Neither Claude code neither codex is actually vendor specific, they just don’t tell you that you can config other providers, including local
However opencode is pretty nice too, so if you like it, use that. I personally find that opencode with GLM 5.2 or Kimi K2.7 isn’t actually that great, it’ll hallucinate more than Claude code or Codex with their respective first party models. I think it’s the models themselves rather than opencode itself though, as when I use GPT for planning and hand it off to deepseek flash to do the actual work, it’s more or less fine.
Not impossible, but also the thinking process reduces the need for something like that. Anything in the context gets regurgitated back and forth multiple times so the model has multiple opportunities to flag something as being weird.
Incidentally if you actually want to do something like that yourself, I believe OpenRouter has a feature for that. But of course it means you can essentially add up each model’s costs and that’s your new cost per prompt (not exact since output token count will differ, but on average).
Neither Claude code neither codex is actually vendor specific, they just don’t tell you that you can config other providers, including local
However opencode is pretty nice too, so if you like it, use that. I personally find that opencode with GLM 5.2 or Kimi K2.7 isn’t actually that great, it’ll hallucinate more than Claude code or Codex with their respective first party models. I think it’s the models themselves rather than opencode itself though, as when I use GPT for planning and hand it off to deepseek flash to do the actual work, it’s more or less fine.
I suspect behind the scenes, the first parties are sending your requests to multiple targets and sending you back quorum.
Not impossible, but also the thinking process reduces the need for something like that. Anything in the context gets regurgitated back and forth multiple times so the model has multiple opportunities to flag something as being weird.
Incidentally if you actually want to do something like that yourself, I believe OpenRouter has a feature for that. But of course it means you can essentially add up each model’s costs and that’s your new cost per prompt (not exact since output token count will differ, but on average).