Nemotron 3 Ultra
Review Nemotron 3 Ultra on key metrics including price, context length, throughput, and model features.
AuthorNvidia
Context Length512.3k
Supports Tools
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it supports text input and output with a context window of up to 1M tokens. It is suited for long-running agentic workflows, including agent orchestration, coding agents, deep research, and complex enterprise tasks.
Activity
Last 14 daysPrompt
431Completion
403Total
834Startup
Startup
Latency (p50)0.67s
Throughput (p50)-
Pricing
Input$0.30/M tokens
Output$1.80/M tokens
Cached input$0.10/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools