Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B is a large language model made by NVIDIA, added to the catalog on 14 Dec 2025. It has a context window of 262,144 tokens and costs $0.06 per 1M input tokens and $0.24 per 1M output tokens. It accepts text and produces text. Typical uses: build customized AI applications, enhance privacy and security in deployments and experiment with agentic AI systems.
Price checked · source: OpenRouter
What Nemotron 3 Nano 30B A3B is
The NVIDIA Nemotron 3 Nano 30B A3B, released on December 14, 2025, is a compact language model designed for high compute efficiency and accuracy. With a context length of 262,144 tokens, this model supports text-to-text modalities, making it ideal for developers looking to create specialized agentic AI systems. The model is fully open, allowing users to customize, optimize, and deploy it on their own infrastructure, ensuring maximum privacy and security. Please note that the free endpoint logs all interactions to enhance the model's capabilities. This model is suitable for a variety of applications but is not intended for production use.
Key features
- High compute efficiency and accuracy
- Open weights and datasets for customization
- Supports a context length of 262,144 tokens
- Text-to-text input and output modalities
- Optimized for specialized agentic AI systems
Typical uses
- Build customized AI applications
- Enhance privacy and security in deployments
- Experiment with agentic AI systems
- Utilize extensive context for complex tasks
Nemotron 3 Nano 30B A3B pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.06 |
| Output, per 1M tokens | $0.24 |
| Cached input read, per 1M tokens | $0.012 |
No price change since it was added on 14 Dec 2025.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0001 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0017 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0023 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.0094 |
Nemotron 3 Nano 30B A3B specifications
| Model id | nvidia/nemotron-3-nano-30b-a3b |
|---|---|
| Version | nemotron-3-nano-30b-a3b |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 235,929 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 14 Dec 2025 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
Write a short essay
RUN20 Nov 2026Write 150 words on how AI might positively upend work, leisure and creativity
AI is poised to upend work, leisure, and creativity by automating routine tasks, personalizing experiences, and amplifying human imagination. In the workplace, intelligent agents handle data‑heavy analysis, scheduling, and customer support, freeing professionals to focus on strategy, empathy, and complex problem‑solving. This shift creates new roles centered on AI oversight, ethics, and interdisciplinary collaboration, while upskilling becomes a lifelong habit rather than a one‑time event. For leisure, adaptive platforms curate content that matches individual tastes, predict recreation needs, and even co‑design games that evolve with players, turning downtime into immersive, purpose‑driven experiences. Creativity itself is redefined: generative models suggest novel designs, compose music, or draft stories, serving as collaborative partners that expand the frontier of what humans can envision. By handling the mundane, AI restores time, sparks curiosity, and empowers people to explore passions previously constrained by skill or resources, ultimately reshaping how we labor, relax, and create in future.
Compare Nemotron 3 Nano 30B A3B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.