Qwen3 hybrid reasoning model enables seamless switching between thinking and non-thinking modes during conversations. It achieves SOTA reasoning performance at its scale and significantly outperforms Qwen2.5-14B in general capabilities.
Try NowMid-size reasoning model needed
Moderate complexity with good efficiency
Self-hosted reasoning task
131,072 tokens
8,192 tokens
$0.35 per 1M tokens
$1.40 per 1M tokens
$4.20 per 1M tokens
$15 per 1K calls
$0.19 per 1K calls