NVIDIA logo

Nemotron 3 Ultra 550B A55B

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

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

Input modalitiesT
Output modalitiesT
Source-linkednemotronOpen weightsReleased 2026-06-04
Report data
Context window1M
Maximum output128K
Provider offers8
Knowledge cutoffUndisclosed
Capabilities

What this model supports

ReasoningYes
Tool callingYes
Structured outputNo
AttachmentsNo
Temperature controlYes
Open weightsYes
Creator
NVIDIA
Family
nemotron
Modalities
Text
License
Not documented
Release date
2026-06-04
Model ID
nvidia/nemotron-3-ultra-550b-a55b
Market availability

Provider pricing

Report price →
Providers offering Nemotron 3 Ultra 550B A55B
ProviderProvider model IDContextInput / 1MOutput / 1MCached / 1MFeaturesAll pricing
UnoRouter logoUnoRouternemotron-3-ultra-550b-a55b:free1M$0 if offer.cost.input is defined else '—'}}$0 if offer.cost.output is defined else '—'}}$0 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "input": 0,
  "output": 0
}
routing.run logorouting.runnemotron-3-ultra131.072K$0.1 if offer.cost.input is defined else '—'}}$0.1 if offer.cost.output is defined else '—'}}$0 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "input": 0.1,
  "output": 0.1
}
Nvidia logoNvidianvidia/nemotron-3-ultra-550b-a55b1M$0.5 if offer.cost.input is defined else '—'}}$2.5 if offer.cost.output is defined else '—'}}$0.15 if offer.cost.cache_read is defined else '—'}}R T S
View
{
  "cache_read": 0.15,
  "input": 0.5,
  "output": 2.5
}
Pioneer logoPioneernvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF161M$0.5 if offer.cost.input is defined else '—'}}$2.5 if offer.cost.output is defined else '—'}}$0.15 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "cache_read": 0.15,
  "cache_write": 0.5,
  "input": 0.5,
  "output": 2.5
}
LLM Gateway logoLLM Gatewaynemotron-3-ultra-550b262.144K$0.5 if offer.cost.input is defined else '—'}}$2.5 if offer.cost.output is defined else '—'}}$0.15 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "cache_read": 0.15,
  "input": 0.5,
  "output": 2.5
}
OpenRouter logoOpenRouternvidia/nemotron-3-ultra-550b-a55b1M$0.5 if offer.cost.input is defined else '—'}}$2.2 if offer.cost.output is defined else '—'}}$0.1 if offer.cost.cache_read is defined else '—'}}R T S
View
{
  "cache_read": 0.1,
  "input": 0.5,
  "output": 2.2
}
Together AI logoTogether AInvidia/nemotron-3-ultra-550b-a55b512.3K$0.6 if offer.cost.input is defined else '—'}}$3.6 if offer.cost.output is defined else '—'}}$0.2 if offer.cost.cache_read is defined else '—'}}R T S
View
{
  "cache_read": 0.2,
  "input": 0.6,
  "output": 3.6
}
Vercel AI Gateway logoVercel AI Gatewaynvidia/nemotron-3-ultra-550b-a55b1M$0.6 if offer.cost.input is defined else '—'}}$2.4 if offer.cost.output is defined else '—'}}$0.12 if offer.cost.cache_read is defined else '—'}}R T ·
View
{
  "cache_read": 0.12,
  "input": 0.6,
  "output": 2.4
}
Evidence

Published benchmark results

Agentic Index vs top 8 models
GPT-5.6 Sol
54.0
Claude Fable 5
52.8
GPT-5.6 Terra
47.4
Anthropic: Claude Opus 4.8
47.2
Claude Sonnet 5
46.7
xAI: Grok 4.5
45.7
GPT-5.6 Luna
45.6
Nemotron 3 Ultra 550B A55B
27.4
BrowseComp vs top 8 models
GPT-5.6 Sol
90.4
GPT-5.5 Pro
90.1
GPT-5.4 Pro
89.3
GPT-5.6 Terra
87.5
Claude Sonnet 5
84.7
GPT-5.5
84.4
MiniMax-M3
83.5
Nemotron 3 Ultra 550B A55B
44.4
Coding Index vs top 8 models
GPT-5.6 Sol
77.4
GPT-5.6 Terra
76.7
Claude Fable 5
76.5
GPT-5.5
74.9
Anthropic: Claude Opus 4.8
74.3
Anthropic: Claude Opus 4.7
73.6
xAI: Grok 4.5
72.4
Nemotron 3 Ultra 550B A55B
49.3
Design Arena: 3d vs top 8 models
Z.ai: GLM 5.2
1371.0
Claude Fable 5
1366.0
Anthropic: Claude Opus 4.6
1349.0
Kimi K2.6
1348.0
xAI: Grok 4.5
1338.0
Z.ai: GLM 5.1
1336.0
DeepSeek V4 Pro
1326.0
Nemotron 3 Ultra 550B A55B
1209.0
Design Arena: asciiart vs top 8 models
Claude Fable 5
1374.0
Anthropic: Claude Opus 4.7
1324.0
Gemini 3.1 Pro Preview
1313.0
Anthropic: Claude Opus 4.8
1308.0
Gemini 3.5 Flash
1305.0
Anthropic: Claude Opus 4.6
1303.0
GPT-5.5
1296.0
Nemotron 3 Ultra 550B A55B
1118.0
Design Arena: codecategories vs top 8 models
Z.ai: GLM 5.2
1351.0
Claude Fable 5
1345.0
Anthropic: Claude Opus 4.6
1336.0
Anthropic: Claude Opus 4.7
1330.0
xAI: Grok 4.5
1327.0
Z.ai: GLM 5.1
1321.0
Kimi K2.6
1320.0
Nemotron 3 Ultra 550B A55B
1164.0
Design Arena: dataviz vs top 8 models
Z.ai: GLM 5.1
1366.0
Claude Fable 5
1363.0
xAI: Grok 4.5
1330.0
Anthropic: Claude Opus 4.6
1322.0
Anthropic: Claude Opus 4.7
1322.0
Anthropic: Claude Sonnet 4.6
1316.0
Z.ai: GLM 5.2
1316.0
Nemotron 3 Ultra 550B A55B
1151.0
Design Arena: gamedev vs top 8 models
Claude Fable 5
1383.0
Z.ai: GLM 5.2
1353.0
Claude Sonnet 5
1345.0
GPT-5.5
1344.0
Anthropic: Claude Opus 4.6
1339.0
Anthropic: Claude Opus 4.7
1336.0
MiMo-V2.5-Pro
1334.0
Nemotron 3 Ultra 550B A55B
1191.0
Design Arena: svg vs top 8 models
Claude Fable 5
1365.0
Gemini 3.1 Pro Preview
1340.0
Gemini 3.5 Flash
1297.0
Anthropic: Claude Opus 4.6
1278.0
GPT-5.5
1277.0
Anthropic: Claude Opus 4.7
1274.0
Z.ai: GLM 5.1
1273.0
Nemotron 3 Ultra 550B A55B
1128.0
Design Arena: uicomponent vs top 8 models
Claude Fable 5
1401.0
Anthropic: Claude Opus 4.7
1359.0
Anthropic: Claude Opus 4.6
1343.0
Z.ai: GLM 5.2
1335.0
Z.ai: GLM 5.1
1331.0
Qwen: Qwen3.7 Max
1330.0
Anthropic: Claude Sonnet 4.6
1320.0
Nemotron 3 Ultra 550B A55B
1167.0
Design Arena: website vs top 8 models
Z.ai: GLM 5.2
1346.0
Claude Fable 5
1338.0
Anthropic: Claude Opus 4.6
1331.0
Anthropic: Claude Opus 4.7
1329.0
xAI: Grok 4.5
1325.0
Anthropic: Claude Sonnet 4.6
1320.0
Claude Sonnet 5
1314.0
Nemotron 3 Ultra 550B A55B
1133.0
GDPval vs top 6 models
GPT-5.5
84.9
GPT-5.4
83.0
GPT-5.5 Pro
82.3
GPT-5.4 Pro
82.0
Nemotron 3 Ultra 550B A55B
46.7
Step 3.7 Flash
45.8
GPQA vs top 1 models
Nemotron 3 Ultra 550B A55B
87.0
Humanity's Last Exam vs top 8 models
Claude Fable 5
64.5
Muse Spark 1.1
62.1
GPT-5.4 Pro
58.7
Claude Opus 4.8
57.9
GPT-5.5 Pro
57.2
Claude Opus 4.7
54.7
GPT-5.5
52.2
Nemotron 3 Ultra 550B A55B
37.4
IFBench vs top 2 models
Nemotron 3 Ultra 550B A55B
81.7
Grok 4.3
81.0
Intelligence Index vs top 8 models
Claude Fable 5
59.9
GPT-5.6 Sol
58.9
Anthropic: Claude Opus 4.8
55.7
GPT-5.6 Terra
55.0
GPT-5.5
54.8
xAI: Grok 4.5
53.8
Anthropic: Claude Opus 4.7
53.5
Nemotron 3 Ultra 550B A55B
37.8
LiveCodeBench vs top 3 models
Fugu Ultra
93.2
Fugu
92.9
Nemotron 3 Ultra 550B A55B
89.0
MMLU-Pro vs top 1 models
Nemotron 3 Ultra 550B A55B
86.8
SWE-Bench Multilingual vs top 7 models
Ornith 1.0 397B
78.9
Claude Sonnet 5
78.3
Qwen3.7 Max
78.3
Grok 4.5
78.0
LongCat-2.0
77.3
Ornith 1.0 35B
69.3
Nemotron 3 Ultra 550B A55B
67.7
SWE-Bench Verified vs top 8 models
Claude Fable 5
95.0
Claude Opus 4.8
88.6
Claude Sonnet 5
85.2
Ornith 1.0 397B
82.4
DeepSeek V4 Pro
80.6
Qwen3.7 Max
80.4
Kimi K2.6
80.2
Nemotron 3 Ultra 550B A55B
70.7
Terminal-Bench vs top 8 models
GPT-5.6 Sol
88.8
Claude Fable 5
88.0
GPT-5.6 Terra
87.4
GPT-5.6 Luna
84.7
Grok 4.5
83.3
GPT-5.5
82.7
Muse Spark 1.1
80.0
Nemotron 3 Ultra 550B A55B
56.4