OpenAI Codex CLI Installation and MYAI168 Setup Guide — Linux

Goal of this guide: install OpenAI Codex CLI on a Linux desktop (Ubuntu / Debian as the example) and connect it to your own MYAI168 API, using gpt-5.6-sol.

Codex speaks the OpenAI format, so it connects to the MYAI168 "OpenAI-compatible endpoint" with gpt-5.6-sol.

Endpoint and Model

Endpoint   https://www.myai168.com/en/api/openai/v1
Model      gpt-5.6-sol

Important Security Notes

• Codex can read, write, and execute files in the working directory. In real use, cd into a project folder before starting it; do not start it in your home directory.
• Treat your API key like a password and never share it. If it leaks, revoke it in the MYAI168 dashboard and issue a new one.
• Verify with a "math question", not with "who are you" (model self-identification is unreliable); also cross-check with the API call records in the MYAI168 dashboard.

First check whether node --version and npm --version print version numbers. If not, install (Ubuntu / Debian):

curl -fsSL https://deb.nodesource.com/setup_lts.x | sudo -E bash -
sudo apt-get install -y nodejs

Or use nvm:

curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.40.1/install.sh | bash
source ~/.bashrc
nvm install --lts

echo $SHELL

• Ends with /bash → use ~/.bashrc
• Ends with /zsh → use ~/.zshrc

Wherever this guide says "shell config file" below, substitute yours.

Officially preferred: the standalone installer (no Node.js needed — you can skip the Node install in "0.5"; official docs https://developers.openai.com/codex/cli/):

curl -fsSL https://chatgpt.com/codex/install.sh | sh

Alternative: npm (requires Node.js). Do not use sudo (it causes permission problems); if you hit an npm permission error, point the npm global directory to your own home directory before installing:

npm install -g @openai/codex

Check:

codex --version

cc-switch is a cross-platform GUI; the Linux desktop interface is the same as on other platforms. (Prerequisite: cc-switch is installed — for installation, see the "cc-switch Linux" page in the Developer Center.)

1. Open cc-switch and click the "Codex" tab.
2. Click "+" to add, and choose Custom Configuration.
3. Fill in: Provider Name = MYAI168; API Key = your key; API Request URL = https://www.myai168.com/en/api/openai/v1
4. Advanced Options: keep "Needs Local Routing" OFF for now (turn it on only if the direct connection fails).
5. Save → Enable on the card.

Set the environment variable (Codex reads it via env_key; write it into your shell config file — use ~/.zshrc for zsh):

echo 'export MYAI168_API_KEY="your-key"' >> ~/.bashrc
source ~/.bashrc

Confirm cc-switch wrote it into config.toml:

cat ~/.codex/config.toml

If cc-switch did not write the file successfully (config.toml does not exist), write it manually with a heredoc (paste the whole block and press Enter):

mkdir -p ~/.codex
cat > ~/.codex/config.toml << 'EOF'
model = "gpt-5.6-sol"
model_provider = "myai168"

[model_providers.myai168]
name = "MYAI168"
base_url = "https://www.myai168.com/en/api/openai/v1"
env_key = "MYAI168_API_KEY"
wire_api = "responses"
EOF

Also confirm the key environment variable is set (the same export line as in Method A).

cd into a test folder before starting (not your home directory):

mkdir -p ~/cc-test
cd ~/cc-test
codex

Verify: once inside codex, ask a question that requires actual computation:

What is 123456 times 789? Reply with the number only.

If it answers 97406784 and the status bar shows gpt-5.6-sol, the connection works.

(Do not verify with "who are you" — model self-identification is unreliable; the API call records in the MYAI168 dashboard are authoritative.)

• codex command not found → run source ~/.bashrc (or source ~/.zshrc) or reopen the terminal; or the npm bin directory is not on PATH — find it with npm prefix -g and add it to PATH. (On Windows: open a new PowerShell.)
• no_pricing_info / model does not exist → that model is not registered on this endpoint; make sure you are using gpt-5.6-sol.
• 404 / responses not found (direct connection fails) → the MYAI168 endpoint may only support Chat Completions for this model. Go back to cc-switch, turn ON "Needs Local Routing", Save, Enable, and keep cc-switch running while you use Codex.
• 401 / unauthorized → check echo "[$MYAI168_API_KEY]" has a value; if needed add requires_openai_auth = false to the provider block. (On Windows: confirm [Environment]::GetEnvironmentVariable("MYAI168_API_KEY","User") has a value, and open a new window.)
• Status bar shows default / replies look like the official model → the config was not applied. Most common cause: env_key was filled with the key string instead of the variable name.
• Switch models → use /model inside a conversation; or change the model line in config.toml. One-off temporary switch: codex -c model='"model-name"'

Update Codex (standalone-installer installs: rerun the official install command; npm installs: use install @latest, not npm update -g):

curl -fsSL https://chatgpt.com/codex/install.sh | sh
# npm installs: npm install -g @openai/codex@latest

Config File Location

~/.codex/config.toml

Official Docs

• https://developers.openai.com/codex/cli
• https://developers.openai.com/codex/config-reference