Claude Code CLI Configuration Guide
¶ 1. Obtain API Key
Open the Lingxi AI Plaza application list, access the available applications, and copy the API Key.
¶ 2. Install Claude Code
macOS / Linux / WSL：
curl -fsSL https://claude.ai/install.sh | bash
Windows PowerShell：
irm https://claude.ai/install.ps1 | iex
Check after installation:
claude --version
¶ 3. Configure Lingxi AI Plaza
For global use, add the following variables to ~/.zshrc or ~/.bashrc:
export ANTHROPIC_BASE_URL="https://api.acedata.cloud"
export ANTHROPIC_AUTH_TOKEN="your API Key"
unset ANTHROPIC_API_KEY
Reopen the terminal or source the corresponding configuration file.
For project-specific use, you can create a .claude/settings.local.json that is included in .gitignore:
{
"env": {
"ANTHROPIC_BASE_URL": "https://api.acedata.cloud",
"ANTHROPIC_AUTH_TOKEN": "your API Key"
}
}
Choose one of the two methods. Do not write the real Key into the team-shared .claude/settings.json; if ANTHROPIC_API_KEY already exists in the environment, it should be truly unset, not set to an empty string.
¶ 4. Start and Verify
cd /path/to/your/project
claude
Once inside, send a read-only task, such as "Read README.md and summarize it in one sentence." Call records and balance can be viewed in the Usage History and Application List.
If a 401 is returned, check if the Key is complete, whether the old ANTHROPIC_API_KEY has been unset, and fully restart Claude Code. The model does not need to be fixed in the access configuration and can be selected from the currently available models in Claude Code.