/ Models

Language models

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...

Maker
Nvidia
Context window
262K
Max output
228K
Input / 1M
$0.05
Output / 1M
$0.2
1M in + 1M out
$0.25

Everything else

Max output228K
Input / 1M$0.05
Output / 1M$0.2
Cache read / 1M$0.025
Cache write / 1M
1M in + 1M out$0.25
Takestext
Returnstext
Toolsyes
Reasoningoptional
Open weightsyes
Released2025-12-14
Knowledge cutoff
Retires
Catalog idnvidia/nemotron-3-nano-30b-a3b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models