Qwen Code CLI

Use Qwen Code CLI with TrueFoundry AI Gateway to interact with AI models from your terminal.

This guide provides instructions for integrating Qwen Code CLI with the TrueFoundry AI Gateway.

What is Qwen Code?

Qwen Code is an open-source, AI-powered terminal coding assistant optimized for the Qwen3-Coder model. It helps you understand large codebases, automate tedious work, and ship faster — all from the command line.

Key Features

1. Terminal-Native AI Agent: Chat with AI models, edit files, and run commands directly from your terminal without switching contexts
2. Repository-Scale Understanding: Analyzes codebases beyond traditional AI context limits with intelligent context management
3. Multi-Protocol Support: Works with OpenAI, Anthropic, and Google GenAI compatible APIs — making it easy to route through TrueFoundry
4. Agentic Workflow: Built-in Skills and SubAgents for a full agentic coding experience

Prerequisites

Before integrating Qwen Code with TrueFoundry, ensure you have:

1. TrueFoundry Account: Create a TrueFoundry account with at least one model provider configured and generate a Personal Access Token by following the instructions in Generating Tokens. For a quick setup guide, see our Gateway Quick Start
2. Qwen Code Installation: Install Qwen Code CLI using one of the methods below:

Quick Install (curl)

The recommended one-line installer for Linux and macOS:

curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen.sh | bash

Installing Qwen Code CLI via curl

Restart your terminal after installation to ensure environment variables take effect.

Homebrew

On macOS or Linux with Homebrew:

brew install qwen-code

Installing Qwen Code CLI via Homebrew

npm

If you already have Node.js 20+ installed:

npm install -g @qwen-code/qwen-code@latest

See the npm package page for additional options and version history.

Windows

Run as Administrator in CMD:

curl -fsSL -o %TEMP%\install-qwen.bat https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen.bat && %TEMP%\install-qwen.bat

Setup Process

1. Get Configuration Details

Get the base URL and model name from your TrueFoundry AI Gateway playground using the unified code snippet:

Get Base URL and Model Name from Unified Code Snippet

2. Configure Qwen Code

Qwen Code uses a settings.json file for configuration. Edit (or create) the file at ~/.qwen/settings.json to route requests through TrueFoundry:

{
  "modelProviders": {
    "openai": [
      {
        "id": "openai-main/gpt-4o",
        "name": "GPT-4o via TrueFoundry",
        "baseUrl": "{GATEWAY_BASE_URL}",
        "description": "GPT-4o routed through TrueFoundry AI Gateway",
        "envKey": "TFY_API_KEY"
      }
    ]
  },
  "env": {
    "TFY_API_KEY": "your-truefoundry-api-key"
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "model": {
    "name": "openai-main/gpt-4o"
  }
}

Replace the placeholders:

• {GATEWAY_BASE_URL} → Your TrueFoundry AI Gateway Base URL
• your-truefoundry-api-key → Your TrueFoundry Personal Access Token
• openai-main/gpt-4o → Your desired model in provider-name/model-name format

The id and model.name fields should use the fully qualified model name from TrueFoundry (e.g., openai-main/gpt-4o, anthropic/claude-4-sonnet). You can find the exact model name in the TrueFoundry AI Gateway playground.

3. Configure Multiple Models (Optional)

You can configure multiple models from different providers to switch between them during a session:

{
  "modelProviders": {
    "openai": [
      {
        "id": "openai-main/gpt-4o",
        "name": "GPT-4o via TrueFoundry",
        "baseUrl": "{GATEWAY_BASE_URL}",
        "description": "GPT-4o routed through TrueFoundry AI Gateway",
        "envKey": "TFY_API_KEY"
      },
      {
        "id": "openai-main/gpt-5",
        "name": "GPT-5 via TrueFoundry",
        "baseUrl": "{GATEWAY_BASE_URL}",
        "description": "GPT-5 routed through TrueFoundry AI Gateway",
        "envKey": "TFY_API_KEY"
      }
    ]
  },
  "env": {
    "TFY_API_KEY": "your-truefoundry-api-key"
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "model": {
    "name": "openai-main/gpt-4o"
  }
}

Use the /model command inside Qwen Code to switch between all configured models during a session.

Usage Examples

Interactive Mode

Launch the interactive terminal UI in your project directory:

cd your-project/
qwen

Once inside the session, you can ask questions about your codebase, generate code, and run commands using natural language.

Headless Mode

Use the -p flag to run Qwen Code without the interactive UI — ideal for scripts, automation, and CI/CD:

# Generate code with a prompt
qwen -p "Write a hello world HTTP server in Python using Flask, keep it minimal"

# Output as plain text (useful for piping)
qwen -p "Write a hello world HTTP server in Python using Flask, keep it minimal" -o text

Qwen Code CLI headless mode output showing a generated Flask server

Common Prompts

# Understand your project
> What does this project do?

# Code generation
> Write unit tests for the auth module

# Refactoring
> Refactor this function to use async/await

# Debugging
> Why is this test failing?

Observability

All requests routed through TrueFoundry AI Gateway are automatically logged and available for monitoring. You can view request traces, latencies, token usage, and full request/response details in the TrueFoundry dashboard.

TrueFoundry trace view showing Qwen Code CLI requests routed through the AI Gateway

This gives you full visibility into:

• Request traces: See every request made by Qwen Code, including the model used and response times
• Token usage: Track input and output token consumption across sessions
• Cost monitoring: Monitor spend across different models and providers
• Governance: Enforce policies, rate limits, and access controls on all AI requests

Fleet-wide enforcement

Gateway config: per user. Qwen Code has a system settings file, /etc/qwen-code/settings.json (Linux), C:\ProgramData\qwen-code\settings.json (Windows), or /Library/Application Support/QwenCode/settings.json (macOS), that overrides user and project settings and can set modelProviders and security.auth.enforcedType. But OPENAI_BASE_URL / OPENAI_API_KEY environment variables and CLI flags rank above it, so the base URL can’t be hard-locked; push the values through MDM and use network policy. See Qwen Code’s settings doc.

MCP servers: enforceable. Remote servers are mcpServers.<name> with httpUrl (Streamable HTTP) or url (SSE), headers, or an oauth block; point them at the MCP Gateway. In the system settings file, mcpServers defined there can’t be overridden by users, and mcp.allowed / mcp.excluded allowlist or block servers by name (mcp.excluded wins). Matching is by name string, so it’s policy rather than a hard boundary. See Qwen Code’s MCP doc.