Codex Client

Scope

This guide applies to Codex desktop clients, Codex IDE extensions, and Codex clients that read the local ~/.codex configuration directory. After setup, Codex will call models through the cnAPI relay.

Before You Start

1. Sign in to cnAPI.
2. Make sure your account has balance.
3. Create an API key in the cnAPI console.
4. Install the Codex client or the related IDE extension.

How It Works

Codex clients read configuration from the local Codex directory:

Use the following values for the cnAPI relay:

One-Click Setup

Windows

Open PowerShell and run:

Configure Codex Client

Use the following stable Windows command:

curl.exe --ssl-no-revoke -fsSL https://cnapi.vip/helper/codex-client-setup.ps1 -o "$env:TEMP\codex-client-setup.ps1"
PowerShell -NoProfile -ExecutionPolicy Bypass -File "$env:TEMP\codex-client-setup.ps1"

Enter the following when prompted:

1. API base URL: press Enter to use the default https://cnapi.vip
2. API key: paste the key created in the cnAPI console

The script writes:

%USERPROFILE%\.codex\config.toml

The script stores the cnAPI key in the active provider's experimental_bearer_token instead of relying on auth.json.OPENAI_API_KEY, avoiding API_KEY_REQUIRED / 401 Unauthorized errors in newer Codex builds.

macOS / Linux

Open Terminal and run:

Configure Codex Client

bash <(curl -fsSL https://cnapi.vip/helper/codex-client-setup.sh)

Enter the following when prompted:

1. API base URL: press Enter to use the default https://cnapi.vip
2. API key: paste the key created in the cnAPI console

The script writes:

~/.codex/config.toml

Manual Setup

You can also create the files manually.

config.toml

Write this to ~/.codex/config.toml:

model = "gpt-5.6-sol"
model_provider = "cnapi"
model_reasoning_effort = "high"
disable_response_storage = true

[model_providers.cnapi]
name = "cnAPI"
base_url = "https://cnapi.vip/v1"
wire_api = "responses"
supports_websockets = false
experimental_bearer_token = "sk-your-cnapi-key"

auth.json

Do not put the cnAPI key in auth.json for the current Codex configuration. Keep auth.json only as the OpenAI account login cache; model requests should use the provider-scoped experimental_bearer_token in config.toml.

Start the Client

After configuration, reopen the Codex client or restart your IDE.

If the client is already running, fully quit and start it again so it reloads ~/.codex/config.toml and ~/.codex/auth.json.

Verify Requests

1. Start a simple task in the Codex client.
2. Open the cnAPI console.
3. Check Usage Logs for the corresponding request.

If the request appears in Usage Logs, the Codex client is using the cnAPI relay.

Troubleshooting

The client still uses the official account

Confirm that the client supports the local ~/.codex configuration. Some official cloud Codex entries only use ChatGPT account login and do not support a third-party API endpoint, so they cannot be relayed through cnAPI.

Authentication failed

Check that OPENAI_API_KEY in auth.json is complete and has no leading or trailing spaces or line breaks.

Model unavailable

Confirm that your cnAPI account can use gpt-5.6-sol. If your account uses a different Codex-compatible model, update the model field in config.toml.

Changes do not take effect

Fully quit the Codex client or IDE and reopen it. If needed, remove old official login cache and run the one-click setup script again.