How do I use the OpenAI API with OpenAI Codex CLI?

In ~/.codex/config.toml add a model provider with base_url https://api.llmsrelay.com/v1 and wire_api = "responses", set model gpt-5.5, and export your sk-cs4 key. Codex CLI then runs the OpenAI API through LLMsRelay.

Which endpoint does Codex CLI use?

The OpenAI Responses API (POST /v1/responses), which LLMsRelay Codex serves directly with streaming.

Does the Codex VS Code extension work too?

Yes. The extension reads the same ~/.codex/config.toml, so once the provider is configured it picks up LLMsRelay Codex automatically.

Back to dashboard

Codex CLI API — Run the OpenAI API in OpenAI Codex CLI

Connect OpenAI Codex CLI and the Codex extension to the OpenAI API through LLMsRelay's Responses API with a Codex-group key.

TL;DR

OpenAI Codex CLI and the Codex extension use the Responses API. LLMsRelay Codex serves /v1/responses directly, so a single config block points Codex at the OpenAI API.

Config

~/.codex/config.tomltoml

model = "gpt-5.5"
model_provider = "llmsrelay"

[model_providers.llmsrelay]
name = "LLMsRelay Codex"
base_url = "https://api.llmsrelay.com/v1"
env_key = "LLMSRELAY_API_KEY"
wire_api = "responses"

shellbash

export LLMSRELAY_API_KEY="sk-cs4-your-key"
codex

Full guide

For the complete walkthrough — creating a Codex-group key, configuring the VS Code extension, and testing — see the Codex CLI & Extension guide and the Codex API Reference.

Ready to start?

Create a key and configure a compatible API route in under 2 minutes.

View Plans

PreviousOpenAI API Access Next OpenAI-Compatible API