NVIDIA model product
1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression.
Updated Aug 12, 2026. Default version: Llama 3.1 Nemotron Ultra 253B v1
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Preference and agent-evaluation results for the default version.
| text style control | overall | 196 | 1347.5 | 2,549 | N/A | |
| text | overall | 206 | 1319.5 | 2,549 | N/A |
Provider-specific output speed and catalog latency for Llama 3.1 Nemotron Ultra 253B v1. Runtime does not affect the capability score.
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| Nvidia | nvidia/llama-3.1-nemotron-ultra-253b-v1 | global | N/A | N/A | 128K | |
| Cortecs | llama-3.1-nemotron-ultra-253b-v1 | global | $0.598 | $1.79 | 128K | |
| Nebius Token Factory | nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | global | $0.60 | $1.8 | 128K | |
| LLM Gateway | llama-3.1-nemotron-ultra-253b | global | $0.60 | $1.8 | 128K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| Llama 3.1 Nemotron Ultra 253B v1 | 30.5 | 253B | N/A | N/A | No | Llama 3.1 Community License |
Key information about Llama 3.1 Nemotron Ultra 253B and its available data.
1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression. It underwent multi-phase post-training (SFT for Math, Code, Reasoning, Chat, Tool Calling; RL with GRPO) to enhance reasoning and instruction-following. Optimized for accuracy/efficiency tradeoff on NVIDIA GPUs.
Supports 128k context.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about Llama 3.1 Nemotron Ultra 253B.
Llama 3.1 Nemotron Ultra 253B's default version was released on Apr 7, 2025.
No official standard PAYG price is currently available for Llama 3.1 Nemotron Ultra 253B. The lowest tracked third-party offer starts at $0.598 input and $1.79 output via Cortecs.
Llama 3.1 Nemotron Ultra 253B was created by NVIDIA.
A context window is not available for the default version.
No. The default version is not marked as having publicly available weights.
4 provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen3 VL 30B A3B Thinking, Qwen3 32B, GPT-5-nano.