Back to all models

Nemotron 3 Ultra 550B

NVIDIA's most capable model with 550B parameters for complex reasoning, coding, and multimodal tasks.

nemotron-3-ultra-550b
STABLEGet StartedView uptime
1,048,576 context
Starting at $0.50/M input tokens
Starting at $2.50/M output tokens
Streaming
Vision
Tools
Reasoning
JSON Output
No ratings yetSign in to rate

Select Provider

All Providers for Nemotron 3 Ultra 550B

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

DeepInfra
Context: 262.1kQuant: fp4
Input
$0.5
/M tokens
Cache Read
$0.15
/M tokens
Output
$2.5
/M tokens
Get Started
Nebius AI
Context: 1.0MQuant: fp4
Input
$1
/M tokens
Cache Read
—
/M tokens
Output
$3
/M tokens
Get Started