NVIDIA
Nemotron 3 Ultra 550b A55b
nvidia/nemotron-3-ultra-550b-a55b
1M context·16.4K max output·text->text
Input
$0.5000
per 1M tokens
Output
$2.20
per 1M tokens
Cache Read
-
not available
Cache Write
-
not available
Quality Benchmarks
GoodValue: 71.4
Coding
Code generation, completion, debugging
Math
Competition math, calculus, olympiad
Reasoning
Logic, spatial, puzzle solving
Language
Summarization, paraphrase, writing
Overall
Source: LiveBench (livebench.ai) / Scores 0-100
Capabilities
VisionTool UseReasoningPrompt Caching
Similar Price Range
More from NVIDIA
Deploy your AI agent for $33/mo flat.
Managed Telegram bot hosting. We handle the infrastructure.
Any model. Any channel. Zero infrastructure.