Codex
Use the OpenAI Codex CLI with Tokener.ai as a custom model provider.
The Codex CLI speaks the OpenAI Responses
API. Tokener.ai serves that API at POST /responses, so Codex runs against
Tokener.ai with your API key and any chat model from the Models
catalog.
Configure
Add the provider to ~/.codex/config.toml and make it the default:
model = "<model-id>"
model_provider = "tokener"
[model_providers.tokener]
name = "Tokener.ai"
base_url = "https://api.tokener.dev/v1"
env_key = "TOKENER_API_KEY"
wire_api = "responses"Set TOKENER_API_KEY to a key created in API keys:
export TOKENER_API_KEY=sk-...To keep your current default provider and use Tokener.ai for a single run, drop the two top-level lines and select the provider on the command line:
codex --config model_provider=tokener --config model=<model-id>Models
Set any chat model id from the Models catalog. Launchers using Codex command authentication can load the API key's model list from Gateway.
Codex requests bill against your organization's credits like any other traffic on the model API.