tokenstat
tokenstat

Llama-3.1-Nemotron-Ultra-253B-v1

nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 · rates as of · Benchmarks · Plans · Calculator

Flagship Nemotron model for high-throughput reasoning and complex agents

Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
128K
tokens
Offers
5
2 sources

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. Showing free/$0 offers. Hide them.

SourceProviderInputOutputCache readContext
models.devcheapestnvidia/llama-3.1-nemotron-ultra-253b-v1NVIDIA$0$0$0128K
models.devnvidia/Llama-3_1-Nemotron-Ultra-253B-v1Nebius$0.6$1.80$0.06128K
LiteLLMnebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1$0.6$1.80$0.06
LiteLLMnvidia/Llama-3.1-Nemotron-Ultra-253B-v1$0.6$1.80$0.06
LiteLLMLlama-3.1-Nemotron-Ultra-253B-v1$0.6$1.80$0.06

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2024-12Released: 2025-01-15Family: 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