Integrate the Martian Gateway With Codex
This document describes how to set up OpenAI Codex CLI to route all your LLM requests through the Martian Gateway.
Ensure you have your Martian API key from the Martian Dashboard before continuing.
Prerequisites
Ensure you have Codex installed. See the Codex quickstart for more options, or use one of the following:
npm install -g @openai/codex
Configuration
Step 1: Store Your API Key
Add your Martian API key to your shell profile (~/.zshrc, ~/.bashrc, etc.) or a secure location like a .env file:
# Add to ~/.zshrc, ~/.bashrc, etc.
export MARTIAN_API_KEY="your-martian-api-key"
Replace your-martian-api-key with your actual Martian API key from the Martian Dashboard.
Then reload your shell:
source ~/.zshrc # or source ~/.bashrc etc.
Step 2: Configure the Martian Provider
Create or edit ~/.codex/config.toml:
Current Codex versions use the Responses API. Martian's provider must therefore use
wire_api = "responses".
[model_providers.martian-responses]
name = "Martian /responses"
base_url = "https://api.withmartian.com/v1"
env_key = "MARTIAN_API_KEY"
wire_api = "responses"
Step 3: Create Model Profiles
Codex 0.134.0 and later load profiles from separate files. Create a profile for each model you want to use:
model = "openai/gpt-5.2"
model_provider = "martian-responses"
Add [features] with multi_agent = false to ~/.codex/config.toml if your selected model or
Martian's /responses implementation does not support Codex's multi-agent tools:
[features]
multi_agent = false
The provider stays in the shared config.toml; each profile file contains only its model-specific
settings. See the
Codex profiles documentation and
Available Models.
Start Using Codex
Navigate to your project directory and start Codex with a profile:
cd your-project
codex --profile gpt-5.2
Codex will now route all requests through the Martian Gateway. You can switch between profiles using the --profile flag or the /model command within Codex.