I’ve been using Claude Code ($20/month) for about two weeks now, and with one of the token usage monitors I can handle most of what I need. I also have the $20/month ChatGPT plan. I know I could try Codex CLI, but I’ve been hesitant since I’ve seen people suddenly hit the limit and get locked out for a week. The problem is that there’s no way to check usage. So I’m wondering if this update improves token usage management, or if there’s now a way to actually see our usage so we don’t end up tripping the limit without any warning.

Same setup as your. Started with codex 2 days ago on a large 3d engine project. Spend at least 20 hours prompting. One time I received a message. Try again in 4 minutes. I generally let Gemini create a prompt and then paste it inside codex. For example is asked gemeni to make a plan for a subdivided lod terrain render with shadow map functionality etc. It took codex almost an hour to execute it. Did an alright job. Quite impressed.