Built for Cline.
In any IDE.
An OpenAI-compatible LLM service that works everywhere Cline does — VS Code, JetBrains, Neovim, or just curl.
https://clinecodex.com/ai/v1
Every Codex model, one endpoint.
Switch between them with a single header. No new accounts, no new SDKs.
codex-5.5
Flagship. Maximum reasoning depth for the hardest problems.
codex-5.2
Strong daily-driver. Best balance of speed and quality.
codex-5
Fast iteration. Great for refactors, tests, and small edits.
codex-5-codex
Tuned for code generation. Sharper on multi-file diffs.
codex-4
Lightweight and cheap. Drop in for routing and classification.
Built for builders.
From weekend side projects to production teams — same endpoint, same speed.
Engineers
Ship features, not boilerplate.
Data scientists
Notebooks that read and write for you.
Researchers
Summarize papers, draft citations.
Writers
Outline, edit, and polish — without the noise.
Indie devs
Big-league models on a side-project budget.
Students
Learn faster. Get unstuck sooner.
One API. Any IDE.
OpenAI-compatible. Drop-in replacement for any client that talks Chat Completions.
$ curl https://clinecodex.com/ai/v1/chat/completions \ -H "Authorization: Bearer $CLINECODEX_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5.5", "messages": [{ "role": "user", "content": "List the files in /etc" }] }' # → 200 OK # → { "choices": [ { "message": { "role": "assistant", "tool_calls": [...] } } ] }
Simple, transparent pricing.
Pay for what you use. Cancel anytime.
Plus
For solo devs and weekend builds.
- 200K tokens per day
- All Codex models
- 10 requests/minute
- Standard email support
- Community Discord
Pro
For power users shipping daily.
- 1M tokens per day
- Priority queue
- 60 requests/minute
- Priority support
- Analytics dashboard
- Early access to new models
Max
For teams and production workloads.
- Unlimited tokens
- Highest priority
- 300 requests/minute
- Dedicated engineer
- 10 team seats
- SSO + audit logs
- Custom rate limits