Head to head

Gemma 4 31B IT vs Llama 3.3 70B Versatile

On a blended workload of one million input tokens and three million output tokens, Llama 3.3 70B Versatile is 1.1× cheaper than Gemma 4 31B IT.

Gemma 4 31B ITLlama 3.3 70B Versatile
Provider Together AI Groq
Input / MTok $0.39 $0.59
Output / MTok $0.97 $0.79
Cache read / MTok
Context window 262,144 131,072
Blended 1M in + 3M out $3.30 $2.96
Status ga ga

Gemma 4 31B IT detail   Llama 3.3 70B Versatile detail