All AI models · LLM benchmarks · Methodology

NVIDIA

Nemotron 3 Ultra 550B A55B

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

Model facts

Context window
1.05M tokens
Maximum output
128K tokens
Cheapest paid input
$0.1 per 1M tokens
Cheapest paid output
$0.1 per 1M tokens
Open weights
yes
Providers
14

Capabilities and modalities

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

Local hardware estimate

At 4K context: Q4_K_M 301.7 GiB, Q8_0 562.7 GiB, F16 1052.1 GiB working memory.

Parameters
560.5 billion
Architecture
nemotronh
Model license
other

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning38.349.3not measured148.3

Observed price history

  • 2026-08-24: $0.1 input / $0.1 output per 1M tokens

API providers

  • Kenari — model id nemotron-3-ultra-550b-a55b; free input / free output per 1M tokens; provider documentation
  • Requesty — model id nemotron-3-ultra-550b-a55b; free input / free output per 1M tokens; provider documentation
  • UnoRouter — model id nemotron-3-ultra-550b-a55b:free; free input / free output per 1M tokens; provider documentation
  • routing.run — model id nemotron-3-ultra; $0.1 input / $0.1 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id nemotron-3-ultra-550b; $0.5 input / $2.2 output per 1M tokens; provider documentation
  • Eden AI — model id deepinfra/nemotron-3-ultra-550b-a55b; $0.5 input / $2.2 output per 1M tokens; provider documentation
  • Kilo Gateway — model id nvidia/nemotron-3-ultra-550b-a55b; $0.5 input / $2.2 output per 1M tokens; provider documentation
  • Fireworks AI — model id accounts/fireworks/models/nemotron-3-ultra-nvfp4; $0.6 input / $2.4 output per 1M tokens; provider documentation
  • Nvidia — model id nvidia/nemotron-3-ultra-550b-a55b; $0.5 input / $2.5 output per 1M tokens; provider documentation
  • Pioneer — model id nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16; $0.5 input / $2.5 output per 1M tokens; provider documentation
  • OpenRouter — model id nvidia/nemotron-3-ultra-550b-a55b; $0.625 input / $3.12 output per 1M tokens; provider documentation
  • Eden AI — model id nebius/nvidia/Nemotron-3-Ultra-550b-a55b; $1 input / $3 output per 1M tokens; provider documentation
  • Nebius Token Factory — model id nvidia/Nemotron-3-Ultra-550b-a55b; $1 input / $3 output per 1M tokens; provider documentation
  • Together AI — model id nvidia/nemotron-3-ultra-550b-a55b; $0.6 input / $3.6 output per 1M tokens; provider documentation