Nemotron 3 Ultra 550B A55B

nvidia/nemotron-3-ultra-550b-a55b

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Compare

Context window: 1M
Input: Text
Output: Text
Released: 2026-06-04

Max output: 128K
Model parameters: 550B
Active parameters: 55B
Weights: Open
Capabilities: Open weight, Reasoning, Temperature, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

Overall capability

44.5/100

Coding: 39.6
Reasoning: 44.9
Professional work: 39.2
Knowledge & language: 49.9


Terminal-Bench Science · AANemotron 3 Ultra 550B A55B (Reasoning)	Reasoning	Artificial Analysis	2026-11-05
BullshitBench v2	Knowledge & language	BullshitBench	2026-11-05
AutomationBench-AANemotron 3 Ultra 550B A55B (Reasoning)	Professional work	Artificial Analysis	2026-11-05
IFBench（Artificial Analysis）Nemotron 3 Ultra 550B A55B (Reasoning)	Knowledge & language	Artificial Analysis	2026-11-05
AA-LCRNemotron 3 Ultra 550B A55B (Reasoning)	Knowledge & language	Artificial Analysis	2026-11-05
AA-Analyst AgentNemotron 3 Ultra 550B A55B (Reasoning)	Professional work	Artificial Analysis	2026-11-05
SciCodeNemotron 3 Ultra 550B A55B (Reasoning)	Coding	Artificial Analysis	2026-11-05
Terminal-Bench 4.0 (AA rerun)Nemotron 3 Ultra 550B A55B (Reasoning)	Coding	Artificial Analysis	2026-11-05

Providers

No providers found

ModelRegistry · Catalog updated 2026-11-05