Qwen3 hybrid reasoning model enables seamless switching between thinking and non-thinking modes during conversations. It delivers strong reasoning performance with fewer parameters, comparable to QwQ, and significantly outperforms Qwen2.5-72B-Instruct in general capabilities, achieving state-of-the-art (SOTA) results for its scale.
Try Now131,072 tokens
8,192 tokens
$0.70
$2.80
$8.40
$15
$0.19
Base 235B; superseded by instruct-tuned variant