Getting Started with Codex CLI and Ace Data Cloud in Your Terminal

Getting Started with Codex CLI and Ace Data Cloud in Your Terminal

When a coding agent runs in your terminal, the useful part is not the chat UI itself; it is how quickly it can read a project, reason about the code, run commands, and help you move without breaking your normal workflow.

This guide walks through a practical setup for using Codex CLI with Ace Data Cloud as an OpenAI Responses-compatible provider. The goal is simple: keep the native codex terminal experience, but point its model requests at https://api.acedata.cloud/v1 through Codex's custom provider configuration.

What you can do

Codex CLI is a local programming agent that runs from the terminal. Once configured, it can help with everyday development work such as:

  • Reading and explaining an unfamiliar project structure.
  • Inspecting source files and suggesting changes.
  • Running shell commands during a debugging session.
  • Helping with small refactors, error explanations, and code review tasks.

The Ace Data Cloud configuration does not require a separate local proxy process or a Codex plugin. Codex already supports custom model providers, and its Responses API wire format can be routed to Ace Data Cloud by editing ~/.codex/config.toml.

How it works

The important pieces are Codex's global configuration file, one environment variable, and the Responses API endpoint.

  1. Codex reads model_provider from ~/.codex/config.toml.
  2. It loads the matching provider block, in this case [model_providers.acedatacloud].
  3. It reads your API token from the environment variable named by env_key.
  4. Because wire_api = "responses", requests go to base_url + /responses, which becomes https://api.acedata.cloud/v1/responses.
  5. Ace Data Cloud verifies the token, checks quota, forwards the request to an available upstream model channel, and records usage after completion.

From the developer's point of view, the command stays the same: you still run codex inside a project directory.

Install Codex CLI

If you already have Node.js 18 or higher, install Codex CLI with npm:

npm install -g @openai/codex

On macOS, the documented Homebrew option is:

brew install --cask codex

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

codex --version

If your shell returns command not found, the current terminal likely has not loaded the new PATH. Reopen the terminal or check the path instructions printed by the installer.

Use one authentication method

The source documentation makes one point worth treating as a rule: choose one authentication method and do not mix them. This guide uses env_key = "ACEDATACLOUD_API_KEY", which means Codex reads the token only from an environment variable.

Add the variable to your shell configuration file, such as ~/.zshrc, ~/.bashrc, or ~/.bash_profile:

export ACEDATACLOUD_API_KEY="{token}"

Replace {token} with your Ace Data Cloud API token. Then reload the shell configuration:

source ~/.zshrc

When checking whether the variable exists, avoid printing the token itself. Use a presence check instead:

test -n "$ACEDATACLOUD_API_KEY" && echo "ACEDATACLOUD_API_KEY is set" || echo "ACEDATACLOUD_API_KEY is missing"

Configure the provider

Codex stores its global configuration at ~/.codex/config.toml. Create the directory and file if they do not already exist:

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

Then write the provider configuration:

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"

Each field has a specific job. model_provider selects the default provider. model selects the default model. model_reasoning_effort accepts common values such as low, medium, and high. The provider block defines the display name, the Ace Data Cloud base URL, the environment variable Codex should read, and the required responses wire protocol.

Clear cached OpenAI login state

If you previously logged in to Codex CLI with an official OpenAI account, Codex may have cached local auth state in ~/.codex/auth.json. Before switching to this environment-variable configuration, clear the old login:

codex logout

If that command is unavailable, remove the cache file directly:

rm -f ~/.codex/auth.json

If you have never used an official OpenAI login with Codex, you can skip this step.

Start and verify a session

Move into a project and start Codex:

cd /path/to/your/project
codex

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

Explain the directory structure of this project

To verify which provider is active, run:

/model

The expected result should show a model such as gpt-5 and the provider as acedatacloud. If it does not, check that model_provider = "acedatacloud" exactly matches [model_providers.acedatacloud], confirm the environment variable is set without printing the token, clear any old auth.json, and fully restart your terminal or editor window.

For a minimal non-interactive validation, the documentation suggests:

codex exec --model gpt-5-mini "Reply with exactly: ADC_Codex_OK" < /dev/null

Choosing a model and project trust

The default model in config.toml can be changed when your workflow changes. The documented examples include 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. You can temporarily override the model from the command line:

codex --model gpt-5-mini

Codex also supports per-project trust levels. For a known repository, you may mark it trusted; for an unfamiliar checkout, keep it untrusted:

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

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

This is a small configuration detail, but it matters. A terminal coding agent is most useful when it has enough permission to help, and safest when that permission is scoped to the project you actually trust.

Wrap-up

The setup is mostly plumbing: install Codex CLI, store the token in ACEDATACLOUD_API_KEY, configure ~/.codex/config.toml, clear conflicting auth state, and verify with /model or a minimal codex exec command. After that, the day-to-day workflow is still the native codex command in your terminal.

Read the original Ace Data Cloud documentation 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

How to Configure Claude Code with CC Switch and Ace Data Cloud

Image
If you use Claude Code across a terminal, VS Code, or remote development setup, the awkward part is often not the model itself but the configuration: where should requests go, where should the token live, and how do you switch providers without editing files by hand? This guide walks through a practical setup using CC Switch as the graphical configuration manager and Ace Data Cloud as the Anthropic-compatible base URL. The goal is simple: configure Claude Code once, verify the active endpoint, and keep the setup easy to change later. What you can do With the setup described in the Ace Data Cloud documentation, you can: Manage Claude Code provider configuration through a desktop UI instead of manually editing settings.json . Store an Ace Data Cloud provider with ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN . Switch the active Claude Code provider from CC Switch without rewriting your configuration every time. Use the same provider configuration from the terminal an...
Read more