Author
Nvidia Context262.1k
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.
Performance
Latency (p50)—
Throughput (p50)—
Pricing
Input$0.03/M tokens
Output$0.12/M tokens
Cached input$0.006/M tokens
Features
Inputtext
Outputtext
APIResponses, Chat Completions, Messages