NVIDIA: Nemotron 3 Nano 30B A3B

deprecated30B / 3B

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.

Context
262K
Max output
236K
Input price
$0.06/1M tokens
Output price
$0.24/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDnvidia/nemotron-3-nano-30b-a3b
Provider OpenRouter
Creator NVIDIA
Family—
License—
Statusdeprecated
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters30B / 3B
Architecture—
Context window262K tokens
Max input—
Max output236K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.06
Output
$0.24
Cache write
—
Cache read
$0.01
Batch in
—
Batch out
—

API

GET/v1/models/openrouter/nvidia/nemotron-3-nano-30b-a3b