Skip to main content
NVIDIA

Nemotron 3.5 Lightning

Nemotron 3.5 Lightning by NVIDIA — compare inference API pricing across providers.

Input from
$0.050 / 1M tokens
across 2 providers

API Pricing

Cheapest on Deep Infra 33% below avg
ProviderInput / 1MOutput / 1MCached / 1M
$0.050$0.200-
$0.100$0.250$0.050

Prices updated daily. Last check: Aug 12, 2026

Nemotron 3.5 Lightning pricing by provider

Input, output, and batch rates, plus alternatives, for one provider at a time.

Performance & Benchmarks

Source: Artificial Analysis →
Intelligence
23.6 / 100
Coding
26.8 / 100
Output Speed
276 t/s
Latency (TTFT)
958ms

Reasoning & Knowledge

  • GPQA Diamond74.3%
  • Humanity's Last Exam10.6%

Coding

  • SciCode31.6%

Agentic & Tool Use

  • Terminal-Bench v2.124.3%
  • τ-bench Banking8.9%

Instruction & Long Context

  • Long-Context Reasoning55.3%

Benchmarks measured Aug 2026. Scores are independent evaluations, not vendor-reported.

Model Details

General

Creator
NVIDIA
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No