Nvidia Nemotron Nano 9B
Context
131K
Max output
131K
Serving providers
3
Cheapest input
$0.04 /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
123 t/s
tokens / second
Time to first token
7.00s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 0% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 20.3 | default | — | |||||||||||||
| ||||||||||||||||
| GPQA Diamond | 57% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 5% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 28% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 72% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 23% | default | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 74% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -42.9 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| SciCode | 22% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 2% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| τ²-bench | 23% | default | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.04 to $0.20 per 1M tokens across 3 providers, so the dearest route costs 400% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.04 | $0.16 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Amazon Bedrock | $0.06 | $0.23 | 1 | ||||||||||||||||
| |||||||||||||||||||
| Fireworks AI | $0.20 | $0.20 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$21
estimated / month
Model IDs
copy the exact identifier for your platformdeepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2nvidia.nemotron-nano-9b-v2fireworks_ai/accounts/fireworks/models/nvidia-nemotron-nano-9b-v2
Frequently asked questions
Nvidia Nemotron Nano 9B pricing, context and availabilityHow much does Nvidia Nemotron Nano 9B cost?
Nvidia Nemotron Nano 9B costs $0.04 per 1M input tokens and $0.16 per 1M output tokens at its cheapest provider via DeepInfra. Across 3 serving providers, input prices range from $0.04 to $0.20 per 1M tokens.
What is the context window of Nvidia Nemotron Nano 9B?
Nvidia Nemotron Nano 9B accepts up to 131K tokens of context and can return up to 131K output tokens.
Which providers serve Nvidia Nemotron Nano 9B?
Nvidia Nemotron Nano 9B is available from 3 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Nvidia Nemotron Nano 9B do?
Nvidia Nemotron Nano 9B supports tool use.
Other NVIDIA models
compare pricing across the NVIDIA lineupNvidia Nemotron Nano 12B$0.20/1M · 2 providersNvidia Nemotron Nano 3 30B$0.06/1M · 1 providerLlama 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