Nvidia Nemotron Nano 3 30B
Context
262K
Max output
8K
Serving providers
1
Cheapest input
$0.06 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
127 t/s
tokens / second
Time to first token
3.76s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 1% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 925.3 | default | — | |||||||||||||
| ||||||||||||||||
| GDPval | 483.8 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 76% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 10% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 71% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 74% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 34% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 79% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -51.6 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| SciCode | 30% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 14% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 7% | reasoning: true | — | |||||||||||||
| τ-bench Banking | 6% | reasoning: true | — | |||||||||||||
| τ²-bench | 41% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Amazon BedrockCheapest | $0.06 | $0.24 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$31
estimated / month
Model IDs
copy the exact identifier for your platformnvidia.nemotron-nano-3-30b
Frequently asked questions
Nvidia Nemotron Nano 3 30B pricing, context and availabilityHow much does Nvidia Nemotron Nano 3 30B cost?
Nvidia Nemotron Nano 3 30B costs $0.06 per 1M input tokens and $0.24 per 1M output tokens at its cheapest provider via Amazon Bedrock.
What is the context window of Nvidia Nemotron Nano 3 30B?
Nvidia Nemotron Nano 3 30B accepts up to 262K tokens of context and can return up to 8K output tokens.
What can Nvidia Nemotron Nano 3 30B do?
Nvidia Nemotron Nano 3 30B supports tool use.
Other NVIDIA models
compare pricing across the NVIDIA lineupNvidia Nemotron Nano 9B$0.04/1M · 3 providersNvidia Nemotron Nano 12B$0.20/1M · 2 providersLlama 3.3 Nemotron Super 49B$0.10/1M · 1 providerNemotron Nano V2 12B VL$0.10/1M · 1 providerLlama 3.3 Nemotron Super 49B V1.5$0.10/1M · 1 providerLlama3 1 Nemotron 70B Instruct FP8$0.12/1M · 1 providerNvidia Nemotron Super 3 120B$0.15/1M · 1 providerNemotron 120B A12b$0.30/1M · 1 provider
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI