Jérôme Tamarelle: “What model do you use the most? I'm 95% on DeepSeek V4.1 Fla…”

What model do you use the most? I'm 95% on DeepSeek V4.1 Flash, cost effective and very fast.

10:21 AM · Oct 17, 2026commit 5f4b92f

That’s what @tom is gonna use

DeepSeek, it’s capable of doing what I want and it’s so ridiculously cheap that I barely ever have to top up my account. I’ll build an entire project and it will bill me $0.70

Jérémy Marodon @Th3Mouk8h

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…

Timo Bakx @TimoBakx8h

Mostly Opus 5.5, with some Fable sprinkled around. I let Opus spawn some Sonnet or Haiku for bigger things that can be done in parallel.

nunomaduro @nunomaduro8h

so @paulinevos was suggesting that model yesterday, need to try it out;