Other

NVIDIA: Nemotron 3.5 Lightning

nvidia/nemotron-3.5-lightning

canonical: nvidia/nemotron-3.5-lightning-20260807

Descriptionfrom OpenRouter

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...

Context length

262,144 tok

Max completion

235,929 tok

Knowledge cutoff

—

Expires

—

Added to OpenRouter

8/11/2026

Cache last refreshed

11/12/2026

Primary modality

text->text

Source

OpenRouter

Input modalities

text

Output modalities

text

Pricing

Field	Per token (USD)	Per million
prompt	0.00000007	$0.070
completion	0.0000002	$0.200
input_cache_read	0.00000004	$0.040

Supported parameters(19)

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

OpenRouter page Hugging Face

Videos

23:16

Benchmarking NVidia Nemotron 3.5 Lightning... how does is stack up against larger models?

Aug 12, 2026 · YouTube

Rounds

3 answersin this database. A round opens every model's answer to the same prompt.

Aug 14, 2026CodingThree bugs and a liein a video round answer
Aug 12, 2026CodingThree bugs and a lie10very badin a video round answer
Aug 12, 2026Real Life ChallengesTranslate video titles10very badin a video round answer