Head to head

Gemma 3n E4B IT vs GPT-OSS 20B

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.

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

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