All AI models · LLM benchmarks · Methodology

NVIDIA

Nemotron Ultra

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Model facts

Context window
203K tokens
Maximum output
203K tokens
Cheapest paid input
$0.6 per 1M tokens
Cheapest paid output
$2.4 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: $0.6 input / $2.4 output per 1M tokens

API providers

  • Baseten — model id nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B; $0.6 input / $2.4 output per 1M tokens; provider documentation