Nemotron 3.5 Lightning
Review Nemotron 3.5 Lightning on key metrics including price, context length, throughput, and model features.
AuthorNvidia
Context Length262.1k
Supports Tools
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 benefit from domain-specific customization.
Activity
Last 14 daysPrompt
699Completion
4KTotal
4KStartup
Startup
Latency (p50)0.57s
Throughput (p50)137.6 tok/s
Pricing
Input$0.04/M tokens
Output$0.10/M tokens
Cached input$0.02/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools