Are you still using Codex and GPT models? Or did you change to Claude Code because of Opus 5.5?
I’m still on Sol 6.1 - is there a huge difference? I want to hear opinions from devs, not from benchmarks :D
Commit
b91233f
Using Codex with Sol 6.0 for implementation work and Claude Code for reviews. Good mix so far.
Are you on $20 subscriptions for both? Are the limits enough for you? I heard that Claude offers much generous limits.
200 for codex and 20 for claude. Was on 1x 200 for claude for a few months. Then a second one because limits of the first one were exhausted pretty quickly. Then switched to codex 200 + claude 200, saw that codex works better and reduced claude to 20.
commit b91233f