Everyone says that you hit token limits after some time using either Claude Code or its web version. Even though GPT 5.5 is cheaper and doesn't impose token limits, it's just too non-nuanced. The only points for which I still stick to using Claude are these:

- I actually rarely hit the token limits using my $20/mo web plan (switch chats when the current one feels "bloated" due to huge context and therefore the token drain), which even covers some of my coding sessions using Claude Code. - The visuals and "interactive" elements are still not introduced in GPT's web UI, unlike Claude's. - The nail in the coffin is the fact that Opus 4.8/5 is just BETTER at doing my RTL verification review jobs than GPT 5.5.

I am not glazing the model; it's just a personal preference for getting the job done...