Hello all, been trying to switch away from Claude Code and have been trailing this:

- Harness: Opencode (via Openchamber) - Subscription: GitHub Copilot (50$) - API Usage (beyond subscription): Open router - Free models: Opencode go

Here's the models I've trialed and like:

- Large (alternative to Opus): GPT 5.3 Codex - Medium (alternative to Sonnet): Minimax 2.7 - Smol: GPT 5.4 mini

these models are not yet on par to their respective Claude alternatives for me, but maybe I need to switch to something else or tune them, what have you been using?

Also looking for nice Opencode plugins, skills, completion providers (alternative to Cursor that I could use with Zen).

Happy to hear about your choices and experience

I ping pong back and forth between claude code and codex.

In my experience (very subjective, obviously) for backend/"logical" tasks Codex seems to outperform Claude.

For front-end/UX related tasks Claude wins easily.

Overall, Claude does seem to be a little better in other areas too.

Codex's biggest advantage in my personal opinion, however, is usage. I think maybe once in several months did I even get close to hitting my limit with the $20 plan.

With Claude, however, I feel like I can sneeze and half my weekly usage is gone. Same $20 price tag.

That's been my experience, I'm sure it differs user to user though.

Just pay the $20 for codex and use it. It's the only real alternative.

I've gone fully custom and would never look back. All of the popular tools lack the experience I'm after, generally lacking the advanced customization I have found makes weaker models more capable. I'm also moving towards open weight models.

The underlying motivation is to avoid Big Ai as much as possible. Incentives are not aligned.