NVIDIA: Nemotron 3 Nano 30B A3B
Analysis Summary
NVIDIA Nemotron 3 Nano 30B A3B is a mixture-of-experts model activating 3B of 30B parameters, priced at $0.05 input and $0.20 output per million tokens. Its benchmark profile is unusual: it records very high math (91) and livecodebench (0.741) scores, yet its intelligence index sits at 14.2 and coding index at 14.4, suggesting strong performance on narrow mathematical and code-generation tasks but limited general reasoning breadth. The agentic index of 27.3 is modest.
For businesses, this model suits cost-sensitive workloads where mathematical computation or structured code generation is the primary need. Tool use and function calling are supported, and the 262K context window is generous for the price tier. It is not suited to complex multi-step reasoning, long-document analysis, or tasks requiring broad world knowledge.
At $0.05 per million input tokens, it offers good value for targeted use cases. Teams should treat it as a specialist rather than a general-purpose model and benchmark it against their specific task before committing.
Assessed June 30, 2026
Editorial notes
Nemotron 3 Nano 30B A3B posts strong math and livecodebench scores but a low intelligence index, suggesting narrow benchmark strength rather than broad reasoning; tool use and 262K context add practical utility at low cost.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How NVIDIA: Nemotron 3 Nano 30B A3B compares
NVIDIA: Nemotron 3 Nano 30B A3B ranks #186 of 387 AI models we track for overall intelligence, #112 of 152 for coding, #156 of 294 for agentic tasks. Its 262K-token context window is larger than 81% of the models we list. At $0.05 per million input tokens it is cheaper than 73% of comparable models.
About NVIDIA: Nemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does NVIDIA: Nemotron 3 Nano 30B A3B stack up?
Compare side-by-side with other efficient models.
Model Information
| OpenRouter ID |
nvidia/nemotron-3-nano-30b-a3b
|
| Provider | nvidia |
| Release Date | December 14, 2025 |
| Context Length | 262,144 tokens |
| Max Completion | 228,000 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.05 | $0.000050 |
| Output | $0.20 | $0.000200 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about NVIDIA: Nemotron 3 Nano 30B A3B
How much does NVIDIA: Nemotron 3 Nano 30B A3B cost?
NVIDIA: Nemotron 3 Nano 30B A3B costs $0.05 per million input tokens and $0.20 per million output tokens.
What is the context window of NVIDIA: Nemotron 3 Nano 30B A3B?
NVIDIA: Nemotron 3 Nano 30B A3B has a context window of 262,144 tokens (262K).
Is NVIDIA: Nemotron 3 Nano 30B A3B good for coding?
On our coding benchmark index, NVIDIA: Nemotron 3 Nano 30B A3B ranks #112 of 152 models, placing it in the broader range of the field for code generation and debugging.
What can NVIDIA: Nemotron 3 Nano 30B A3B do?
NVIDIA: Nemotron 3 Nano 30B A3B supports tool use and function calling.
Who created NVIDIA: Nemotron 3 Nano 30B A3B?
NVIDIA: Nemotron 3 Nano 30B A3B is developed by NVIDIA and was released on December 14, 2025.
