Model FatigueLLMs under $1, measured — and who holds your data
Models

gemma-4-31b-it

Gemma 4 31B IT

Made by Google. Sold by 1 provider, from $0.09 per million input tokens.

Maker
Google
Released
2026-04-02
Context
262K tokens
Max output
262K tokens
Input
text, image
Output
text
Open weights
Yes
Knowledge cutoff
2025-12

Where to buy it

ProviderInput $/MOutput $/MBlended*Holds your promptTraining
DeepInfra$0.09$0.34$0.15runs it 🇺🇸 United Statesno training
DeepInfra$0.20$0.40$0.25runs it 🇺🇸 United Statesno training
DeepInfra$0.27$0.76$0.39runs it 🇺🇸 United Statesno training

Blended is our calculation: (3 × input + output) ÷ 4, US dollars per million tokens — most calls read far more than they write. Tiers that are cheaper because they train on your data are not used for the “from” price.

Compare with every other model →