Head to head

GPT-OSS 20B vs Qwen3.5 9B

On a blended workload of one million input tokens and three million output tokens, GPT-OSS 20B is 1.4× cheaper than Qwen3.5 9B.

GPT-OSS 20BQwen3.5 9B
Provider Together AI Together AI
Input / MTok $0.05 $0.17
Output / MTok $0.2 $0.25
Cache read / MTok
Context window 128,000 262,144
Blended 1M in + 3M out $0.65 $0.92
Status ga ga

GPT-OSS 20B detail   Qwen3.5 9B detail