← ← Back to Rankings

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...

β€”
Rank
256K
Context Window
$0.05
Min Input /1M
$0.20
Min Output /1M

Model Info

Model ID nvidia-nemotron-3-nano-30b-a3b
Modality text->text
Context Window 256K tokens
Platforms OR

Usage & Rankings

Rank Unranked
Weekly Usage β€”

Cross-Platform Pricing

Platform Input /1M Output /1M Context Model ID
OR OpenRouter $0.050 $0.200 256K nvidia/nemotron-3-nano-30b-a3b
Input
$0.050
/ 1M tokens
Output
$0.200
/ 1M tokens
Round Trip
$0.25
/ 1M tokens
Value Rating
🟒
🟒 Economy β€” great for high volume

About NVIDIA: Nemotron 3 Nano 30B A3B

NVIDIA: Nemotron 3 Nano 30B A3B is a large language model with a 256K token context window.

The best available input price is $0.050/1M tokens and output price is $0.200/1M tokens, with a round-trip cost of $0.25/1M tokens.