Docs · Codex CLI
Two environment variables, and you are done
FreeModel is an AI model gateway: one key for 477 models across dozens of providers, routed by task with free capacity tried first. Codex CLI speaks the OpenAI API, so the whole setup is pointing one variable at the right base URL and handing over a key.
Setup
# OpenAI-compatible base. Note: /v1 is part of the base —
# the client appends /chat/completions itself.
export OPENAI_BASE_URL="https://freemodel.online/v1"
export OPENAI_API_KEY="sk-your-key"Restart the shell that launches Codex CLI, or put the two lines in your shell profile so they survive a new terminal.
Which model you get
Whatever you ask for. If you name a specific model, that is what answers. If you would rather not track model names, pass a route instead:
| If you want | Use |
|---|---|
| Best available for code, chosen for you | auto/best-coding |
| Free quota only | auto/best-free |
| Fastest that still works | auto/best-fast |
The full set of ids is at Models, and the live list is
curl https://freemodel.online/v1/models.
Checking it works
# does the base answer at all? 401 = yes, it wants a key. 404 = wrong path.
curl -s -o /dev/null -w "%{http_code}\n" \
-X POST https://freemodel.online/v1/chat/completions \
-H "Content-Type: application/json" -d '{}'
# and a real call, which proves the key
curl -s https://freemodel.online/v1/chat/completions \
-H "Authorization: Bearer sk-your-key" \
-H "Content-Type: application/json" \
-d '{"model":"auto/best-chat","messages":[{"role":"user","content":"hi"}]}'
A 400 with messages: ... required on the first command is the
good outcome — it means the endpoint exists and parsed your (empty) body.
Common problems
| Symptom | Cause |
|---|---|
| 404 on every request | Base URL carries /v1 twice, or carries /chat/completions — the base stops at /v1 |
| 401 on every request | Key not exported in the shell that launched the client |
| Works in one terminal, not another | export is per-shell. Put it in your profile for it to stick |
| Model not found | The id is not in /v1/models; routes must match exactly, prefix included |