Skip to main content
Codex uses OpenAI-compatible Responses traffic. Add OmniaKey as a custom provider and set your API key in the shell that launches Codex.

Configuration

In ~/.codex/config.toml:
Then run:

Models

Use gpt-5.5 or any supported OpenAI-compatible model from Models.
wire_api = "responses" is the current Codex CLI shape for custom providers. If you keep an older wire_api = "chat" provider block, update it before testing OmniaKey.