Codex
Use Tempools from the OpenAI Codex CLI
Codex CLI is OpenAI's official terminal coding agent. Tempools's OpenAI-compatible endpoint is a drop-in replacement for the default, and the recommended setup is to pin it in ~/.codex/config.toml plus an environment variable.
Prerequisites
- Node.js 20+ (download)
- On Windows, install Git; it's optional on macOS / Linux
- A Tempools API key from the console
Configuration
Install Codex CLI
sudo npm install -g @openai/codexRun from CMD or PowerShell:
npm install -g @openai/codexWire in Tempools
In the .codex folder under your home directory, create config.toml:
model_provider = "tempools"
model = "<paste exact model title from /models>"
model_reasoning_effort = "high"
disable_response_storage = true
[model_providers.tempools]
name = "tempools"
base_url = "https://api.tempools.com"
wire_api = "responses"
env_key = "TEMPOOLS_API_KEY"The model value must match the full card title shown on the Models
page or in the Console → Models catalog.
Then export the key as TEMPOOLS_API_KEY:
echo 'export TEMPOOLS_API_KEY="sk-tb-xxxxxxxxxxxxxxxx"' >> ~/.zshrc
source ~/.zshrcsetx TEMPOOLS_API_KEY "sk-tb-xxxxxxxxxxxxxxxx"You must restart the terminal after running this.
On Windows the .codex directory may not exist — create it manually. Explorer hides dot-directories by default; either enable View → Show → Hidden items or just run mkdir.
Launch and sanity-check
From any project directory:
codexOnce the welcome screen appears, try:
Hi — please explain this code.A real reply means Tempools is live.
VS Code extension (optional)
Only connect the VS Code extension after the CLI works end-to-end — it narrows the debug surface.
- Search the marketplace for Codex; only install the entry with the OpenAI verified badge.
- The extension reads
~/.codex/config.tomland your environment variables — nothing to re-enter in VS Code.
If codex still fails in the terminal, installing the extension won't
magically fix it — config path and env var issues usually surface there first.
Stuck? See the FAQ.