tokenstat
homepricingstatshelpsign in
tokenstat
NVIDIA

Nemotron Ultra

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B · rates as of · Benchmarks · 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
Offers
3
1 source

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BBaseten$0.6$2.40$0.12203K
models.devnvidia-nemotron-3-ultra-550b-a55bVenice AI$0.625$3.13$0.1875256K
models.devnvidia/NVIDIA-Nemotron-3-Ultra-550B-A55BWeights & Biases$0.75$2.75$0.15262K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Released: 2026-06-04Family: nemotron

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash