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

baseten

Baseten

1 model on Baseten, with the price per million tokens and who ends up holding your prompt.

Company based in
🇺🇸 United States
How it serves
Runs 1 model itself
Training on your prompts
no training
Data policy source
www.baseten.co
Policy checked
2026-10-20

Models

ModelInput $/MOutput $/MBlended*Holds your promptTraining
GLM-5.3$1.40$4.40$2.15runs 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.