ModelBeat
Models/Nemotron 3.5 Lightning
All models
N

NVIDIA: Nemotron 3.5 Lightning

Watch this modelCompareFind source
nvidia/nemotron-3.5-lightning

Nemotron 3.5 Lightning is NVIDIA’s AI model, released Aug 11, 2026. It costs $0.06/M input and $0.16/M output tokens, and handles a 262K-token context window.

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

Context
262K
Input
$0.06 / 1M
Output
$0.16 / 1M
Released
Aug 11, 2026
Modalities
text→text

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Nemotron 3.5 Lightning lands among all models tracked on Model Beat.

9.0
Intelligence Index
Artificial Analysis
9th percentile of tracked models
7.0
Coding Index
Artificial Analysis
7th percentile of tracked models

Reasoning

2 evals
GPQA Diamond74.3%

Graduate-level scientific reasoning

Humanity's Last Exam10.6%

Frontier of human expert knowledge

Coding

1 evals
SciCode32.1%

Scientific research coding

In the news

1

Changelog

12
  • Nemotron 3.5 Lightning: cheapest credible provider via DeepInfra now $0.16 per 1M output tokens (was $0.2, -20%)cheapest provider · Oct 1, 2026
  • Nemotron 3.5 Lightning: cheapest credible provider via DeepInfra now $0.06 per 1M input tokens (was $0.07, -14%)cheapest provider · Oct 1, 2026
  • Nemotron 3.5 Lightning: context window changed from 1,000,000 to 262,144 tokenscontext · Sep 29, 2026
  • Nemotron 3.5 Lightning: context window changed from 262,144 to 1,000,000 tokenscontext · Sep 25, 2026
  • Nemotron 3.5 Lightning: cheapest credible provider via CoreWeave now $0.07 per 1M input tokens (was $0.08, -12%)cheapest provider · Sep 16, 2026
  • Nemotron 3.5 Lightning: cheapest credible provider via DeepInfra now $0.2 per 1M output tokens (was $0.25, -20%)cheapest provider · Aug 23, 2026
  • Nemotron 3.5 Lightning: cheapest credible provider via DeepInfra now $0.08 per 1M input tokens (was $0.1, -20%)cheapest provider · Aug 23, 2026
  • Nemotron 3.5 Lightning: context window changed from 1,000,000 to 262,144 tokenscontext · Aug 20, 2026
  • Nemotron 3.5 Lightning: context window changed from 1,048,576 to 1,000,000 tokenscontext · Aug 13, 2026
  • Nemotron 3.5 Lightning: context window changed from 1,000,000 to 1,048,576 tokenscontext · Aug 13, 2026
  • Nemotron 3.5 Lightning: context window changed from 262,144 to 1,000,000 tokenscontext · Aug 13, 2026
  • Nemotron 3.5 Lightning (NVIDIA) added to the tracker: $0.1/$0.25 per 1M, 262K context.tracked · Aug 11, 2026

Compare Nemotron 3.5 Lightning with

Nemotron 3.5 Lightning vs GPT-6 AstraNemotron 3.5 Lightning vs Claude Fable 5Nemotron 3.5 Lightning vs Kimi K3Nemotron 3.5 Lightning vs Gemini 3.7 FlashNemotron 3.5 Lightning vs Grok 4.6

Frequently asked questions

What is 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.

Who created Nemotron 3.5 Lightning?

Nemotron 3.5 Lightning is an AI model developed by NVIDIA, part of the Nemotron family, released Aug 11, 2026.

How much does Nemotron 3.5 Lightning cost?

Nemotron 3.5 Lightning is served from $0.06 per million input tokens and $0.16 per million output tokens (cheapest credible provider on OpenRouter: DeepInfra).

What is Nemotron 3.5 Lightning's context window?

Nemotron 3.5 Lightning supports a context window of up to 262K tokens.

How does Nemotron 3.5 Lightning perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Nemotron 3.5 Lightning scores 10.6% on Humanity's Last Exam, 74.3% on GPQA Diamond, 32.1% on SciCode.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Oct 6, 2026.