Skip to main content

One command →

curl -fsSL https://get.aireserve.com/install.sh | sh installs the aireserve CLI and configures Codex with the full gateway model catalog in its native model picker — reasoning-effort toggles included.

Or connect in one click →

The guided connect page creates a managed key and writes ~/.codex/config.toml for you.
Everything below is the manual equivalent.

Codex CLI / ChatGPT desktop app

Define a custom provider in ~/.codex/config.toml. Two auth styles work; pick one:
With env_key (or experimental_bearer_token) Codex never refreshes its model list from the provider, so its picker only shows the model you pinned. The aireserve CLI configures command auth plus a served model catalog instead — that is what unlocks the full native picker with per-model reasoning-effort options. If you want that experience, use the CLI; it is not practical to maintain by hand.

Codex SDK

The Codex runtime speaks the OpenAI Responses format, served at /v1/responses:
Legacy audacity_api_… keys and the AUDACITY_API_KEY name keep working everywhere aireserve_api_… does.