All Models

Nemotron 3 Ultra 550B A55B

nemotron Reasoning Tool Calling Open Weights Structured Output

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...

Providers 4
Released Jun 4, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

37.8
Intelligence Index
49.3
Coding Index

Available Providers (4)

Provider Model ID Input Cost Output Cost Context Max Output Docs
LLM Gateway nemotron-3-ultra-550b $0.50/MTok $2.50/MTok 1M 128K
Nvidia nvidia/nemotron-3-ultra-550b-a55b $0.50/MTok $2.50/MTok 1M 65.5K
OpenRouter nvidia/nemotron-3-ultra-550b-a55b $0.50/MTok $2.20/MTok 262.1K 16.4K
Together AI nvidia/nemotron-3-ultra-550b-a55b $0.60/MTok $3.60/MTok 512.3K 512.3K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output