All AI models · LLM benchmarks · Methodology

Nemotron 3 Super 120B (Public Preview)

Nemotron middle tier for collaborative agents and high-volume reasoning workloads

Model facts

Context window
1M tokens
Maximum output
33K tokens
Cheapest paid input
$0.3 per 1M tokens
Cheapest paid output
$0.65 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: $0.3 input / $0.65 output per 1M tokens

API providers

  • DigitalOcean (NVIDIA) — model id nvidia-nemotron-3-super-120b; $0.3 input / $0.65 output per 1M tokens; provider documentation