Head to head

GPT-OSS 20B vs Gemma 3n E4B IT

On a blended workload of one million input tokens and three million output tokens, Gemma 3n E4B IT is 1.5× cheaper than GPT-OSS 20B.

GPT-OSS 20BGemma 3n E4B IT
Provider Together AI Together AI
Input / MTok $0.05 $0.06
Output / MTok $0.2 $0.12
Cache read / MTok
Context window 128,000 32,768
Blended 1M in + 3M out $0.65 $0.42
Status ga ga

GPT-OSS 20B detail   Gemma 3n E4B IT detail