---
id: "nvidia/nemotron-3.5-lightning"
also: ["nvidia/nemotron-3.5-lightning-20260807", "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "hf/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16", "vercel/nvidia/nemotron-3.5-lightning"]
cheapest_list_usd_per_m: "0.025 in, 0.12 out, at darkbloom/int4 on openrouter"
cheapest_effective_usd_per_m: "0.0176 in, 0.1196 out, at darkbloom/int4 on openrouter"
context: 262144
max_output: 235929
input: ["text"]
output: ["text"]
released: "2026-08-11"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 13
gateways: "openrouter (8), vercel (4), hf (1)"
no_training: 9
trains: 2
retains_prompts: 4
intelligence: 5.5000
coding: 26.8000
agentic: 3.5000
---
# NVIDIA: Nemotron 3.5 Lightning

NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.