← Model list

Nemotron 3.5 Lightning 30B A3B

nvidia·nvidia/nemotron-3.5-lightning·GA·Open weights·nemotron series·NEW

Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads

At a glance
Official price$0 / $0 per 1M
Cache read · Nvidia
Lowest paid$0.05 / $0.15
RunInfra Gateway · 10× spread
3 more $0 channels
Context262,144
⚠ Providers report 8,192–1,048,576; the table below is authoritative
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff
Released / updated2026-08-11 / 2026-08-11

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 8 providers5 with public prices · 3 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaOfficial
nvidia/nemotron-3.5-lightning-30b-a3b
First-partyFree262,144262,144
Merge Gateway
nvidia/nemotron-3.5-lightning-30b-a3b
GatewayFree1,000,000262,144
Requesty
nemotron-3.5-lightning-30b-a3b
GatewayFree1,048,57665,536
RunInfra
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Gateway$0.05$0.15262,14432,768
Fireworks AI
accounts/fireworks/models/nemotron-lightning-3p5-30b-a3b
Cloud$0.05$0.20$0.01262,144262,144
OpenRouterGateway$0.08$0.20$0.04262,144131,072
Kilo GatewayGateway$0.08$0.20$0.04262,144131,072
Pioneer
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
Gateway$0.50$0.50$0.50$0.508,1924,096

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Fireworks AI$15.20
2RunInfra$17.50
3OpenRouter$21.20
4Kilo Gateway$21.20
5Pioneer$125.00

3 more channels offer $0 (Nvidia, Merge Gateway, Requesty); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

Toggle (on / off)effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokenseffort = xhigh

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.087$02026-08-122026-08-172026-08-12 · Input list $02026-08-13 · Input list $02026-08-17 · Input list $02026-08-12 · Output list $02026-08-13 · Output list $02026-08-17 · Output list $02026-08-12 · Min blended $0.0872026-08-13 · Min blended $0.0872026-08-17 · Min blended $0.075