alt Hacker NewsGPT-5.4 works amazingly well.
I’ve moved away from Claude and toward open-source models plus a ChatGPT subscription.
That setup has worked really well for me: the subscription is generous, the API is flexible, and it fits nicely into my workflow. GPT-5.4 + Swival (https://swival.dev) are now my daily drivers.
Replies
Yeah it's much better, another plus is you can use it with OpenCode (or other 3rd party tools) so you can easily switch between Codex and most other models by alright companies (not Anthropic or Google).
I hit the limits on the lower tiers of Codex just as fast as with Claude. At the moment I'm cycling between Claude, Codex, GLM5.1, and Kimi. The latter two are getting good enough, though, that I can make things go really far by doing planning with Opus and then switching to one of the cheap models for execution.
Chatgpt has better limits however the responses even on 5.4 xtra thinking are not as good as sonnets. Wish Claude would get their house in order.