Back to Explore
Nemotron 3 Ultra 550B A55B (Reasoning)
NVIDIA·Released 2026-06-04
Open Source
Comparison data ready73% coverage12/12 fields directly observedUpdated Jul 18, 2026, 6:01 PM
Related Models
NVIDIA: Nemotron 3 Ultra2026-06-04NVIDIA: Nemotron 3 Ultra (free)2026-06-04NVIDIA: Nemotron 3.5 Content Safety (free)2026-06-04Nemotron 3 Nano Omni 30B A3B Reasoning2026-04-29NVIDIA: Nemotron 3 Nano Omni (free)2026-04-28Nemotron Cascade 2 30B A3B2026-03-19NVIDIA: Nemotron 3 Super2026-03-11NVIDIA: Nemotron 3 Super (free)2026-03-11
Pricing
Input
$0.68
per 1M tokens
Output
$2.67
per 1M tokens
Blended
$1.18
per 1M tokens
Cheaper than 38% of models. Median price is $0.70/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$1.18
Monthly
$35.25
vs. Similar Models
Claude Opus 4.6 (Non-reasoning, High Effort)Q:0.0
$10.00+751%
Gemini 3 Flash Preview (Reasoning)Q:0.0
$1.13-4%
Grok 4.3 (high)Q:-0.2
$1.56+33%
GPT-5.2 (medium)Q:+0.2
$4.81+310%
Performance
195
tokens/sec
Faster than 88% of models
0.99
seconds
Faster than 57% of models
12.64
seconds
Faster than 37% of models
Market Median
94 tok/s
107% faster
Median TTFT
1.07s
7% faster
Throughput/Dollar
166
tok/s per $/1M
Speed Comparison
Gemini 2.5 Flash (Non-reasoning)
196 tok/s+0%
Grok 4.20 0309 (Non-reasoning)
200 tok/s+2%
Qwen3.7 Max
201 tok/s+3%
Benchmarks
MMLU-ProNot evaluated
GPQA Diamond
86.7%
HLE
26.6%
LiveCodeBenchNot evaluated
SciCode
39.9%
TerminalBench Hard
36.4%
MATH-500Not evaluated
AIMENot evaluated
AIME 2025Not evaluated
IFBench
81.4%
Long Context Recall
67.0%
Tau2
83.3%
Market AverageTop Score