modelbenchmark.io

Nvidia Nemotron 3.5 Lightning

NVIDIA · nemotron-3-5-lightning

Compare

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

Specification

most-agreed values

Context
1M
Max output
1M
Released
2026-08-11
Knowledge cutoff
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.06
Output
$0.24
Cache read
$0.01

Available from 9 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
kilo · freefreefree1M66K
openrouter · freefreefree1M66K
nano-gpt$0.05$0.20$0.011M66K
nano-gpt · thinking$0.05$0.20$0.011M66K
vercel$0.05$0.20$0.01262K131K
nebius$0.06$0.24$0.061M1M
kilo$0.065$0.18262K131K
nano-gpt · tee$0.08$0.20$0.04262K66K
openrouter$0.08$0.20$0.04262K131K

Price history

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

DateHostField$/M
2026-09-02kiloInput$0.08
2026-09-12kiloInput$0.065
2026-09-02openrouterInput$0.08
2026-09-06openrouterInput$0.08
2026-09-02openrouter · freeInputfree
2026-09-06openrouter · freeInputfree
2026-09-02kiloOutput$0.20
2026-09-12kiloOutput$0.18
2026-09-02openrouter · freeOutputfree
2026-09-06openrouter · freeOutputfree
2026-09-03nebiusInput$0.06
2026-09-06nebiusInput$0.06
2026-09-03nebiusOutput$0.24
2026-09-06nebiusOutput$0.24

Other listings of this model

same model, different key

More from NVIDIA

most-hosted first