Qwen 3 Max Thinking

alibaba

The most capable Qwen reasoning model, integrating thinking and non-thinking modes for comprehensive problem-solving. In thinking mode, it combines deliberate reasoning with web search, web extraction, and code interpreter tools to tackle complex challenges with greater accuracy. With a 256K context window and 65K output tokens, this model excels at problems requiring both deep thought and external tool use.

Try Now

Capabilities

Tool Use

Extended Thinking

Example Use Cases

Complex multi-step reasoning with tool access

Need deliberate slow thinking for difficult problems

Combining reasoning with web search or code execution

Technical Specifications

Context Window

262,144 tokens

Max Output

65,536 tokens

Cache Miss Cost

$1.20 per 1M tokens

Non-Reasoning Cost

$6 per 1M tokens

Cache Read Cost

$0.24 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls