tokenstat
tokenstat

Nemotron 3 Ultra 550B A55B

fireworks_ai/nemotron-3-ultra-nvfp4 · rates as of · Benchmarks · AI plans · Calculator

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

Cheapest input
$0.6
$/MTok · models.dev
Cheapest output
$2.40
$/MTok
Context
262K
tokens
Sources
2
4 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestaccounts/fireworks/models/nemotron-3-ultra-nvfp4Fireworks AI$0.6$2.40$0.12262K
models.devnemotron-3-ultra-nvfp4Requesty$0.6$2.40$0.12262K
LiteLLMaccounts/fireworks/models/nemotron-3-ultra-nvfp4N/A$0.6$2.40$0.12N/A
LiteLLMnemotron-3-ultra-nvfp4N/A$0.6$2.40$0.12N/A

Capabilities

  • Reasoning
  • Tool calling
  • Open weights
  • In: text
  • Out: text
Released: 2026-06-13Family: nemotron

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.