/

/

/

Nemotron 3 Ultra 550B A55B

NVIDIA logo

Nemotron 3 Ultra 550B A55B

NVIDIA Nemotron 3 Ultra is a 550B hybrid MoE model for multi-agent and complex reasoning workloads.

MODALITIES

CONTEXT

1,000,000 tokens

ARTIFICIAL ANALYSIS CODING

49.3

ARTIFICIAL ANALYSIS INTELLIGENCE

22.9

PROVIDERS / REGIONS

All live provider offers for this model, with region and token pricing.

Provider

Product

Context (tokens)

Location

Input/M tokens

Output/M tokens

Cached Input

Artificial Analysis Coding

Artificial Analysis Intelligence

Support ZDR

Perplexity logo

Perplexity

Nemotron 3 Ultra 550B A55B

262,144

global

$

0.25

$

2.5

$

0.25

49.3

22.9

No

NVIDIA logo

NVIDIA

Nemotron 3 Ultra 550B A55B

1,000,000

global

-

-

—

49.3

22.9

No

Nebius logo

Nebius

Nemotron 3 Ultra 550B A55B

1,048,576

global

$

1

$

3

—

49.3

22.9

No

Baseten logo

Baseten

Nemotron Ultra

202,800

global

$

0.6

$

2.4

$

0.12

49.3

22.9

No

Base pricing shown. Rates may vary by usage and processing conditions.

Features

Supported features from the live CMS record.

Reasoning

Tool calling

Streaming

Support may vary by provider.

Explore the full model garden

Compare providers, capabilities, and pricing across the live Orq.ai catalog.

Build on sovereign EU infrastructure