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

Tool Use

Extended Thinking

Example Use Cases

Dedicated reasoning without hybrid mode

Competitive math or coding problem

Self-hosted reasoning model

Technical Specifications

Context Window

32,768 tokens

Max Output

32,768 tokens

Cache Miss Cost

$0.15 per 1M tokens

Non-Reasoning Cost

$0.40 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus