Use Modellix LLM with Codex CLI - Modellix

Point Codex CLI at the Modellix LLM gateway so chat and coding requests use your Modellix API key and openai/... models over OpenAI-compatible Chat Completions.

Configure

Set your API key in the environment:

export OPENAI_API_KEY="mdlx-xxxxxxxx"

In ~/.codex/config.toml, set the base URL and model (recommended). Newer Codex builds deprecate OPENAI_BASE_URL as an environment variable—prefer openai_base_url in config:

model = "openai/gpt-5.5"
openai_base_url = "https://llm.modellix.ai/v1"

Setting	Value
`openai_base_url`	`https://llm.modellix.ai/v1`
`OPENAI_API_KEY`	Modellix API Key
`model`	`openai/...` (for example `openai/gpt-5.5`). See Models & Pricing.

Get a Modellix API key from the console. It is not an OpenAI platform key.

Verify

After saving the config, run Codex as usual. Traffic should hit https://llm.modellix.ai/v1 (typically Chat Completions). For protocol details, see Chat Completions and the LLM API guide.

OpenAI SDK — same /v1 base URL for application code
OpenCode — another OpenAI-compatible client config
Cursor — IDE OpenAI-compatible provider setup