Qwen3-Max

Copied!
Try AIAdd to Compare
Text GenerationReasoning

Overview

Text GenerationReasoning

The Qwen 3 series Max model has undergone specialized upgrades in agent programming and tool invocation compared to the preview version. The officially released model this time has achieved state-of-the-art (SOTA) performance in its field and is better suited to meet the demands of agents operating in more complex scenarios.

Input

Text

Output

Text

Features

Prefix Completion

Function Calling

Cache

Structured Outputs

Batches

Web Search

Pricing

  • Input
    $1.2Per 1M tokens
  • Output
    $6Per 1M tokens
  • Input(Implicit Cache)
    $0.24Per 1M tokens
  • Input(Batch File)
    $0.6Per 1M tokens
  • Output(Batch File)
    $3Per 1M tokens
  • Explicit Cache Creation
    $1.5Per 1M tokens
  • Explicit Cache Read
    $0.12Per 1M tokens
  • Input
    $1.2Per 1M tokens
  • Output
    $6Per 1M tokens
  • Input(Implicit Cache)
    $0.24Per 1M tokens
  • Input(Batch File)
    $0.6Per 1M tokens
  • Output(Batch File)
    $3Per 1M tokens
  • Explicit Cache Creation
    $1.5Per 1M tokens
  • Explicit Cache Read
    $0.12Per 1M tokens

Context

Context
262.14K
Max Input
258.04K
Max Output
65.53K

Rate Limits

  • RPMRequests Per Minute
    600
  • TPMTokens Per Minute
    1M

Built-in Tools

search_strategy:agentCompletions API
web_searchResponses API
code_interpreterResponses API
web_extractorResponses API

API Reference

Get API Key
Copied!
12345678910111213141516171819202122232425262728293031
import os
from dashscope import Generation
import dashscope
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who are you?"},
]
response = Generation.call(
    # If the environment variable is not set, replace it with your Model Studio API key: api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-max",
    messages=messages,
    result_format="message",
    # Enable deep thinking
    enable_thinking=True,
)

if response.status_code == 200:
    # Print thinking process
    print("=" * 20 + "Thinking process" + "=" * 20)
    print(response.output.choices[0].message.reasoning_content)
    
    # Print response
    print("=" * 20 + "Full response" + "=" * 20)
    print(response.output.choices[0].message.content)
else:
    print(f"HTTP return code: {response.status_code}")
    print(f"Error code: {response.code}")
    print(f"Error message: {response.message}")