NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

Llama3

Text

Paid

Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural...

Parameters

253B

Context Window

131,072

tokens

Input Price

$0.6

per 1M tokens

Output Price

$1.8

per 1M tokens

Capabilities

Model capabilities and supported modalities

Performance

Reasoning

Excellent reasoning capabilities with strong logical analysis

Math

Capable of solving most mathematical problems accurately

Coding

Capable of generating functional code with good practices

Knowledge

Good knowledge foundation across many domains

Modalities

Input Modalities

text

Output Modalities

text

LLM Price Calculator

Calculate the cost of using this model

Input Tokens (0.00000060/token)$0.000900

Output Tokens (0.00000180/token)$0.005400

Common Scenarios:

Input Cost:$0.000900

Output Cost:$0.005400

Total Cost:$0.006300

Estimated usage: 4,500 tokens

Monthly Cost Estimator

Based on different usage levels

Light Usage

$0.0240

~10 requests

Moderate Usage

$0.2400

~100 requests

Heavy Usage

$2.4000

~1000 requests

Enterprise

$24.0000

~10,000 requests

Note: Estimates based on current token count settings per request.

Last Updated: 2026/04/11