QwQ 32B

Alibaba

QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g., DeepSeek-R1, o1-mini.

Try Now

Capabilities

Thinking

Tool Use

Technical Specifications

Context Window

32,768 tokens

Max Output

32,768 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.15

Non-Reasoning Output

$0.40

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Reasoning research model; superseded by Qwen3.5 Plus

Recommended Replacement

Qwen3.6 Plus