NVIDIA NIM model
Llama 3.1 Nemotron Ultra 253B V1 on NVIDIA NIM
Llama 3.1 Nemotron Ultra 253B V1 is a NVIDIA NIM model tracked in Sim. It supports a 131k token context window. Pricing starts at $0.6/1M input tokens and $1.8/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.
Input price$0.6/1M
Cached inputN/A
Output price$1.8/1M
Context window131k
Max output8k tokens
ProviderNVIDIA NIM
UpdatedJul 9, 2026
Temperature0 to 2
Reasoning effortNot supported
VerbosityNot supported
Thinking levelsNot supported
Structured outputsSupported
Tool choiceSupported
Computer useNot supported
Deep researchNot supported
Memory supportSupported
Max output tokens8k
Frequently asked questions
Llama 3.1 Nemotron Ultra 253B V1 is a NVIDIA NIM model available in Sim. Llama 3.1 Nemotron Ultra 253B V1 is a NVIDIA NIM model tracked in Sim. It supports a 131k token context window. Pricing starts at $0.6/1M input tokens and $1.8/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.
