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

nemotron-3.5-lightning

Nemotron 3.5 Lightning 30B A3B

Made by NVIDIA. Sold by 2 providers, from $0.06 per million input tokens.

Maker
NVIDIA
Released
2026-08-11
Context
1,049K tokens
Max output
1,049K tokens
Input
text
Output
text
Open weights
Yes
Knowledge cutoff
2025-09

Where to buy it

ProviderInput $/MOutput $/MBlended*Holds your promptTraining
DeepInfra$0.06$0.16$0.08runs it 🇺🇸 United Statesno training
nebius$0.06$0.24$0.10runs it 🇳🇱 Netherlandsno 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 →