NVIDIA: Nemotron 3 Ultra

550B / 55B

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE).

Context
262K
Max output
183K
Input price
$0.6/1M tokens
Output price
$2.4/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/nemotron-3-ultra-550b-a55b
Provider OpenRouter
Creator NVIDIA
Family—
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters550B / 55B
Architecture—
Context window262K tokens
Max input—
Max output183K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.6
Output
$2.4
Cache write
—
Cache read
$0.12
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/nvidia/nemotron-3-ultra-550b-a55b