Skip to content

NVIDIA · Chat

Nemotron 3.5 Lightning

NVIDIA 🇺🇸ChatOpen weights. One of its sources says the weights are publicly available.
From Aiml API's listing:
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model with 3B active parameters out of 30B total, built for high-throughput agentic workloads and specialized task execution with up to 1M context length.
llminfo IQ
116.2
Market median price
$0.0875 blended / 1M
Max context
1M
Listings
37

Evidence and sources

🤗 nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16llminfo IQ 116.2, ranked among chat models. From 12 benchmarks. A fair amount of data behind it.How llminfo IQ is computedFair value (49.3). Costs per task about what its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksMaker HQ: US (source)
All rankings: #22 on OpenRouter today #27 on OpenRouter this month #29 on OpenRouter this week #128 on NanoGPT recentlySources: Darkbloom data docs, IO Intelligence (io.net) data, DeepInfra data, Models.dev data, AI/ML API dataPrimary data from Darkbloom from IO Intelligence (io.net): name from DeepInfra: variant from Models.dev: weights availability from AI/ML API: primary mode, description

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 4 of the 9 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 8 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

ReasoningFunction callingStructured outputPrompt caching

Listings

 Aihubmixnemotron-3.5-lightning-free · freeSource: AIHubMix data docs1M$0.00$0.00——
 Flowdotnvidia/nemotron-3.5-lightning:free · freeSource: FlowDot data1M$0.00$0.00——
 Kilonvidia/nemotron-3.5-lightning:free · freeSources: Kilo AI Gateway data, Models.dev data1M$0.00$0.00——
 OpenRouterInference by NVIDIA NIMnvidia/nemotron-3.5-lightning:free · free, nvfp4 · nvfp4Source: OpenRouter data docs1M$0.00$0.00120442ms
 Vercelnvidia/nemotron-3.5-lightning-free · freeSources: Models.dev data, Vercel AI Gateway data1M$0.00$0.00——
 Opencodenemotron-3.5-lightning-free · freeSource: OpenCode Zen dataNot published by the provider$0.00$0.00——
 Darkbloomnvidia-nemotron-3.5-lightning · int4Source: Darkbloom data docsNot published by the provider$0.02cache read $0.01$0.096——
 NanoGPTInference by DarkbloomRegions: GLBnvidia/nemotron-3.5-lightning · int4Source: NanoGPTNot published by the provider$0.021$0.1008——
 Ionetnvidia/nemotron-3.5-lightningSource: IO Intelligence (io.net) data262K$0.0513cache read $0.0256$0.170.0691,472.571ms
 Fastrouternvidia/nemotron-3.5-lightningSource: FastRouter data262K$0.06cache read $0.03$0.16——
Show all 35 listings

Showing 10 of 35: the cheapest per 1M input tokens from each provider.

Also sold by DeepInfra, Nebius AI Studio, Nous Portal, Wavespeed.

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Agentic

Source: OpenRouter benchmark exports
7 Aug 2026 version · 90-day results
Across 8 providers lowest 65.4% median 66.8% highest 71.5%OpenRouter's automatic routing 65.6%
Show results from 8 providers and OpenRouter's automatic routingHide results from 8 providers and OpenRouter's automatic routing
  • Wafer
  • CoreWeave
  • Fireworks
  • Darkbloom
  • ModelRun
  • OpenRouter's automatic routing
  • Phala
  • DeepInfra
  • Io Net

Science

GPQA Diamond9 results
Source: OpenRouter benchmark exports
7 Aug 2026 version · 90-day results
Across 8 providers lowest 63.4% median 73% highest 74.8%OpenRouter's automatic routing 70.6%
Show results from 8 providers and OpenRouter's automatic routingHide results from 8 providers and OpenRouter's automatic routing
  • Wafer
  • ModelRun
  • Io Net
  • CoreWeave
  • Phala
  • DeepInfra
  • OpenRouter's automatic routing
  • Darkbloom
  • Fireworks

Multilingual

Benchmark Nusantara4 related benchmarks · 4 results

Human preference

Other

Data credits: Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · Benchmark Nusantara, ibahasa (M. Khoirul Huda), doi:10.5281/zenodo.21970463. Test results CC BY 4.0, attribution to ibahasa; aggregate results CSV only. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)

Also known as: deepinfra/nvidia/nvidia-nemotron-3.5-lightning, nebius/nvidia/nemotron-3_5-lightning, nemotron-3.5-lightning-free, nvidia-nemotron-3.5-lightning, nvidia/nemotron-3.5-lightning, nvidia/nemotron-3.5-lightning-free, nvidia/nemotron-3.5-lightning:free, nvidia/nemotron-3.5-lightning:thinking, nvidia/nemotron-3_5-lightning, nvidia/nvidia-nemotron-3.5-lightning

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works