Credentials. The key is stored as experimental_bearer_token in plaintext in config.toml, so keep the file private.
Who it is forA developer who uses Codex CLI and wants to switch between several gateway models without re-running any tool.
The problemCodex needs a provider block, a Responses API endpoint, and a model catalog file, and those are easy to get wrong by hand.
The outcomeCodex uses the gateway as its provider, and the chosen models appear in the built-in /model picker after one restart.
What you need first
- Node.js 18 or newer installed
- A gateway base URL that exposes /v1 and an API key for it
- A model id the gateway serves, or access to GET /v1/models so the picker can list them
- For Codex: a gateway that serves the Responses API (/v1/responses)
Steps
- Run
node bin/setup-gateway.mjs codexand enter the Base URL and API key. - In interactive mode, tick the extra models you want in the multi-select list, or leave only the main model for a headless run.
- Restart Codex once so it reads gateway-catalog.json at startup.
- Open
/modelin Codex and choose a gateway model. - Run
node setup-gateway.mjs statusand check the Catalog line.
Prompt for your agent
In the repo Sinholms/setup-gateway, run `node bin/setup-gateway.mjs codex --base-url <GATEWAY_BASE_URL> --api-key <API_KEY> --model <MODEL_ID> --yes`. Expect config.toml and gateway-catalog.json to be written in the Codex config directory. Verify that config.toml sets wire_api to responses and that model_catalog_json points to an existing gateway-catalog.json.
Caveat. The gateway must serve the Responses API (/v1/responses), because Chat Completions only gateways will not work with Codex directly.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Disclaimer
Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page