Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) is developed by NVIDIA, released 2025-04-07.
Input price
$0.60 / 1M tok
Output price
$1.80 / 1M tok
Blended price
$0.90 / 1M tok
Intelligence
8.9
Coding
—
Math
63.7
Speed
53 tok/s
Time to first token
0.69s
Official pricing from NVIDIA. Multi-gateway price comparison
(OpenRouter, Together, etc.) is coming soon.
See all of NVIDIA's models on its provider page, or browse the full model directory.