#codex cli

[metavi]

繁中 AI Coding Tools 系列：Codex、Claude Code 與一鍵切換腳本

繁中 AI Coding Tools 系列：Codex、Claude Code 與一鍵切換腳本

這組文章整理了：

一條指令把 OpenAI Codex CLI 接到 Crazyrouter

用 Crazyrouter Token 一鍵配置 Claude Code

Codex CLI / Claude Code / Hermes Agent 的一鍵切換腳本思路

Base URL、模型名、環境變數常見排錯

GitHub repo:

https://github.com/xujfcn/crazyrouter-codex-cli

https://github.com/xujfcn/crazyrouter-claude-code

https://github.com/xujfcn/crazyrouter-hermes

Crazyrouter:

https://crazyrouter.com?utm_source=tumblr&utm_medium=article&utm_campaign=ai_coding_tools_tw

[metavi]

Crazyrouter Codex CLI: Use Codex with One API Key and an OpenAI-Compatible Gateway

Crazyrouter Codex CLI: Use Codex with One API Key and an OpenAI-Compatible Gateway

OpenAI Codex CLI is useful when you want an AI coding agent directly inside your terminal. The painful part is not the idea — it is the setup: API keys, base URLs, model names, Windows environment variables, macOS shell profiles, Linux config files, and different providers for different models.

The new crazyrouter-codex-cli repo solves one specific problem:

connect Codex CLI to Crazyrouter with one API key and an OpenAI-compatible API endpoint.

Repository:

https://github.com/xujfcn/crazyrouter-codex-cli

What this repo does

The repo provides simple install scripts for:

Windows PowerShell

Windows batch file

macOS

Linux

It configures Codex CLI to use:

OPENAI_BASE_URL=https://cn.crazyrouter.com/v1 OPENAI_API_KEY=your-crazyrouter-key

That means Codex CLI can talk to Crazyrouter through an OpenAI-compatible interface, while Crazyrouter handles the model/provider side.

Important rule:

Do not add UTM parameters to API endpoints. UTM belongs on human-clickable website links, not OPENAI_BASE_URL.

Correct:

export OPENAI_BASE_URL=https://cn.crazyrouter.com/v1

Wrong:

export OPENAI_BASE_URL=https://cn.crazyrouter.com/v1?utm_source=...

Why use Codex CLI through Crazyrouter?

A terminal coding agent is most useful when it can become part of your normal development loop:

open a project directory;

ask the agent to inspect code;

let it patch files;

run tests;

review the diff;

repeat.

But real developer teams often want more than one model. Some tasks need a fast low-cost model. Some need a stronger reasoning model. Some need Claude-style code review. Some need Gemini-style long-context analysis. Some teams also need a more stable route from regions where direct access is unreliable.

Crazyrouter gives Codex CLI a single OpenAI-compatible gateway:

one API key;

one base URL;

multiple model choices;

OpenAI-compatible client configuration;

easier switching between coding models.

One-command install

Windows PowerShell

Open PowerShell as a normal user and run:

iwr -UseB https://raw.githubusercontent.com/xujfcn/crazyrouter-codex-cli/main/install-crazyrouter-codex.ps1 | iex

Or download and run:

install-crazyrouter-codex.bat

macOS / Linux

curl -fsSL https://raw.githubusercontent.com/xujfcn/crazyrouter-codex-cli/main/install-crazyrouter-codex.sh | bash

The script asks for your Crazyrouter API key, writes the needed environment variables, and backs up existing Codex configuration when needed.

Manual setup

If you prefer to configure it yourself, install Codex CLI first:

npm install -g @openai/codex

Node.js 22+ is recommended.

Then set the environment variables.

macOS / Linux

export OPENAI_API_KEY=sk-your-crazyrouter-key export OPENAI_BASE_URL=https://cn.crazyrouter.com/v1

Windows PowerShell

setx OPENAI_API_KEY "sk-your-crazyrouter-key" setx OPENAI_BASE_URL "https://cn.crazyrouter.com/v1"

After setx, reopen your terminal.

Then start Codex:

codex

Codex config.toml example

Some Codex CLI versions support provider configuration in:

Read the full guide

[codeagency-blog1]

OpenAI Releases Codex CLI, a New AI Tool for Terminal-Based Coding - <FrontBackGeek/>

April 17, 2025 — OpenAI has officially released Codex CLI, a new open-source tool that brings artificial intelligence directly into the term