Use uncensored models in Codex
Add Silk Compute as a provider in Codex's config file. Every model we serve then shows up in /model.
1. Install Codex
npm install -g @openai/codex2. Set your API key
Create a key on the API keys page, then export it. Add the line to ~/.zshrc or ~/.bashrc so new terminals have it too.
export SILK_API_KEY="sk-..."3. Add Silk Compute
Add these lines to ~/.codex/config.toml. Create the file if it doesn't exist.
model = "deepseek-v4.1-flash-1017-uncensored"
model_provider = "silkcompute"
web_search = "disabled"
[model_providers.silkcompute]
name = "Silk Compute"
base_url = "https://api.silkcompute.com"
env_key = "SILK_API_KEY"
model_catalog_url = "https://api.silkcompute.com/codex/models"4. Run it
codexSwitch the model and effort with /model.
Keep OpenAI as your default
Save the same lines as ~/.codex/silk.config.toml instead and run codex --profile silk.
Troubleshooting
Run this in the same terminal. A list of models means the key works. A 401 means SILK_API_KEY is empty or wrong there.
curl -s https://api.silkcompute.com/models -H "Authorization: Bearer $SILK_API_KEY"