OpenAI Codex API key setup
OpenAI's Codex coding agent (CLI, IDE, Web, Sites). Codex CLI runs locally in your terminal with a ChatGPT sign-in (free) or an OpenAI API key; the IDE integrates into VS Code; Codex Web runs cloud tasks asynchronously; Codex Sites builds workspace-internal web apps. Powered by GPT-5.5, with AGENTS.md configuration, 24 slash commands, approval modes, and role-specific plugins. Code review with in-place annotations is available on ChatGPT plans. ChatGPT plans (Plus, Pro, Business) add the IDE and Web surfaces with rate limits that scale by model tier.
Get your key
- Open the OpenAI Codex site: openai.com/codex/
- Create an account and generate an API key.
- Paste it into the Dracon key manager — stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.
Free tier
Yes. Codex CLI is free with a ChatGPT account (sign-in required). The Codex usage page or limit banner in the active CLI session is the canonical way to see remaining allowance and reset windows.
Rate limits: Codex usage: 1x tier (~20 messages/5hr, ChatGPT Plus) — base models. 5x tier (~100 messages/5hr, ChatGPT Pro) — all models. 20x tier (~200 messages/5hr, Business/Enterprise) — highest tier. Pro is higher-allowance, not unlimited. Windows reset on a 5-hour rolling basis. API-key usage is on a separate billing lane.
Connection details
- Env var
OPENAI_API_KEY- Model lineup
- codex-1, codex-mini, gpt-5-codex, gpt-5, gpt-4.1
Gotchas
Browser-direct chat is not available for this provider: CLI tool, not an API. The vault still stores its key for tools that run elsewhere (for example a LiteLLM chain from the router builder).