Use Codex with Fabric AI Gateway
You can send OpenAI Codex traffic through Fabric AI Gateway by adding the gateway as a model provider in Codex’s config.toml file and passing a gateway key as a custom header. The gateway then applies your plugins to Codex requests, and you can review them in the console. This topic shows you how to configure Codex and confirm that requests arrive.
Prerequisites
Before you begin, make sure you have the following:
- Codex installed on your computer.
- A route for an OpenAI connection. For the steps, see Connect an LLM provider.
- A gateway key for the route. The gateway reads it from the
fg-api-keyheader. For more information, see Authenticate requests with Key Auth.
Configure Codex to use the gateway
Codex reads its settings from ~/.codex/config.toml. To configure Codex, do the following:
-
In the Fabric console, select LLMs > Routes, find your OpenAI route, and then select Copy LLM base URL.
-
Set your gateway key in an environment variable, for example in your shell profile:
-
Open
~/.codex/config.toml, and add the gateway as a model provider: -
Replace
GATEWAY_KEYwith your gateway key andBASE_URLwith the URL that you copied, ending in/v1. -
Restart Codex.
The settings do the following:
model_providermakes Codex use the provider that you define.base_urlsends requests to the gateway route instead of the OpenAI API.wire_api = "responses"makes Codex use the OpenAI Responses API format.env_http_headersadds the gateway key to each request, using the value of theFABRIC_GATEWAY_KEYenvironment variable. This keeps the key out of the file.
Treat the gateway key as a secret. Don’t put it in a config file that you commit.
The gateway supplies the OpenAI credential. It adds the API key saved on the connection when it forwards requests to OpenAI, so Codex doesn’t need an OpenAI key. Use a model that the connection allows.
Confirm that requests pass through the gateway
To confirm that Codex uses the gateway, do the following:
- In Codex, send a message, for example
Hello, is this working?. - In the Fabric console, select Admin, and then select Traces.
- Find the requests from your user on the route.
Next steps
- Add a rate limit to the route. For the steps, see Control traffic with plugins.
- Add fallback routing, so Codex keeps working when a provider returns errors. For the steps, see Adaptive Model Routing and Provider Failover.
- Review token usage and estimated cost by model on the LLM tab of Review analytics.

