Llama-3.1-Nemotron-Ultra-253B-v1 API
About
Process massive datasets with Llama-3.1-Nemotron-Ultra-253B-v1, featuring an expansive 128K context window for long-document analysis. This model delivers cost-effective pricing at $0.60/1M input and $1.80/1M output tokens, native tool calling support, open weights architecture. Access Llama-3.1-Nemotron-Ultra-253B-v1 via the Nebius Token Factory API with up to 4K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
128K
Tokens
Input Limit
120K
Tokens
Max Output
4K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.60
Output
$1.80
Caching (per 1M tokens)
Read
$0.06
Write
$0.75
Frequently Asked Questions
Llama-3.1-Nemotron-Ultra-253B-v1 by Nebius Token Factory costs $0.60 per 1M input tokens and $1.80 per 1M output tokens. Cached reads cost $0.06 per 1M tokens. Cache writes cost $0.75 per 1M tokens.
Model Details
ID
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1
Provider
Nebius Token FactoryFamily
llama
Release Date
Jan 15, 2025
Knowledge Cutoff
Dec 1, 2024
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NEBIUS_API_KEY
API Base URL
https://api.tokenfactory.nebius.com/v1