← Model list

nemotron-3-ultra-nvfp4

nvidia·nvidia/nemotron-3-ultra-nvfp4·GA·Closed·nemotron series·NEW

Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.

At a glance
Reference price$0.54 / $2.16 per 1M
Cache read $0.108 · Requesty
Lowest paid$0.54 / $2.16
Requesty Gateway
Context262,144
Output limit262,144
Capabilities
ReasoningTool useStructured output? TemperatureAttachments
Modalities
Text
Knowledge cutoff
Released / updated2026-06-13 / 2026-06-13

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGateway$0.54$2.16$0.108262,144262,144

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Requesty$164.16
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.40$02026-08-192026-08-212026-08-19 · Input list $0.602026-08-21 · Input list $0.542026-08-19 · Output list $2.402026-08-21 · Output list $2.162026-08-19 · Min blended $1.052026-08-21 · Min blended $0.945