Models/Nemotron-3-Nano-30B-A3B

Nemotron-3-Nano-30B-A3BActive · Cloud

DeepInfra · Released Dec 2025 · NVIDIA Open Model License

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...

Context

262K

Max output

Input

$0.05

Output

$0.20

Cached in

$0.02

Latency

Capabilities

Core

Streaming

Function calling

JSON mode

Structured outputs

Multimodal

Vision

Image input

Audio

Image generation

Video

Advanced

Reasoning

Tool calling

MCP

Prompt caching

Batch API

Embeddings

Details

ProviderDeepInfra

ReleasedDec 2025

LicenseNVIDIA Open Model License

InputText

OutputText

Throughput-

Availability100%

Nemotron-3-Nano-30B-A3BActive · Cloud

Capabilities

Details

Related models