All AI models · LLM benchmarks · Methodology

NVIDIA

Nemotron 3.5 Lightning 30B

Nemotron model for efficient reasoning, coding, and specialized AI agents

Model facts

Context window
262K tokens
Maximum output
131K tokens
Cheapest paid input
$0.05 per 1M tokens
Cheapest paid output
$0.2 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Observed price history

  • 2026-08-24: free input / free output per 1M tokens
  • 2026-08-25: $0.05 input / $0.2 output per 1M tokens
  • 2026-08-26: $0.05 input / $0.15 output per 1M tokens
  • 2026-08-29: $0.05 input / $0.2 output per 1M tokens

API providers

  • Vercel AI Gateway — model id nvidia/nemotron-3.5-lightning; $0.05 input / $0.2 output per 1M tokens; provider documentation