How to Use Codex CLI with Ace Data Cloud in Your Terminal

How to Use Codex CLI with Ace Data Cloud in Your Terminal

When a coding agent runs in your terminal, the hard part is not the chat interface. It is making sure the CLI reads the right provider configuration, sends requests to the right API protocol, and behaves safely inside each project.

This guide walks through configuring Codex CLI to use Ace Data Cloud as an OpenAI Responses-compatible provider, while keeping the native codex terminal workflow intact.

What you can do

Codex CLI is a local programming agent that runs from the terminal. According to the Ace Data Cloud documentation, it can read code, modify files, execute commands, explain errors, and assist with everyday development tasks. The useful part for builders is that Codex CLI supports custom model providers, so you can point the CLI at Ace Data Cloud instead of changing your workflow or adding a separate local proxy.

Once configured, the CLI sends requests to https://api.acedata.cloud/v1. For the Responses protocol specifically, the effective endpoint is https://api.acedata.cloud/v1/responses.

How it works

The integration is mostly configuration. Codex CLI reads a global TOML file at ~/.codex/config.toml, finds the selected model_provider, then loads the matching [model_providers.acedatacloud] block. In that block, base_url tells Codex where to send traffic, env_key tells it which environment variable contains your API token, and wire_api = "responses" tells it to use the OpenAI Responses API protocol.

The request flow is straightforward:

  1. Codex CLI reads model_provider = "acedatacloud" from ~/.codex/config.toml.
  2. It reads the API token from ACEDATACLOUD_API_KEY.
  3. It sends the request using wire_api = "responses" to base_url + /responses.
  4. Ace Data Cloud verifies the token, checks available quota, forwards the request to an available upstream model channel, and records usage after completion.

The result is that you keep using the original codex command and interactive terminal experience, while the underlying model service is provided through Ace Data Cloud.

Install Codex CLI

Codex CLI supports macOS, Linux, Windows, and WSL. If you already have Node.js installed, the documented npm path is the most direct one. It requires Node.js 18 or higher.

npm install -g @openai/codex

On macOS, Homebrew is also supported:

brew install --cask codex

After installation, reopen your terminal and check that the command is available:

codex --version

If you see command not found, your current shell probably has not loaded the updated PATH. Close and reopen the terminal, or check the path instructions printed by the installer.

Configure Ace Data Cloud as the provider

First, store your Ace Data Cloud API token in a shell environment variable. The docs recommend writing it to a shell profile such as ~/.zshrc, ~/.bashrc, or ~/.bash_profile:

export ACEDATACLOUD_API_KEY="{token}"

Replace {token} with the API token copied from the Ace Data Cloud Console. Then reload your shell configuration. For example, if you use zsh:

source ~/.zshrc

Next, create the Codex configuration file if it does not already exist:

mkdir -p ~/.codex
touch ~/.codex/config.toml

Write the provider configuration below into ~/.codex/config.toml:

model_provider = "acedatacloud"
model = "gpt-5"
model_reasoning_effort = "high"

[model_providers.acedatacloud]
name = "Ace Data Cloud"
base_url = "https://api.acedata.cloud/v1"
env_key = "ACEDATACLOUD_API_KEY"
wire_api = "responses"

The key fields are worth understanding. model_provider must match the provider block name. model sets the default model used by Codex CLI. model_reasoning_effort accepts common values such as low, medium, and high. base_url points to the Ace Data Cloud OpenAI Responses proxy, env_key names the environment variable Codex reads for the token, and wire_api must be responses for this integration.

Clear old login state before switching providers

If you previously logged into Codex CLI with an official OpenAI account, the local login state may be cached in ~/.codex/auth.json. The docs recommend clearing it before switching to the Ace Data Cloud provider:

codex logout

If that command is not available, remove the cached auth file manually:

rm -f ~/.codex/auth.json

If you have never logged into another provider from Codex CLI, you can skip this step.

Start a session and verify the active provider

Move into a project directory and start Codex CLI:

cd /path/to/your/project
codex

Inside the interactive interface, you can ask something simple first:

Explain the directory structure of this project

To verify the active model and provider, run:

/model

You should see output similar to:

Model: gpt-5
Provider: acedatacloud

If the provider is not acedatacloud, recheck that ~/.codex/config.toml was saved correctly and that ACEDATACLOUD_API_KEY is readable in the current terminal.

Switch models per task

The model field in ~/.codex/config.toml controls the default. The Ace Data Cloud documentation lists commonly supported models including gpt-5, gpt-5-mini, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, gpt-5.5, gpt-5.5-pro, gpt-4.1, o3, and o4-mini.

For a lightweight task, you can temporarily override the model when starting Codex:

codex --model gpt-5-mini

For a permanent change, edit the model field in ~/.codex/config.toml and restart Codex CLI.

Use project trust levels deliberately

Codex CLI can apply different trust levels per project. This matters because the agent may execute commands and modify files. For known repositories, you may choose trusted; for unfamiliar codebases, untrusted is safer.

[projects."/path/to/trusted/project"]
trust_level = "trusted"

[projects."/path/to/untrusted/project"]
trust_level = "untrusted"

In the docs, trusted gives the agent full permissions to execute commands and modify files, while untrusted limits what it can do. My default habit is to start new or third-party projects as untrusted, then promote them only after I understand the repository and the tasks I want the agent to handle.

Closing notes

This setup is small, but it removes a lot of friction: one terminal command, one TOML provider block, one environment variable, and the Responses-compatible endpoint at https://api.acedata.cloud/v1/responses. If you already use Codex CLI, this is a practical way to keep the same local agent workflow while routing model requests through Ace Data Cloud.

Read the full reference here: Codex CLI Terminal User Guide.

Comments

Post a Comment

Popular posts from this blog

Artistic QR Code API Integration Guidance

Image
Artistic QR code is an innovative technological product that combines QR codes with beautiful background images, creating practical and visually appealing works. They not only possess the functionality of traditional QR codes, allowing quick scanning and recognition by smart devices, but also incorporate artistic elements to enhance visual appeal and brand recognition. Some artistic QR codes are even generated by artificial intelligence, fully leveraging modern technology to demonstrate unparalleled innovation and uniqueness. This makes artistic QR codes widely applicable in areas such as brand marketing and advertising. In simple terms, artistic QR codes are the perfect combination of QR code scanning and artistic aesthetics. They not only provide the function of information transmission, but also enhance the user's visual experience, making each scan a delightful artistic enjoyment. Overview of Artworks Let's take a look at a few QR code works: How are they? These are ar...
Read more
Image
Nexior is an open-source project on GitHub that allows us to deploy our AI application site with one click, including AI Q&A, Midjourney drawing, knowledge base Q&A, artistic QR codes, and more. There is no need to develop AI systems, purchase AI accounts, worry about API support, or configure payment systems. It comes with zero startup costs and allows you to earn income through AI without risk. This article will introduce the deployment process of the Nexior project on Vercel. Without any programming skills, you can deploy your AI site in a few minutes and easily generate revenue. Preparation First, open the Nexior GitHub repository at: https://github.com/AceDataCloud/Nexior , then register or log in to your GitHub account. Click Fork to clone the code to your local repository, as shown below: After completing the Fork, we will get our personal repository, as shown below: In this example, the account is Germey, so we can see that we have Forked to the Germey user, wit...
Read more

A Small Tip for Using AI Agents: Don’t Ask for the Plan Too Soon

Image
A Small Tip for Using AI Agents: Don’t Ask for the Plan Too Soon Recently, while using AI agents to think through product and technical designs, I found a small but useful habit. It is not a complicated prompt trick. It is much simpler than that. Instead of asking the agent to immediately produce a plan, I first ask it to understand my requirement. If anything is unclear, I ask it to question me before writing the final proposal. In other words: Don’t generate the solution yet. First understand what I want. If anything is unclear, ask me questions. After we clarify the details, then give me the plan. This sounds ordinary, but it has improved the quality of the output quite a lot. 1. The problem with asking for a plan too early I used to work with agents in a very direct way. I would describe a rough idea and say something like: Help me design a solution. The agent would usually respond quickly with a complete-looking proposal. The structure was often clean. The logic lo...
Read more