Jump to Content

Qwen Code

Qwen Code is an open-source command-line tool from Qwen designed to streamline AI-assisted coding workflows.

Qwen Code Integration

1.1 Usage

Method 1: Configuration File

First, export your API key in the environment:

export RYGEN_API_KEY="your-rygen-api-key"

Next, update your configuration file located at ~/.qwen/settings.json

Add the following configuration:

{
  "modelProviders": {
    "openai": [
      {
        "id": "minimax/minimax-m2.5",
        "name": "Rygen Minimax M2.5",
        "envKey": "RYGEN_API_KEY",
        "baseUrl": "https://api.rygen.io/v1",
        "generationConfig": {
          "timeout": 120000,
          "maxRetries": 2,
          "samplingParams": {
            "temperature": 0.2,
            "max_tokens": 8192
          }
        }
      }
    ]
  },
  "security": {
    "auth": {
      "selectedType": "openai"
    }
  },
  "model": {
    "name": "minimax/minimax-m2.5"
  }
}

Once configured, launch Qwen Code:

qwen

Method 2: Runtime Flags

For quick testing without modifying configuration files, you can pass parameters directly via CLI:

export RYGEN_API_KEY="your-rygen-api-key"

qwen --auth-type openai \
  --model minimax/minimax-m2.5 \
  --openaiApiKey "$RYGEN_API_KEY" \
  --openaiBaseUrl https://api.rygen.io/v1

1.2 References