QwQ 32B Preview · deepinfra

QwQ is an experimental research model developed by the Qwen Team, designed to advance AI reasoning capabilities. This model embodies the spirit of philosophical inquiry, approaching problems with genuine wonder and doubt. QwQ demonstrates impressive analytical abilities, achieving scores of 65.2% on GPQA, 50.0% on AIME, 90.6% on MATH-500, and 50.0% on LiveCodeBench. With its contemplative approach and exceptional performance on complex problems.

Base modelAll models on this baseAll models of the providerto the provider

All Qwen models at every provider

Input, $/1M $0.12

Output, $/1M $0.18

Context 32 768

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —