← Model list

Nemotron 3.5 Lightning

nvidia·nvidia/nvidia-nemotron-3.5-lightning-30b-a3b·GA·Open weights·nemotron series·NEW

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.

At a glance
Reference price$0.10 / $0.25 per 1M
Cache read $0.05 · Weights & Biases
Lowest paid$0.10 / $0.25
Weights & Biases Cloud
Context262,144
Output limit262,144
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
Text
Knowledge cutoff
Released / updated2026-08-11 / 2026-08-11

Quality & performanceArtificial Analysis · Intelligence Index v4.1

Intelligence23.6
Value172
Coding26.8
Agentic13.8
Output speed302 tok/s
TTFT1.16 s
Cost per task$0.0764
Value formulaIQ 23.6 ÷ min blended $0.138 = 172

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Weights & Biases
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
Cloud$0.10$0.25$0.05262,144262,144

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

1Weights & Biases$26.50
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)

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.25$02026-08-112026-08-132026-08-11 · Input list $0.102026-08-12 · Input list $0.102026-08-13 · Input list $0.102026-08-11 · Output list $0.252026-08-12 · Output list $0.252026-08-13 · Output list $0.252026-08-11 · Min blended $0.1382026-08-12 · Min blended $0.1382026-08-13 · Min blended $0.138