Qwen Code - Qwen Cloud

Qwen Code is an AI programming assistant.

Install Qwen Code

macOS/Linux
Windows

Install Qwen Code:

bash -c "$(curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen.sh)" -s --source bailian

Verify installation:

qwen --version

Open CMD as an administrator Search for CMD and select Run as administrator.
Install Qwen Code

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

Verify the installation Close the current CMD window, open a new one, and verify:

qwen --version

Configure and use Qwen Code

Edit or create the settings.json file. Replace YOUR_API_KEY with your Token Plan API key. The file is located at one of the following paths:

macOS/Linux: ~/.qwen/settings.json
Windows: C:\Users\<Windows username>\.qwen\settings.json

{
  "env": {
    "BAILIAN_TOKEN_PLAN_API_KEY": "YOUR_API_KEY"
  },
  "modelProviders": {
    "openai": [
      {
        "id": "qwen3.6-plus",
        "name": "[Token Plan] qwen3.6-plus",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "glm-5",
        "name": "[Token Plan] glm-5",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "MiniMax-M2.5",
        "name": "[Token Plan] MiniMax-M2.5",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "deepseek-v3.2",
        "name": "[Token Plan] deepseek-v3.2",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      }
    ]
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "tokenPlan": {
    "region": "global"
  },
  "model": {
    "name": "qwen3.6-plus"
  },
  "$version": 3
}

Start Qwen Code in your project directory:

qwen

Common commands

These commands are for Qwen Code CLI. IDE extensions support only a subset.

Command	Description	Example
`/model`	Switch the model used in the current session.	`/model`
`/auth`	Change the authentication method.	`/auth`
`/init`	Analyze the current directory and create a context file (QWEN.md) with project-level instructions.	`/init`
`/clear`	Clear the screen and start a new chat session.	`/clear`
`/compress`	Replace the chat history with a summary to save tokens.	`/compress`
`/settings`	Open settings (language, theme, etc.).	`/settings`
`/summary`	Generate a project summary from the chat history.	`/summary`
`/resume`	Resume a previous chat session.	`/resume`
`/stats`	Show session statistics.	`/stats`
`/help`	Show available commands.	`/help` or `/?`
`/quit`	Exit Qwen Code.	`/quit`

For more commands and usage details, see the official Qwen Code docs.

Switch models (optional)

Enter /model to switch between models supported by Qwen Cloud Token Plan.

Text-based models, such as qwen3.6-plus and glm-5, work out of the box. Image generation models use a separate API and must be integrated through extension mechanisms. See Integrate multimodal generation models.

If a required model (such as qwen3.6-plus, MiniMax-M2.5, or glm-5) is not listed, update Qwen Code:

Enter /quit to exit Qwen Code.
Update Qwen Code:

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

Restart Qwen Code:

qwen

Use /model to select models.

Qwen Code IDE plugin (optional)

Qwen Code is available as an IDE plugin for VS Code and JetBrains IDEs, providing AI-powered programming capabilities directly within your editor.

VS Code
JetBrains

Requires VS Code 1.85.0 or later.

Search for Qwen Code Companion in VS Code extensions and install it.
Edit or create the settings.json file. Replace YOUR_API_KEY with your Token Plan API key. The file is located at:
- macOS/Linux: ~/.qwen/settings.json
- Windows: C:\Users\<Windows username>\.qwen\settings.json
Skip this if you already configured Qwen Code CLI -- the extension reads from the same settings.json file.

{
  "env": {
    "BAILIAN_TOKEN_PLAN_API_KEY": "YOUR_API_KEY"
  },
  "modelProviders": {
    "openai": [
      {
        "id": "qwen3.6-plus",
        "name": "[Token Plan] qwen3.6-plus",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "glm-5",
        "name": "[Token Plan] glm-5",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "MiniMax-M2.5",
        "name": "[Token Plan] MiniMax-M2.5",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      },
      {
        "id": "deepseek-v3.2",
        "name": "[Token Plan] deepseek-v3.2",
        "baseUrl": "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
        "envKey": "BAILIAN_TOKEN_PLAN_API_KEY",
        "generationConfig": {
          "extra_body": {
            "enable_thinking": true
          }
        }
      }
    ]
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "tokenPlan": {
    "region": "global"
  },
  "model": {
    "name": "qwen3.6-plus"
  },
  "$version": 3
}

Click the icon in the upper-right to start Qwen Code. Switch models: enter / and select Switch model.

Requires a JetBrains IDE with Agent Client Protocol (ACP).

Install Qwen Code CLI first -- the IDE extension depends on it. See Install Qwen Code.
Open the AI Chat panel and click Install Plugin to install JetBrains AI Assistant.
Click the three-dot menu > Add Custom Agent. Replace /path/to/qwen with your Qwen Code installation path (find it with):
- macOS/Linux: which qwen
- Windows: where qwen (CMD) or Get-Command qwen (PowerShell)

{
  "agent_servers": {
    "qwen": {
      "command": "/path/to/qwen",
      "args": ["--acp"],
      "env": {}
    }
  }
}

Qwen Code now appears in AI Chat. Switch models in the lower-right corner.

Learn more

For advanced features such as sub-agents, MCP, and Skills, see the official Qwen Code docs.
For more Qwen Code examples, see Showcase.

FAQ

See FAQ.

​Install Qwen Code

​Configure and use Qwen Code

​Common commands

​Switch models (optional)

​Qwen Code IDE plugin (optional)

​Learn more

​FAQ

Install Qwen Code

Configure and use Qwen Code

Common commands

Switch models (optional)

Qwen Code IDE plugin (optional)

Learn more

FAQ