Qwen (Tongyi) Series

Qwen 3.7 generation flagship model, designed for the AI agent era. Coding, office tasks, and long-cycle autonomous execution capabilities comprehensively improved. Supports thinking mode switching, function calling, and web search. Million-level context.

The strongest preview model in the Qwen3.6 series, suited for complex reasoning, multi-step code generation, and tool-based tasks.

Balanced flagship model, supports million-level context window, function calling, and built-in tools. Suited for most production scenarios.

Balanced performance model, suited for most production scenarios. Outstanding Chinese capability and fast response speed.

High-speed response model, suited for latency-sensitive scenarios. Highly cost-efficient.

from openai import OpenAI

client = OpenAI(
    api_key="sk-air-your-key",
    base_url="https://nexusflow.vip/v1",
)

# Use Qwen to handle long text
response = client.chat.completions.create(
    model="qwen3.6-plus",
    messages=[
        {"role": "system", "content": "You are a professional document analysis assistant."},
        {"role": "user", "content": "Please summarize the main points of the following long document content... (you can input very long text here)"}
    ],
    max_tokens=4096,
)

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