Head to head

Safety GPT-OSS 20B vs Qwen3.5 9B

On a blended workload of one million input tokens and three million output tokens, Qwen3.5 9B is 1.1× cheaper than Safety GPT-OSS 20B.

Safety GPT-OSS 20BQwen3.5 9B
Provider Groq Together AI
Input / MTok $0.075 $0.17
Output / MTok $0.3 $0.25
Cache read / MTok
Context window 131,072 262,144
Blended 1M in + 3M out $0.97 $0.92
Status preview ga

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