Head to head

Gemma 4 31B Instruct (Pearl AI) vs Codestral

On a blended workload of one million input tokens and three million output tokens, Gemma 4 31B Instruct (Pearl AI) is 1.0× cheaper than Codestral.

Gemma 4 31B Instruct (Pearl AI)Codestral
Provider Together AI Mistral
Input / MTok $0.28 $0.3
Output / MTok $0.86 $0.9
Cache read / MTok
Context window 32,000
Blended 1M in + 3M out $2.86 $3.00
Status ga ga

Gemma 4 31B Instruct (Pearl AI) detail   Codestral detail