NVIDIA · Released Apr 1, 2026
Nemotron 3.5 Lightning
NVIDIA's latency-optimized open model engineered for high-concurrency microservices, instant autocomplete, and low-latency agents.
OpenRating Index
36.6
0–100 composite
Reasoning Index
51.5
0–100 composite
Cost / Task
$0.076
benchmark run
Output speed
285 tok/s
blended tok/s
Time to first token
0.3s
median latency
Input price
$0.04
per 1M tokens
Output price
$0.16
per 1M tokens
Context window
128K
tokens
Strengths
284 tok/s high-speed generation
Ultra-low latency (0.31s TTFT)
Minimal resource footprint for edge and server deployment
How we rate Nemotron 3.5 Lightning
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
36.6
Reasoning Index
51.5
Token Pricing
Input per 1M tokens
$0.04
Output per 1M tokens
$0.16
Cost of 1M input + 1M output
$0.2
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.076 total).
Related models
Compare Nemotron 3.5 Lightning with the models it is most often measured against.