Codex
Connect Codex CLI, desktop, and VS Code to the Triton AI Developer API.
Codex can use a custom model provider through the OpenAI Responses API. The configuration belongs in your user-level Codex settings.
Supported by Triton AI
Triton AI has verified the production Responses route with a current public model. Select a model that supports Responses and tool use.
Configure the provider
Set the API key in the environment that starts Codex:
export TRITONAI_API_KEY="<YOUR_TRITON_AI_API_KEY>"Add the provider to your user configuration file:
| Platform | User configuration file |
|---|---|
| macOS, Linux, or WSL | ~/.codex/config.toml |
| Native Windows | %USERPROFILE%\.codex\config.toml |
model = "<MODEL_ALIAS>"
model_provider = "tritonai"
[model_providers.tritonai]
name = "Triton AI Developer API"
base_url = "https://tritonai-api.ucsd.edu/v1"
env_key = "TRITONAI_API_KEY"
wire_api = "responses"Choose an appropriate alias from the live model catalog.
Use the user configuration file
Do not put provider settings in a project .codex/config.toml. Codex ignores project settings that redirect credentials or change providers.
Start Codex from a shell that contains TRITONAI_API_KEY:
codexThe CLI reads the model and provider from the user configuration file shown above.
Verify the connection
Ask Codex to describe the current project without changing files. Confirm that the selected model alias appears in the client.
OpenAI documents the shared configuration layers in Codex configuration basics. See advanced configuration for custom providers and project-level restrictions.
Current limits
- Codex custom providers use the Responses API.
- A model can answer a basic prompt but still lack reliable tool support.
- Built-in OpenAI tools might not be available through a custom provider.