Nemotron 3 Nano 30B A3B
NVIDIA · 1 configuration
Intelligence—
Input / 1M$0.05
Output / 1M$0.20
Context262.1K
Tariff: OpenRouter · Source: openrouter · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
◌
No pair of measurements available
Change the filters or pick another benchmark. Missing values are not estimated.
Selected: thinking default · Click a point to switch configuration
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...
This model is in the catalog but has no imported benchmarks. Capabilities are not estimated.
Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputYes
SpeedNot available
First tokenNot available
Maximum output235.9K
Catalog listing date2025-12-14