency bug. TokenX chooses per task instead.

技能

Route Codex agents