Skip to main content
Have an API key from the ViVi-API dashboard ready, and confirm that its group supports your chosen model. Back up any existing configuration before merging the fields below.

Configuration files

Edit config.toml and auth.json in this directory, creating them if they do not exist. If CODEX_HOME is set, use that directory instead.
Choose a model available to your account that supports the Responses protocol. The example uses the ViVi-API model ID gpt-6-astra. Save the files, restart Codex, and test in a new conversation.
Codex uses the Responses protocol, so the gateway must support /v1/responses. Models or channels that only support Chat Completions may not work with Codex. Do not commit auth.json to a repository: it contains your API key.
This example stores credentials in a file. Back up your existing settings if you already use ChatGPT sign-in or another provider. For supported client settings, see the official Codex configuration reference. See the Integration overview and FAQ for more help.