Setting up ChatGPT / Codex Desktop

Codex Desktop uses the same user profile as the Codex CLI. Create that profile once, then select it in the app. The file, context window, and checks are in Setting up Codex.

Values

Field	Value
Profile file	~/.codex/nexus.config.toml
Base URL	https://api.nexus-hub.tech/v1
Protocol	OpenAI Responses
Route	POST /v1/responses
Key	NEXUS_API_KEY

Steps

1. Create ~/.codex/nexus.config.toml as described in the CLI guide. Keep the key in NEXUS_API_KEY, not in the file.
2. Start Codex Desktop with that profile, or choose nexus if the app lists profiles.
3. Set the model to an id from GET /v1/models for this key.

export NEXUS_API_KEY="your_nexus_key"
codex --profile nexus

A project file .codex/config.toml cannot override the profile keys from the CLI guide. Keep the Nexus profile in ~/.codex.

Check

Open the app on the nexus profile and send a short prompt. A normal reply means the connection works.

If it does not work

Use the checks on Setting up Codex.

• 401 or invalid_key: NEXUS_API_KEY is missing, has extra spaces, or was revoked.
• unsupported_model: the id is not allowed on Responses. Pick another id from GET /v1/models.
• The profile did not apply: the file name is nexus.config.toml inside ~/.codex, and the app was started with --profile nexus.

Send support the route, error code, time, and x-request-id. Do not send the key or a full prompt.

Official reference: Codex config reference.