Head to head

Qwen3.8 2.4T-A95B vs o3

On a blended workload of one million input tokens and three million output tokens, Qwen3.8 2.4T-A95B is 1.2× cheaper than o3.

Qwen3.8 2.4T-A95Bo3
Provider Together AI OpenAI
Input / MTok $2.5 $2
Output / MTok $6.25 $8
Cache read / MTok $0.5
Context window 200,000
Blended 1M in + 3M out $21.25 $26.00
Status ga ga

Qwen3.8 2.4T-A95B detail   o3 detail