"20X the usage of pro" still sounds like quotas where the hammer could fall as it becomes less of an experiment for a limited number of power users..
The costs of self hosting some reasonable size models for a development group of various sizes is what I would want to know before investing in the skills to do a high usage style that might be being mostly bankrolled by investors for now.
My guess is: absolutely not, at least not for more than a few minutes. Subagents chew through tokens at a very high rate, and this system makes heavy use of subagents.
Claude Max is fixed cost
"20X the usage of pro" still sounds like quotas where the hammer could fall as it becomes less of an experiment for a limited number of power users..
The costs of self hosting some reasonable size models for a development group of various sizes is what I would want to know before investing in the skills to do a high usage style that might be being mostly bankrolled by investors for now.
Is it doable with just pro?
My guess is: absolutely not, at least not for more than a few minutes. Subagents chew through tokens at a very high rate, and this system makes heavy use of subagents.