Skip to content
Not available in this workspace
OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Collections
  • Providers
  • Pricing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Support
  • Works With OR
  • Data

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for nvidia

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

nvidia/llama-3.1-nemotron-ultra-253b-v1

Model weights

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 Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node.

Note: you must include detailed thinking on in the system prompt to enable reasoning. Please see Usage Recommendations(opens in new tab) for more.

Modalities

Context

131K

Released

Apr 8, 2025

Knowledge Cutoff

Mar 2024

About NVIDIA: Llama 3.1 Nemotron Ultra 253B v1

OpenRouter makes NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 available through a unified, OpenAI-compatible API using the model ID nvidia/llama-3.1-nemotron-ultra-253b-v1.

NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 accepts text and returns text. It has a 131,072-token context window.

It was released on April 8, 2025; its knowledge cutoff is March 31, 2024.

More models from Nvidia

  • Nemotron 3.5 ASR Streaming Multilingual 0.6B
  • Nemotron 3.5 Lightning
  • Nemotron 3 Embed 1B (free)

Frequently asked questions

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 Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency.

Llama 3.1 Nemotron Ultra 253B v1 has a 131,072 token context window.

Nemotron 3.5 Lightning, Nemotron 3.5 Content Safety (free), Nemotron 3 Ultra and 5 more are other text models from Nvidia.

Llama 3.1 Nemotron Ultra 253B v1 was released on April 8, 2025. Its knowledge cutoff is March 31, 2024.

ActivityFAQ

Activity

Token volume and request traffic to this model over time.