nebius
Llama-3.1-Nemotron-Ultra-253B-v1
NVIDIA Llama 3.1 Nemotron Ultra is a reasoning model tuned for high-efficiency agentic workloads.
Provider:
nebius
Model type:
chat
Location:
europe
Context Window
8000
Intelligence Rating
Speed Rating
Cost Efficiency Rating
Pricing
$
0.6
Input tokens per million
$
1.8
Output tokens per million
Features
Tool Calling
Supported
Reasoning
Supported
