Nemotron 3.5 Lightning 30B

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.

Input / 1M tokens$0.05

Output / 1M tokens$0.15

Maximum context262.1K

Inference providers3

Price comparison

USD per one million tokens, using current provider data.

Provider latency

Last-hour p50 in milliseconds; lower is better.

Provider uptime

Reported availability over the last 24 hours; not a contractual SLA.

Inference providers

Compare current pricing, performance, and privacy across every available provider.

Deepinfra

100.00%

Context262.1K

Max output131.1K

p50 latency341 ms

Throughput88.5 t/s

Input price$0.08

Output price$0.2

Zero retentionNo trainingCaching

Fireworks

100.00%

Context262.1K

Max output131.1K

p50 latency258 ms

Throughput357.0 t/s

Input price$0.05

Output price$0.2

Zero retentionNo trainingCaching

Runinfra

100.00%

Context262.1K

Max output131.1K

p50 latency837 ms

Throughput—

Input price$0.05

Output price$0.15

Caching

Provider	Maximum context	Max output	p50 latency	p50 throughput	24h uptime	Input / 1M tokens	Output / 1M tokens
Deepinfra	262.1K	131.1K	341 ms	88.5 t/s	100.000%	$0.08	$0.2
Fireworks	262.1K	131.1K	258 ms	357.0 t/s	100.000%	$0.05	$0.2
Runinfra	262.1K	131.1K	837 ms	—	100.000%	$0.05	$0.15