Nemotron 3 Nano 30B A3B

NVIDIA · nvidia/nemotron-3-nano-30b-a3b

← Back to leaderboard

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...

Nemotron 3 Nano 30B A3B ranks #76 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.12 blended per million tokens, it is cheaper than 90% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 262144
Max output: 235929

Pricing

Input / 1M: 0.05
Output / 1M: 0.20
Blend / 1M: 0.12

Quality

Quality index:

Provider

Provider: NVIDIA
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.12per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.12
10,000,000$1.25
100,000,000$12.50

Related models

Same lab, similar price, or similar quality — useful next comparisons.

Closest API price