What model do you use the most? I'm 95% on DeepSeek V4.1 Flash, cost effective and very fast.
Commit
08b50f5
My frequency of usage : Opus 5.5 (brainstorming/exploration/security) > Gpt 6 Luna (all my Hermes agents for daily life, professional work delegation) > Sonnet 5.5 (execution) > Sol 6 (adversial critic/second point of view) > Haiku 5.5 (code exploration, summary, dumb execution supervised/reviewed)
I care about privacy, so I use only them because I've unselected the training agreement on my data.
commit 08b50f5