1. Standard Python API Usage

The API is compatible with OpenAI's specification. Notably, Qwen3.6-Plus introduces a new preserve_thinking parameter. This is highly recommended for agentic tasks, as it preserves the reasoning context across multiple turns, improving decision consistency and saving tokens.

from openai import OpenAI
import os

# Set your API Key from Alibaba Cloud Model Studio
api_key = os.environ.get("DASHSCOPE_API_KEY")
if not api_key:
    raise ValueError("DASHSCOPE_API_KEY is required. Set it via: export DASHSCOPE_API_KEY='your-api-key'")

client = OpenAI(
    api_key=api_key,
    base_url=os.environ.get(
        "DASHSCOPE_BASE_URL", 
        "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
    ),
)

messages = [{"role": "user", "content": "Explain the concept of vibe coding."}]
model = os.environ.get("DASHSCOPE_MODEL", "qwen3.6-plus")

completion = client.chat.completions.create(
    model=model,
    messages=messages,
    extra_body={
        "enable_thinking": True, 
        # "preserve_thinking": True, # Uncomment for agentic tasks
    },
    stream=True
)

reasoning_content = "" 
answer_content = "" 
is_answering = False 

print("\n" + "=" * 20 + " Reasoning " + "=" * 20 + "\n")

for chunk in completion:
    if not chunk.choices:
        continue
    
    delta = chunk.choices[0].delta
    
    # Print reasoning process
    if hasattr(delta, "reasoning_content") and delta.reasoning_content is not None:
        if not is_answering:
            print(delta.reasoning_content, end="", flush=True)
            reasoning_content += delta.reasoning_content
            
    # Print actual answer
    if hasattr(delta, "content") and delta.content:
        if not is_answering:
            print("\n" + "=" * 20 + " Answer " + "=" * 20 + "\n")
            is_answering = True
        print(delta.content, end="", flush=True)
        answer_content += delta.content

2. Integrating with OpenClaw

Qwen3.6-Plus is highly compatible with OpenClaw (formerly Moltbot/Clawdbot), an open-source AI coding agent that runs directly in your terminal. Here is how to set it up:

# Ensure you have Node.js 22+ installed
curl -fsSL https://molt.bot/install.sh | bash # For macOS / Linux

# Set your API key
export DASHSCOPE_API_KEY=<your_api_key>

# Launch the OpenClaw dashboard in your browser
openclaw dashboard 

# Or open a new terminal and start the TUI
# openclaw tui 

On your first run, you'll need to point OpenClaw to Model Studio by editing your ~/.openclaw/openclaw.json file. Merge the following configuration into your existing file:

{
  "models": {
    "mode": "merge",
    "providers": {
      "modelstudio": {
        "baseUrl": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
        "apiKey": "DASHSCOPE_API_KEY",
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3.6-plus",
            "name": "qwen3.6-plus",
            "reasoning": true,
            "input": ["text", "image"],
            "contextWindow": 1000000,
            "maxTokens": 65536
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "modelstudio/qwen3.6-plus"
      }
    }
  }
}

3. Using Claude Code via Anthropic API Protocol

Because the Qwen API also supports the Anthropic API protocol, you can easily plug it into tools like Claude Code for an elevated, context-aware coding experience from your CLI.

# Install Claude Code globally
npm install -g @anthropic-ai/claude-code

# Configure your environment variables for Qwen
export ANTHROPIC_MODEL="qwen3.6-plus"
export ANTHROPIC_SMALL_FAST_MODEL="qwen3.6-plus"
export ANTHROPIC_BASE_URL="https://dashscope-intl.aliyuncs.com/apps/anthropic"
export ANTHROPIC_AUTH_TOKEN="<your_api_key>"

# Launch the CLI interface
claude

Real-World Applications for Engineering Students

With these tools at your disposal, what can you actually build? The capabilities of Qwen3.6-Plus open doors to highly complex projects:

• Autonomous Robotics Navigation: Use the model's spatial intelligence to process live camera feeds, recognize objects (like distinguishing a specific person in a crowd), and send navigation commands back to a microcontroller.
• Smart Visual Coding Assistants: Feed UI mockups or whiteboard wireframes into the model and have it generate the complete HTML/CSS/JS frontend code instantly.
• Automated Research Synthesizers: Utilize the 1M context window to ingest dozens of academic PDFs, extract specific data points, and generate a cohesive literature review or project plan.

Accelerate Your Journey with AcadKits

Building real-world agents is complex, but it doesn't have to be overwhelming. At AcadKits, we provide the foundational templates, hardware suggestions, and software development kits (SDKs) to help you integrate models like Qwen3.6-Plus seamlessly into your university projects or personal portfolio.

By leveraging our ready-made projects alongside Qwen's powerful reasoning and coding capabilities, you can spend less time debugging boilerplate code and more time innovating. You can quickly get up to speed with Qwen3.6-Plus and start developing intelligent agents that make a tangible difference.

Ready to push the boundaries of your engineering projects? Dive into the code snippets above, grab an API key, and start building.

For more tutorials on AI integration and hardware projects, keep exploring the AcadKits blog!