Nvidia Nemotron 3 Super 120B A12b
Context
262K
Max output
n/a
Serving providers
1
Cheapest input
$0.085 /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
145 t/s
tokens / second
Time to first token
1.31s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| APEX Agents | 2% | default | — | |||||||||||||
| Automation Bench | 0.0 | default | — | |||||||||||||
| CritPt | 3% | default | — | |||||||||||||
| GDPval (normalized)Frozen Aug 18, 2026 | 0% | default | — | |||||||||||||
| GPQA Diamond | 80% | default | — | |||||||||||||
| Humanity's Last Exam | 21% | default | — | |||||||||||||
| IFBench | 71% | default | — | |||||||||||||
| IT-Bench SRE | 1% | default | — | |||||||||||||
| Long-Context Reasoning | 66% | default | — | |||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.0 | default | — | |||||||||||||
| Omniscience | -41.5 | default | — | |||||||||||||
| Omniscience Accuracy | 0.2 | default | — | |||||||||||||
| Omniscience Non Hallucination | 0.1 | default | — | |||||||||||||
| SciCode | 36% | default | — | |||||||||||||
| Terminal Bench40 | 0 | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 29% | default | — | |||||||||||||
| TerminalBench v2.1 | 39% | default | — | |||||||||||||
| ||||||||||||||||
| τ-bench Banking | 10% | default | — | |||||||||||||
| τ²-bench | 68% | 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 expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.085 | $0.40 | 1 | ||||||||||
Standarddeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
| |||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Price history is accruing. We record a point each day a listed seller price changes; the full backfill lands shortly.
Cost calculator
estimate your monthly spend on this model$49
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
Frequently asked questions
Nvidia Nemotron 3 Super 120B A12b pricing, context and availabilityHow much does Nvidia Nemotron 3 Super 120B A12b cost?
Nvidia Nemotron 3 Super 120B A12b costs $0.085 per 1M input tokens from DeepInfra, and $0.40 per 1M output tokens from DeepInfra.
What is the context window of Nvidia Nemotron 3 Super 120B A12b?
Nvidia Nemotron 3 Super 120B A12b accepts up to 262K tokens of context.
What can Nvidia Nemotron 3 Super 120B A12b do?
Nvidia Nemotron 3 Super 120B A12b supports tool use, reasoning 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 3 Ultra 550B A55b$0.50/1M · 3 providersNvidia Nemotron Nano 12B V2$0.20/1M · 2 providersLlama 3.1 Nemotron 70B Instruct$0.60/1M · 2 providers
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