NVIDIA model product
Nemotron Nano 9B
Nemotron Nano 9B is an NVIDIA large language model trained from scratch for reasoning and non-reasoning tasks.
Updated Oct 23, 2026. Default version: Nemotron Nano 9B v2
LLMBoard Score30.4Nemotron Nano 9B v2
Coverage80%5 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Nemotron Nano 9B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Nemotron Nano 9B Benchmark Results
Benchmark scores for Nemotron Nano 9B v2.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBFCL_v3_MultiTurn | Score66.90% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score97.80% | Rank05 | Participants33 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score90.30% | Rank15 | Participants70 | Percentile79.71% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score71.10% | Rank22 | Participants76 | Percentile72.00% | EvidenceC | Evaluated |
| BenchmarkAA AIME 2025 | Score69.67% | Rank45 | Participants96 | Percentile53.68% | EvidenceB | EvaluatedN/A |
| BenchmarkAIME 2025 | Score72.10% | Rank91 | Participants122 | Percentile25.62% | EvidenceC | Evaluated |
| BenchmarkAA CritPt | Score0.00% | Rank142 | Participants200 | Percentile29.15% | EvidenceB | EvaluatedN/A |
| BenchmarkAA IFBench | Score27.62% | Rank157 | Participants168 | Percentile6.59% | EvidenceB | EvaluatedN/A |
| BenchmarkAA LCR v1.1 | Score24.00% | Rank158 | Participants193 | Percentile18.23% | EvidenceB | EvaluatedN/A |
| BenchmarkAA HLE Text No Tools | Score4.87% | Rank161 | Participants200 | Percentile19.60% | EvidenceB | EvaluatedN/A |
| BenchmarkAA GPQA Diamond | Score56.97% | Rank166 | Participants199 | Percentile16.67% | EvidenceB | EvaluatedN/A |
| BenchmarkGPQA | Score64.00% | Rank175 | Participants256 | Percentile31.76% | EvidenceC | Evaluated |
| BenchmarkAA Omniscience Accuracy | Score11.80% | Rank181 | Participants201 | Percentile10.00% | EvidenceB | EvaluatedN/A |
Nemotron Nano 9B Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Nemotron Nano 9B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.06 input, $0.23 output per 1M via Merge Gateway
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMerge Gateway | Provider model IDnvidia/nemotron-nano-9b-v2 | Regionglobal | Input / 1M$0.06 | Output / 1M$0.23 | Context128K | Updated |
| ProviderVercel AI Gateway | Provider model IDnvidia/nemotron-nano-9b-v2 | Regionglobal | Input / 1M$0.06 | Output / 1M$0.23 | Context131.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Nemotron Nano 9B Runtime Performance
Provider-specific output speed and catalog latency for Nemotron Nano 9B v2. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Nemotron Nano 9B Specifications
Technical details for the model's default version.
- Version
- Nemotron Nano 9B v2
- Released
- Aug 18, 2025
- Knowledge cutoff
- Sep 1, 2024
- Parameters
- 8.9B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- NVIDIA Open Model License Agreement
Nemotron Nano 9B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionNemotron Nano 9B v2 | Released | LLMBoard30.38 | Parameters8.9B | ContextN/A | Max outputN/A | Open weightsYes | LicenseNVIDIA Open Model License Agreement |
Models similar to Nemotron Nano 9B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
Llama 3.1 Nemotron Ultra 253B
NVIDIA
NV
Nemotron 3 Nano
NVIDIA
NV
Nemotron 3.5 Lightning
NVIDIA
NV
Nemotron Labs Dory 1.0
NVIDIA
NV
Llama 3.3 Nemotron Super 49B
NVIDIA
NV
Nemotron 3 Super
NVIDIA
What is Nemotron Nano 9B?
Key information about Nemotron Nano 9B and its available data.
Nemotron Nano 9B is an NVIDIA large language model trained from scratch as a unified model for reasoning and non-reasoning tasks. Its reasoning traces can be controlled through a system prompt, including configuring it to provide only a final answer.
Data as of 2026-10-22.
FAQ
Common questions about Nemotron Nano 9B.
When was Nemotron Nano 9B released?
Nemotron Nano 9B's default version was released on Aug 18, 2025.
How much does Nemotron Nano 9B cost?
No official standard PAYG price is currently available for Nemotron Nano 9B. The lowest tracked third-party offer starts at $0.06 input and $0.23 output via Merge Gateway.
Who created Nemotron Nano 9B?
Nemotron Nano 9B was created by NVIDIA.
What is the context window for Nemotron Nano 9B?
A context window is not available for the default version.
Is Nemotron Nano 9B open weight?
Yes. The default version is marked as open weight under NVIDIA Open Model License Agreement.