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

llama-4-scout-17b-16e-instruct

Llama 4 Scout 17B 16E Instruct

Made by Meta. Sold by 1 provider, from $0.10 per million input tokens.

Maker
Meta
Released
2025-04-05
Context
328K tokens
Max output
131K tokens
Input
text, image
Output
text
Open weights
Yes
Knowledge cutoff
2024-08

Where to buy it

ProviderInput $/MOutput $/MBlended*Holds your promptTraining
DeepInfra$0.10$0.30$0.15runs 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 →