Skip to main content

Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

Input / output price
$0.06 / $0.16 per 1M
Context
1M tokens
Released
Aug 11, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "nemotron-3.5-lightning".

Read docs

Providers

6 providers, cheapest first, retired then OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/nemotron-lightning-3.5-30b
$0.05/M$0.20/M
IO.netionet/nvidia/nemotron-3.5-lightning
$0.05125/M$0.17/M
DeepInfradeepinfra/nemotron-3.5-lightning
$0.06/M$0.16/M
Nebiusnebius/nemotron-3.5-lightning
$0.06/M$0.24/M
FireworksRetiredfireworks/nemotron-3.5-lightning
$0.05/M$0.20/M

Is a provider down? Fireworks AI status, OpenRouter status

Pricing

Averaged across 6 providers, in USD per 1M tokens after gateway discounts.

Average input
$0.06 per 1M
Average output
$0.19 per 1M
Average cache read
$0.03 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.07/MOpenRouterLowest$0.05/MConcentrate and Fireworks

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

33tokens/sacross providers

Faster than 59% of the other 595 models on the gateway

Response latency

Lower is better

4.5sacross providers

Faster than 32% of the other 756 models on the gateway

Benchmarks

The Respan Index plus 7 published scores from 2 sources, each linked to where it was published.

16.1/ 100

Respan Index#155 of 176

176 ranked models. The shaded band is this model's 95% interval, 11.9 to 25.6. DeepSeek V3 0324 and GPT-4o fall inside it, so the gap is within the margin of error.
Nemotron 3.5 Lightning by category: Coding 1.4, Agents 13.5, Reasoning 20.5, Knowledge & language 13.7, Human preference 38.9
  1. 155NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP416.1
  2. 153DeepSeek V3 032416.3
  3. 156GPT-4o16.0

Published scores

BenchmarkScore
SWE-bench Verifiedhuggingface.co52.8%
Terminal-Bench 2.1huggingface.co23.5%

Compare Nemotron 3.5 Lightning: NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4, NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs Muse Spark 1.3, NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs NVIDIA Nemotron 3.5 Super VL 120B-A12B NVFP4, NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs NVIDIA Nemotron 3 Super 120B-A12B, NVIDIA Nemotron 3.5 Lightning 30B-A3B NVFP4 vs NVIDIA Nemotron 3 Nano 30B-A3B BF16

Apps

Use Nemotron 3.5 Lightning in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Nemotron 3.5 Lightning FAQ

Short answers, built from the data on this page.

Nemotron 3.5 Lightning is a model from NVIDIA, released on Aug 11, 2026. NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total.

On the Respan gateway, input starts at $0.05 per 1M tokens on Concentrate and Fireworks, and output starts at $0.16 per 1M tokens on DeepInfra, after gateway discounts. Averaged across its 6 providers, it costs $0.06 per 1M input tokens and $0.19 per 1M output tokens.

Nemotron 3.5 Lightning is available through 6 providers: Concentrate, IO.net, DeepInfra, Nebius, Fireworks, and OpenRouter.

Nemotron 3.5 Lightning accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "nemotron-3.5-lightning". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Nemotron 3.5 Lightning scores 16.1 out of 100 on the Respan Index v1.1, ranking #155 of 176 models. By category: Coding 1.4, Agents 13.5, Reasoning 20.5, Knowledge & language 13.7, and Human preference 38.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Nemotron 3.5 Lightning has 7 published benchmark scores, including SWE-bench Verified 52.8%, BrowseComp 36.8%, and GPQA Diamond 75.6%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.