Question 1

What is Nemotron 3.5 Lightning?

Accepted Answer

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. It is suited for high-throughput agentic workloads and specialized tasks that...

Question 2

How much does Nemotron 3.5 Lightning cost?

Accepted Answer

On the Respan gateway, input starts at $0.05 per 1M tokens on Fireworks, and output starts at $0.16 per 1M tokens on DeepInfra and OpenRouter, after gateway discounts. Averaged across 4 providers, it costs $0.06 per 1M input tokens and $0.19 per 1M output tokens.

Question 3

Which providers serve Nemotron 3.5 Lightning on Respan?

Accepted Answer

4 providers serve Nemotron 3.5 Lightning: Fireworks, DeepInfra, OpenRouter, and Nebius. Fireworks requires your own provider API key (BYOK).

Question 4

What is Nemotron 3.5 Lightning's context window?

Accepted Answer

Nemotron 3.5 Lightning accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Nemotron 3.5 Lightning with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ 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.

Question 6

How fast is Nemotron 3.5 Lightning?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 144 tokens per second, and the lowest response latency was 0.5 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Nemotron 3.5 Lightning rank on the Respan Index?

Accepted Answer

Nemotron 3.5 Lightning scores 14.0 out of 100 on the Respan Index v1.1, ranking #129 of 138 models. By category: Coding 1.7, Agents 15.0, Reasoning 11.7, Knowledge & language 12.2, and Human preference 37.7. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Nemotron 3.5 Lightning score on benchmarks?

Accepted Answer

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 llmmetric.com.

Provider	Context	Input	Output
FireworksBYOK only`fireworks_ai/nemotron-lightning-3p5-30b-a3b`	262K	$0.05/M	$0.20/M
DeepInfra`deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning`	262K	$0.06/M	$0.16/M
OpenRouter`openrouter/nvidia/nemotron-3.5-lightning`	262K	$0.06/M	$0.16/M
Nebius`nebius/nvidia/Nemotron-3_5-Lightning`	1.0M	$0.06/M	$0.24/M

Nemotron 3.5 Lightning

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding2

Agents

Apps