NVIDIA logo

Llama 3.1 Nemotron Ultra 253B

nvidia/llama-3.1-nemotron-ultra-253b

Flagship Nemotron model for high-throughput reasoning and complex agents

Source-linkednemotronOpen weightsReleased 2025-04-07
Report data
Context window128K
Maximum output8.192K
Provider offers1
Knowledge cutoffUndisclosed
Capabilities

What this model supports

ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
Creator
NVIDIA
Family
nemotron
Modalities
Text
License
Not documented
Release date
2025-04-07
Model ID
nvidia/llama-3.1-nemotron-ultra-253b
Market availability

Provider pricing

Report price →
Providers offering Llama 3.1 Nemotron Ultra 253B
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
LLM Gatewayllama-3.1-nemotron-ultra-253b128K$0.600$1.800· · S
View
{
  "input": 0.6,
  "output": 1.8
}
Evidence

Published benchmark results

Insufficient benchmark coverage. ModelBench does not infer a score from price, context size, or model name.