1. Install Codex CLI
Shell
npm install -g @openai/codex
codex --version2. Configure ~/.codex/config.toml
TOML
model = "YOUR_RESPONSES_MODEL_ID"
model_provider = "ghc-api"
model_reasoning_effort = "high"
[model_providers.ghc-api]
name = "ghc-api"
base_url = "http://127.0.0.1:8313/v1"
env_key = "GHC_API_TOKEN"
wire_api = "responses"Shell
export GHC_API_TOKEN=1
codex3. Match model capabilities
Select a model whose supported_endpoints contains /responses. Only set model_reasoning_effort to a value listed under capabilities.supports.reasoning_effort.
Do not assume every GPT model supports every effort.
Live model metadata is the source of truth for the current account.
4. Verify
- Confirm Responses support in
/v1/models/full/. - Check that requests arrive at
/v1/responses. - For 401 errors check the environment token; for 400 errors check the model and effort.
- Disable reverse-proxy buffering for streaming.
Codex configuration reference ↗
Next step
Inspect the models and endpoints available to your account before copying a model ID into client configuration.
Inspect models and parameters →