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

gemma4-26b

Gemma 4 26B A4B IT

Made by Google. Sold by 1 provider, from $0.15 per million input tokens.

Maker
Google
Released
2026-04-02
Context
256K tokens
Max output
33K tokens
Input
text
Output
text
Open weights
Yes

Where to buy it

ProviderInput $/MOutput $/MBlended*Holds your promptTraining
Google Vertex AI$0.15$0.60$0.26runs it 🇺🇸 United Statesoff by default

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 →