Chasing Next
Explore LessonsAI UpdatesBlogAbout
Log inFor TeamsStart for Free
Chasing Next

Learn AI by doing.

Start for FreeFor TeamsFree AI GuideAboutFAQUpdatesBlog
Sign UpSign InSupport
2026 Moonswell Marketing LLC·Terms·Privacy··
All Updates
PerplexityPerplexitymodel
August 12, 2026·Source

Nemotron 3.5 Lightning in the Perplexity Agent API

NVIDIA's open-weight Nemotron 3.5 Lightning is now available in Perplexity's Agent API, priced for the high-volume, repetitive parts of an agent's work.

Details

  • A 30 billion parameter open model that switches on only 3 billion of those parameters for any given request, which is where the speed and low price come from
  • Priced at $0.0115 per million input tokens and $0.17 per million output tokens, with cached input at $0.00115 per million
  • The model ID is perplexity/nemotron-3.5-lightning-30b-a3b
  • Available in both the Agent API and the Gateway API
  • Perplexity positions it as the execution layer you pair with a frontier model that does the planning

Best for

The cheap, repetitive steps inside an agent: calling tools, checking results, and handing work off to subagents.

When to use it

An agent is making the same kind of call thousands of times and a frontier model's price stops making sense.

Who benefits

Developers running always-on agents where the constraint is cost per call, not reasoning depth.

More from Perplexity

All updates
model
pplx-embed-v2-late
model
pplx-decider v1.1
api
Perplexity Decisions API
Chasing Next

Staying informed is great. Staying ahead is better.

Pick a topic and leave with something you created.

Start for FreeBring to Your Team

Get new module drops and weekly AI strategy.