Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

  1. Nemotron 3 Ultra (Free)NVIDIARemove
nemotron-3-ultra-550b-a55b:free
AttributeNemotron 3 Ultra (Free)nemotron-3-ultra-550b-a55b:free
Pricing
Input$0 / 1M
Output$0 / 1M
Cache Write$0 / 1M
Cache Read$0 / 1M
Context
Max context1M
Max outputN/A
Capabilities
VisionYes
Function CallingYes
JSON ModeYes
StreamingYes
Catalogue
ProviderNVIDIA
Categorychat
Charge typeFree
Released
Description
SummaryNVIDIA Nemotron 3 Ultra is an open frontier reasoning and orchestration model featuring a 550B-parameter Mixture-of-Experts (MoE) architecture with 55B active parameters per token. Built on a hybrid Transformer–Mamba design, it supports text input and output with a 1M-token context window, enabling large-scale reasoning and long-horizon task execution. Optimized for agent orchestration, coding agents, deep research, and complex enterprise workflows, the model excels at multi-step reasoning, planning, and sustained execution. With high-throughput inference designed for large-scale agent pipelines, Nemotron 3 Ultra serves as a powerful foundation for advanced agentic AI systems.