Skip to main content
NVIDIA/ Nemotron

Llama 3.1 Nemotron Ultra 253B

nvidia/nemotron/llama-3-1-nemotron-ultra-253b

Flagship Nemotron model for high-throughput reasoning and complex agents

Released
2025-04-07
Context window
128K
Max output
8.2K
Weights
Open weight

Modalities

Input
Text
Output
Text

Identity

Version
llama-3.1-nemotron-ultra-253b
Aliases
Llama 3.1 Nemotron Ultra 253B

Resources

Providers

ProviderProvider model IDProtocolContextMax outputInputOutputCapabilitiesNotesPricingStreaming
LLM Gatewayllama-3.1-nemotron-ultra-253bopenai_chat128K8.2K
Text
Text
ReasoningTool callTemperatureOpen weight
-
input $0.6/M
output $1.8/M
Yes

Capabilities

ReasoningTool callTemperatureOpen weight

FAQ