All Models
Nemotron 3 Nano 30B A3B (free)
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 open with open-weights, datasets and recipes so developers can easily customize, optimize, and deploy the model on their infrastructure for maximum privacy and security.
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OpenRouter | nvidia/nemotron-3-nano-30b-a3b:free | $0.00/MTok | $0.00/MTok | 256K | 256K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output