Codex CLI API: Use FreeTheAI Models in Codex

Codex CLI talks to FreeTheAI through the OpenAI Responses API. Add FreeTheAI as a model provider in config.toml and keep the key in an environment variable.

Website Source code API reference

Steps

Save your key in an environment variable
On Windows run the first line and open a new terminal; on macOS and Linux add the second line to your shell profile.
text
```
setx FREETHEAI_API_KEY "ftai_your_key_here"
export FREETHEAI_API_KEY="ftai_your_key_here"
```

Edit config.toml

Open ~/.codex/config.toml (on Windows, %USERPROFILE%\.codex\config.toml) and add:

toml

model = "glm-5.3"
model_provider = "freetheai"

[model_providers.freetheai]
name = "FreeTheAI"
base_url = "https://api.freetheai.org/v1"
env_key = "FREETHEAI_API_KEY"
wire_api = "responses"

Run Codex
Start codex. To switch models, change model = "..." to any ID freetheai.org/models lists and restart.

How this guide was checked: Tested with the current Codex CLI on 2026-09-29 (Responses streaming and tool calls through FreeTheAI).

Tips

Codex only speaks the Responses API now; wire_api = "chat" is refused by current versions.
glm-5.3 and kimi-k3.1-pro handle tool calls well.

Troubleshooting

Does FreeTheAI support the Responses API Codex needs?

Yes. /v1/responses is translated for every chat model, streamed or not. It was tested with Codex on 2026-09-29.

Common errors

401: the key is wrong or incomplete. Paste the whole key.
403: follow a provider of the model, or confirm your email.
404: the model ID or URL is wrong.
429: daily limit reached, or too many requests at once.

More guides: Coding tools

All setup guides