Head to head

Gemma 4 31B IT vs Codestral

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

Gemma 4 31B ITCodestral
Provider Together AI Mistral
Input / MTok $0.39 $0.3
Output / MTok $0.97 $0.9
Cache read / MTok
Context window 262,144
Blended 1M in + 3M out $3.30 $3.00
Status ga ga

Gemma 4 31B IT detail   Codestral detail