Codex CLI Integration

Codex CLI can connect to LLM Gateway through a custom provider using the Responses API. This walkthrough was verified with Codex CLI 0.153.4.

Video walkthrough

Install

pnpm add -g @openai/codex
codex --version

Configure LLM Gateway

Create a key in your dashboard and export it in the terminal where you launch Codex:

export LLMGATEWAY_API_KEY="your_api_key"

Merge these settings into ~/.codex/config.toml:

model = "deepseek-v4-flash"
model_provider = "llmgateway"
model_reasoning_effort = "low"

[model_providers.llmgateway]
name = "LLM Gateway"
base_url = "https://api.llmgateway.io/v1"
env_key = "LLMGATEWAY_API_KEY"
wire_api = "responses"

The named provider reads your gateway key from the environment. You can keep your existing ChatGPT login. Current Codex versions use responses; changing an environment variable cannot switch them to Chat Completions.

Codex's default cached web search works with every model: requests served by OpenAI on a model with native web search search OpenAI's cached index, and everything else answers without searching (see cache-only search). web_search = "live" needs a model with native web search from the catalogue.

Start coding

cd your-project
codex

For a scripted task:

codex exec --sandbox workspace-write "Fix the failing test and run it again"

Verify the connection

Open a small project and ask the agent to read a file, make a change, and run its tests. Our recorded example fixes a TypeScript slugifier and passes all three tests with deepseek-v4-flash through LLM Gateway.

Hello, LLM Gateway! becomes hello-llm-gateway; repeated separators collapse into one hyphen; empty and punctuation-only inputs stay empty. The demo uses Node.js 24 to run node --test slugify.test.ts directly.

Review the diff and test output, then check the request in your LLM Gateway dashboard. Choose other compatible models from the live catalogue.

Troubleshooting

• Authentication fails: check that model_provider matches the provider table and that LLMGATEWAY_API_KEY is exported in the same shell.
• Native web search is unsupported: web_search = "live" is set for a model without native web search. Remove it or choose a model with that capability, then start a new session.
• Model metadata or catalogue refresh warning: Codex 0.153.4 can warn about missing metadata or the gateway's model-list response format. Our configured model still completed the task. Use an explicit model ID and verify the actual request result.
• Wrong endpoint: the provider's base_url must end in /v1.

See OpenAI's custom-provider configuration for configuration profiles and other options.