Skip to main content
Route every model call Codex CLI makes through the Orq.ai AI Gateway by editing ~/.codex/config.toml. Requests appear in Traces automatically.

​
Prerequisites

​
Setup

1

Export the API key

export ORQ_API_KEY="<your-orq-api-key>"
This sets the variable for the current shell session. To persist it across sessions, add the line to ~/.zshrc or ~/.bashrc.
2

Create or edit ~/.codex/config.toml

Create ~/.codex/config.toml if it does not exist. Add or merge the following keys. The top-level model and model_provider lines set the default; the [model_providers.orq] block registers the custom provider:
model = "openai/gpt-5.4"
model_provider = "orq"

[model_providers.orq]
name = "Orq AI Gateway"
base_url = "https://api.orq.ai/v3/router"
env_key = "ORQ_API_KEY"
wire_api = "responses"
requires_openai_auth = false
Replace openai/gpt-5.4 with the provider-prefixed model to use by default (e.g. anthropic/claude-sonnet-4-6). If a model key already exists in the file, replace it.
Do not name the provider openai. That identifier is reserved and hardcoded to api.openai.com. Setting base_url has no effect on it.
3

Run Codex

codex
Running codex without flags routes all calls through the AI Gateway using the model configured in ~/.codex/config.toml.Pass --model to override the model for a single invocation:
codex --model anthropic/claude-sonnet-4-6

​
Configuration reference

FieldValueDescription
modelprovider/model-idDefault model. Must use provider-prefixed format.
model_providerorqSelects the custom provider defined below.
base_urlhttps://api.orq.ai/v3/routerAI Gateway router endpoint.
env_keyORQ_API_KEYEnvironment variable that holds the API key.
wire_apiresponsesWire protocol. Codex uses the Responses API.
requires_openai_authfalseDisables the OpenAI auth header. Required for Orq-routed calls.

​
Troubleshooting

Confirm ORQ_API_KEY is exported in the shell running Codex. Run echo $ORQ_API_KEY to verify the value is set.
The model must be enabled in AI Gateway → Supported Models before Codex can route to it. Check that the model ID in config.toml uses the provider-prefixed format (e.g. openai/gpt-5.4, not gpt-4o).
Confirm base_url is https://api.orq.ai/v3/router and model_provider is set to the custom provider name (e.g. orq), not openai.

​
Verification

Send a prompt in Codex. The response appears in the terminal and the trace appears in Orq.ai Traces with the model identifier (e.g. openai/gpt-5.4).