nvidia

NVIDIA: Nemotron 3.5 Lightning

Name: NVIDIA: Nemotron 3.5 Lightning
Creator: nvidia
Published: 2026-08-11T12:52:31.000Z

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...

View source on OpenRouter Hugging Face

Overview

Model specifications

Context: 262,144 tokens
Maximum output: 131,072 tokens
Architecture: text->text
Tokenizer: Other
Knowledge cutoff: Not provided
Moderated: No

Capabilities

Input → Output

Input

text

Output

text

Reasoning

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Available providers

2 providers

DeepInfra

bf16

Context: 262K
Maximum output: 131K
Input: $0.080
Output: $0.200
Cache read: $0.040
Cache write: Not provided

CoreWeave

bf16

Context: 262K
Maximum output: 236K
Input: $0.100
Output: $0.250
Cache read: $0.050
Cache write: Not provided

nvidia

models

All models

Nnvidia

Released Aug 14, 2026

NVIDIA: Nemotron 3.5 ASR Streaming Multilingual 0.6B

Nemotron 3.5 ASR Streaming Multilingual 0.6B is a speech recognition model from NVIDIA. Its prompt-conditioned, cache-aware FastConformer-RNNT design targets low-latency transcription across more than 40 languages for real-time captioning, voice...

Context: Not provided
Input: audio
Output: transcription

Input: $3.33Output: Freeper 1M tokens

View model details →

Nnvidia

Released Aug 11, 2026