Allow setting default model per provider

Resolved 💬 1 comment Opened May 19, 2025 by MrLightful Closed Aug 7, 2025

What version of Codex is running?

0.1.2505172129

Which model were you using?

_No response_

What platform is your computer?

Darwin 24.4.0 arm64 arm

What steps can reproduce the bug?

I would expect to be able able to set default model per provider in config file.

Something like this:

{
  "provider": "ollama",
  "approvalMode": "full-auto",
  "fullAutoErrorMode": "ask-user",
  "notify": true,
  "providers": {
    "openai": {
      "name": "OpenAI",
      "baseURL": "https://api.openai.com/v1",
      "envKey": "OPENAI_API_KEY",
      "model": "o4-mini"
    },
    "ollama": {
      "name": "Ollama",
      "baseURL": "http://localhost:11434/v1",
      "envKey": "OLLAMA_API_KEY",
      "model": "qwen2.5-coder:14b"
    }
  }
}

And the expected behaviour would be that by default codex enables ollama provider. But if specified, codex --provider openai it would enable o4-mini without additional inputs.

What is the expected behavior?

_No response_

What do you see instead?

_No response_

Additional information

_No response_

View original on GitHub ↗

This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗