OpenAI Codex Integration Tutorial: Custom Base URL Configuration for GPT

发布时间2026年8月30日 09:08
语言en

Tutorial on integrating OpenAI Codex (Codex CLI) terminal coding agent: installation, configuring custom Base URLs and keys via environment variables or config.toml, and using GPT models.

1. What is Codex?

OpenAI Codex (Codex CLI) is OpenAI's official terminal coding agent that supports custom API endpoints. By pointing it to our gateway's OpenAI-compatible entry point, you can use GPT series models with your sk- key.

2. Installing Codex CLI

npm install -g @openai/codex

After installation, enter codex in your terminal; switch models using codex --model gpt-5.4 or through the model selection menu during interaction.

3. Configuring Codex

① Environment Variables (Fastest)

export OPENAI_BASE_URL="https://www.relay-api.com/v1"
export OPENAI_API_KEY="sk-your-key"
codex --model gpt-5.4

② config.toml (Recommended for long-term use)

# ~/.codex/config.toml
[model_providers.myrelay]
name = "Azztimes Relay"
base_url = "https://www.relay-api.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "chat"

[model]
model_provider = "myrelay"
model = "gpt-5.4"

Save the file and run codex --model gpt-5.4 to get started.

4. API Endpoint Reference

Model Group	Base URL	Protocol
Claude / Anthropic	`https://www.relay-api.com`	Anthropic Messages
GPT / OpenAI	`https://www.relay-api.com/v1`	OpenAI Chat Completions
Gemini	`https://www.relay-api.com/v1beta`	Google generateContent

5. Troubleshooting

Issue	Solution
401 / 403	Invalid key, disabled, or insufficient balance; verify the `sk-` key and top up if necessary.
404 / Model unavailable	The model name does not match the platform slug, or the model is not enabled; check the model ID.
Unknown model	Ensure the model ID is precise (including case sensitivity); verify it via the Model Plaza.

Security Note: Do not commit your API key to public repositories. Use .env files or environment variables. Generation tasks can consume significant tokens, so keep an eye on your balance.