Picking the right effort level
Technique
Effort level controls how long the model thinks and how much it checks before answering. Picking the right level lets you match the model's thinking to the task. Opus offers low, medium, high, extra-high and max.
Theo's current stance
Theo now calls high "the goat" and his default for Opus 5.5: it rarely fails, doesn't overdo things, and isn't much less token-efficient than medium. He calls low and max garbage.
Try it
- Have your agent run Opus 5.5 on high as the default.
- If you stay on medium and it misses things, bump to high or extra-high.
- Avoid low and max.
- Switch levels mid-session when needed; this no longer breaks the cache, the reused earlier context.
First seen
8:36
This model's interesting in this particular way. It feels like low and max are dangerous and generally best avoided, but medium, high, XH high, those all have seemed really good for my experience so far.
Every mention
9:16
High is the goat. I have rarely found tasks high couldn't complete and it also doesn't do too much and it is not that much less token efficient. I have been very happy with high.
8:36
This model's interesting in this particular way. It feels like low and max are dangerous and generally best avoided, but medium, high, XH high, those all have seemed really good for my experience so far.
13:00
…means that you would bust cash whenever you changed your reasoning levels, which isn't great. Now you can change reasoning levels midsession without busting cash. Very nice change.
Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.