Integrate Thesean With Codex
Set up OpenAI Codex CLI to use supported Ship models through Thesean.
Ensure you have your Thesean API key from the Thesean 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 Thesean API key to your shell profile (~/.zshrc, ~/.bashrc, etc.) or a secure location like a .env file:
# Add to ~/.zshrc, ~/.bashrc, etc.
export THESEAN_API_KEY="your-thesean-api-key"
Replace your-thesean-api-key with your actual Thesean API key from the Thesean Dashboard.
Then reload your shell:
source ~/.zshrc # or source ~/.bashrc etc.
Step 2: Configure the Thesean Provider
Create or edit ~/.codex/config.toml:
Current Codex versions use the Responses API. Thesean's provider must therefore use
wire_api = "responses".
[model_providers.thesean-responses]
name = "Thesean /responses"
base_url = "https://api.thesean.ai/v1"
env_key = "THESEAN_API_KEY"
wire_api = "responses"
Step 3: Create Model Profiles
Codex 0.134.0 and later load profiles from separate files. Create one file for each Ship model:
model = "ship-like/gpt-5.6-sol"
model_provider = "thesean-responses"
[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 ship-gpt
Codex will now use the selected Ship model through Thesean's /responses endpoint. Switch between the
two configured profiles with --profile or the /model command within Codex.