modelbenchmark.io

Nemotron 3.5 Lightning

NVIDIA · nvidia-nemotron-3-5-lightning-30b-a3b

Compare

Nemotron 3.5 Lightning is an MoE model built for fast, reliable agentic tasks across use cases such as financial services, cybersecurity, telecom, and retail.

Specification

most-agreed values

Context
262K
Max output
262K
Released
2026-08-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.07
Output
$0.20
Cache read
$0.04

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
wandb$0.07$0.20$0.04262K262K
wandb · wandb$0.10$0.25$0.05262K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02wandbCache read$0.05
2026-09-15wandbCache read$0.04
2026-09-02wandbInput$0.10
2026-09-15wandbInput$0.07
2026-09-02wandbOutput$0.25
2026-09-15wandbOutput$0.20

More from NVIDIA

most-hosted first