Head to head

Aura-2 vs Gemma 3n E4B IT

On a blended workload of one million input tokens and three million output tokens, Aura-2 is 420000.0× cheaper than Gemma 3n E4B IT.

Aura-2Gemma 3n E4B IT
Provider Deepgram Together AI
Input / MTok $0.06
Output / MTok $0.12
Cache read / MTok
Context window 32,768
Blended 1M in + 3M out $0.00 $0.42
Status ga ga

Aura-2 detail   Gemma 3n E4B IT detail