Skip to main content

​
About the Provider

Alibaba Cloud is the cloud computing arm of Alibaba Group and the creator of the Qwen model family. Through its open-source initiative, Alibaba has released state-of-the-art language and multimodal models under permissive licenses, enabling developers and enterprises to build powerful AI applications across diverse domains and languages.

​
Model Quickstart

This section helps you quickly get started with the Qwen/Qwen3-Max model on the Qubrid AI inferencing platform. To use this model, you need:
  • A valid Qubrid API key
  • Access to the Qubrid inference API
  • Basic knowledge of making API requests in your preferred language
Once authenticated with your API key, you can send inference requests to the Qwen/Qwen3-Max model and receive responses based on your input prompts. Below are example placeholders showing how the model can be accessed using different programming environments.
You can choose the one that best fits your workflow. 
from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
    base_url="https://platform.qubrid.com/v1",
    api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
    model="Qwen/Qwen3-Max",
    messages=[
      {
        "role": "user",
        "content": "Explain quantum computing in simple terms"
      }
    ],
    max_tokens=4096,
    temperature=0.7,
    top_p=1,
    stream=True
)

# If stream = False comment this out
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

​
Model Overview

Qwen3-Max is Alibaba Cloud’s most powerful closed-source model in the Qwen3 series, featuring a 235B Mixture-of-Experts architecture with 22B parameters active per forward pass.
  • It delivers frontier-level performance in complex reasoning, multilingual tasks, long-context understanding, and advanced coding — rivaling GPT-4o and Claude Sonnet on major benchmarks.
  • Accessible exclusively via the DashScope API, it supports 29+ languages and a hybrid thinking mode for complex reasoning tasks.

​
Model at a Glance

FeatureDetails
Model IDQwen/Qwen3-Max
ProviderAlibaba Cloud (Qwen Team)
ArchitectureSparse Mixture-of-Experts (MoE) Transformer — 235B total / 22B active per token
Model Size235B params (22B active)
Parameters4
Context Length128K Tokens
Release DateApril 2025
LicenseProprietary — Alibaba Cloud DashScope API only
Training DataLarge-scale multilingual pretraining corpus with RLHF post-training (not publicly disclosed)

​
When to use?

You should consider using Qwen3 Max if:
  • You need complex multi-step reasoning tasks
  • Your application requires advanced coding and debugging
  • You are doing research and analytical writing
  • Your use case involves long-document summarization
  • You need multilingual chat and translation across 29+ languages
  • You are building enterprise chatbots and assistants

​
Inference Parameters

Parameter NameTypeDefaultDescription
StreamingbooleantrueEnable streaming responses for real-time output.
Temperaturenumber0.7Controls creativity and randomness. Higher values produce more diverse output.
Max Tokensnumber4096Maximum number of tokens the model can generate.
Top Pnumber1Controls nucleus sampling for more predictable output.

​
Key Features

  • 235B MoE Architecture: Frontier-level intelligence with only 22B parameters active per token.
  • Rivals GPT-4o and Claude Sonnet: Competitive performance on major reasoning, coding, and multilingual benchmarks.
  • 128K Context Window: Supports long-document analysis, extended conversations, and complex multi-turn workflows.
  • 29+ Languages: Strong multilingual performance with consistent instruction following across languages.
  • Hybrid Thinking Mode: Configurable reasoning depth for complex problem solving tasks.
  • Excellent Structured Output: Strong instruction following for JSON, function calling patterns, and schema-based responses.

​
Summary

Qwen3-Max is Alibaba Cloud’s flagship closed-source model, delivering GPT-4o and Claude Sonnet-level performance via the DashScope API.
  • It uses a 235B sparse MoE Transformer with 22B active parameters, released April 2025.
  • It supports 128K context, 29+ languages, and a hybrid thinking mode for complex reasoning.
  • The model excels at complex reasoning, advanced coding, long-document summarization, and multilingual enterprise workflows.
  • Licensed under Alibaba Cloud’s proprietary DashScope API license.