Connect Codex CLI to TeamoRouter

Codex CLI is OpenAI's terminal-based AI coding assistant. Install it first (section 1), then connect it to TeamoRouter (section 2). If Codex is already installed, skip straight to section 2.

1. Install Codex

  • Codex requires Node.js 22 or later. Install it from the official installer or via Homebrew (brew install node).

  • macOS users can also install Codex with Homebrew: brew install codex.
  • In your terminal, run:
plaintext
npm install -g @openai/codex
  • After installation, check the version:
plaintext
codex --version

2. Connect to TeamoRouter

Configure the provider

macOS / Linux

Open a terminal, paste the full block below, and press Enter:

plaintext
mkdir -p ~/.codex && cat > ~/.codex/config.toml <<'EOF'
model_provider = "teamorouter"
model = "gpt-5.6-sol"
model_reasoning_effort = "high"
[model_providers.teamorouter]
name = "TeamoRouter"
base_url = "https://api.teamorouter.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"
EOF

Windows

Open PowerShell and run:

plaintext
New-Item -ItemType Directory -Force -Path "$HOME\.codex" | Out-Null
@'
model_provider = "teamorouter"
model = "gpt-5.6-sol"
model_reasoning_effort = "high"

[model_providers.teamorouter]
name = "TeamoRouter"
base_url = "https://api.teamorouter.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"
'@ | Set-Content -Path "$HOME\.codex\config.toml" -Encoding UTF8

Set the API key

Replace <your-TeamoRouter-key> with the API key you created in the TeamoRouter dashboard.

macOS

plaintext
echo 'export OPENAI_API_KEY="<your-TeamoRouter-key>"' >> ~/.zshrc
source ~/.zshrc

Linux

plaintext
echo 'export OPENAI_API_KEY="<your-TeamoRouter-key>"' >> ~/.bashrc
source ~/.bashrc

Windows

plaintext
[Environment]::SetEnvironmentVariable("OPENAI_API_KEY", "<your-TeamoRouter-key>", "User")

Windows users: after running the command above, close the current PowerShell window and open a new one.

After both steps, run codex in the terminal. It will use TeamoRouter.

3. Enable Fast mode (optional)

Fast mode makes GPT-series models respond faster (gpt-5.6-sol runs up to 2.5x faster than Standard), billed at 2x the standard rate.

To enable it for the current session, type this inside Codex:

bash
/fast

(/fast is a toggle — type it again to turn it off.)

To enable it permanently, add this line at the top of ~/.codex/config.toml:

toml
service_tier = "fast"

All requests under this config will then use Fast mode.

Ready? Three steps to startLog in to the console · top up · create an API key
DiscordGet community help instantly
Connect Codex CLI to TeamoRouter · Docs