Nemotron 3 Nano 30B A3B

NVIDIA Nemotron 3 Nano is an open reasoning model optimized for fast, cost-efficient inference. Built with a hybrid MoE and Mamba architecture and trained on NVIDIA-curated synthetic reasoning data, it delivers strong multi-step reasoning with stable latency and predictable performance for agentic and production workloads.

Model overview

Model ID: nvidia/nemotron-3-nano-30b-a3b
Provider: nvidia
Type: language
Context window: 262,144 tokens
Max output tokens: 262,144

Tags: reasoning

Model pricing

Metric	Value
`Input tokens (/1M)`	`$0.05`
`Output tokens (/1M)`	`$0.24`
`Image generation`	`n/a`
`Cached input read (/1M)`	`n/a`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix