Qwen: Qwen3.6 Max Preview

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse Mixture-of-Experts architecture with approximately 1T total parameters. It is optimized for high-end reasoning, agentic coding, tool use, instruction following, and complex text generation workflows.

Why It Looks Great

• Proprietary frontier Qwen model for demanding reasoning and coding workloads
• Sparse Mixture-of-Experts architecture with approximately 1T total parameters
• Strong fit for agentic coding, tool use, complex reasoning, and instruction-following tasks
• 262K-token context window for long prompts, repository-scale context, documents, and multi-turn workflows
• Up to 64K output tokens for extended reasoning, coding, and structured generation
• Thinking mode support for reasoning-heavy requests
• Function calling and tool-use support for agentic application workflows
• Structured output support for JSON responses and schema-constrained generation

Key Features

• Architecture: Sparse Mixture-of-Experts
• Total Parameters: approximately 1T
• Context Window: 262,144 tokens
• Max Input: 196,608 tokens
• Max Output: 65,536 tokens
• Thinking Budget: 128K tokens
• Input: Text
• Output: Text
• Vision: Not listed
• Function Calling: Supported
• Structured Outputs: Supported
• Thinking Mode: Supported
• Built-in Tools: Not listed
• Batch Calling: Not listed
• Audio Input: Not listed
• Image Generation: Not listed
• Supported Parameters: include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_logprobs, top_p

Specifications

Pricing

How to Use

1. Write your prompt - describe the task, provide context, and specify the desired output format.
2. Submit - the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1
API Endpoint: chat/completions
Model ID: qwen/qwen3.6-max-preview

API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

response = client.chat.completions.create(
    model="qwen/qwen3.6-max-preview",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen/qwen3.6-max-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

• Model: qwen/qwen3.6-max-preview
• Provider: alibaba
• Best suited for high-end reasoning, agentic coding, tool use, long-context text workflows, and structured output generation