Context
262K
Max output
203K
Serving providers
3
Cheapest input
$0.50 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
166 t/s
tokens / second
Time to first token
1.12s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.1 | default | — | |||||||||||||||||
| Automation Bench | 0.0 | default | — | |||||||||||||||||
| CritPt | 3% | default | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 2065.9 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1163.0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 87% | default | — | |||||||||||||||||
| Harvey Lab | 0.8 | default | — | |||||||||||||||||
| Humanity's Last Exam | 28% | default | — | |||||||||||||||||
| IFBench | 81% | default | — | |||||||||||||||||
| Long-Context Reasoning | 79% | default | — | |||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||
| Omniscience | -0.4 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.7 | default | — | |||||||||||||||||
| SciCode | 40% | default | — | |||||||||||||||||
| SWE-bench VerifiedHugging Face did not report this score in its latest run on Oct 14, 2026 | 72% | — | — | |||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 36% | default | — | |||||||||||||||||
| TerminalBench v2.1 | 54% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 14% | default | — | |||||||||||||||||
| τ²-bench | 83% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.50 to $0.60 per 1M tokens across 3 providers, so the dearest route costs 20% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.50 | $2.20 | 1 | |||||||||||||
Standarddeepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
| ||||||||||||||||
| Wandb | $0.50 | $2.15 | 1 | |||||||||||||
Standardwandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
| ||||||||||||||||
| Baseten | $0.60 | $2.40 | 1 | |||||||||||||
Standardbaseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Cost calculator
estimate your monthly spend on this model$276
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bwandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55Bbaseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
Frequently asked questions
Nvidia Nemotron 3 Ultra 550B A55b pricing, context and availabilityHow much does Nvidia Nemotron 3 Ultra 550B A55b cost?
Nvidia Nemotron 3 Ultra 550B A55b costs $0.50 per 1M input tokens from DeepInfra, and $2.15 per 1M output tokens from Wandb. Across 3 serving providers, input prices range from $0.50 to $0.60 per 1M tokens.
What is the context window of Nvidia Nemotron 3 Ultra 550B A55b?
Nvidia Nemotron 3 Ultra 550B A55b accepts up to 262K tokens of context and can return up to 203K output tokens.
Which providers serve Nvidia Nemotron 3 Ultra 550B A55b?
Nvidia Nemotron 3 Ultra 550B A55b is available from 3 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Nvidia Nemotron 3 Ultra 550B A55b do?
Nvidia Nemotron 3 Ultra 550B A55b supports image input (vision), tool use, reasoning, prompt caching and structured output.
Other NVIDIA models
compare pricing across the NVIDIA lineupNvidia Nemotron Nano 9B V2$0.04/1M · 4 providersNemotron 3 Nano 30B A3B$0.05/1M · 4 providersNemotron 3 Ultra$0.60/1M · 4 providersNemotron 3.5 Lightning$0.05/1M · 3 providersNemotron 3 Super$0.08/1M · 3 providersNvidia Nemotron Nano 12B V2$0.20/1M · 2 providersLlama 3.1 Nemotron 70B Instruct$0.60/1M · 2 providersNemotron Lightning 3.5 30B A3b$0.05/1M · 1 provider
Popular comparisons
head-to-head pages featuring Nvidia Nemotron 3 Ultra 550B A55b
Nvidia Nemotron 3 Ultra 550B A55b vs Claude Fable 5.1side-by-side pricing & benchmarks Nvidia Nemotron 3 Ultra 550B A55b vs Claude Opus 5side-by-side pricing & benchmarks
Nvidia Nemotron 3 Ultra 550B A55b vs DeepSeek V4.1 Flashside-by-side pricing & benchmarks Nvidia Nemotron 3 Ultra 550B A55b vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Nvidia Nemotron 3 Ultra 550B A55b vs Gemini 3.7 Flashside-by-side pricing & benchmarks Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI