[NVIDIA](/ai-gateway/models/labs/nvidia)

# NVIDIA Nemotron 3 Super 120B A12B

NVIDIA Nemotron 3 Super 120B A12B is NVIDIA's 120B total, 12B active-parameter hybrid Mamba-Transformer MoE built for complex multi-agent applications, featuring latent MoE and multi-token prediction. Your use is subject to NVIDIA's [Terms](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA_Technology_Access_TOU.pdf) & [Privacy](https://www.nvidia.com/en-us/about-nvidia/privacy-policy/) Policies.

ReasoningTool Use

[Use with AI Gateway](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai%3Futm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get+Started+with+Vercel+AI+Gateway) [View docs](https://vercel.com/docs/ai-gateway)

AI SDKChat CompletionsMessagesResponses

```
1import { streamText } from 'ai'
2

3const result = streamText({
4  model: 'nvidia/nemotron-3-super-120b-a12b',
5  prompt: 'Why is the sky blue?'
6})
```

[Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk)

[Overview](/ai-gateway/models/nemotron-3-super-120b-a12b) [API](/ai-gateway/models/nemotron-3-super-120b-a12b/api) [About](/ai-gateway/models/nemotron-3-super-120b-a12b/about) [Providers](/ai-gateway/models/nemotron-3-super-120b-a12b/providers) [Throughput](/ai-gateway/models/nemotron-3-super-120b-a12b/throughput) [Latency](/ai-gateway/models/nemotron-3-super-120b-a12b/latency) [Uptime](/ai-gateway/models/nemotron-3-super-120b-a12b/uptime) [Status](/ai-gateway/models/nemotron-3-super-120b-a12b/status) [Similar](/ai-gateway/models/nemotron-3-super-120b-a12b/similar) [FAQ](/ai-gateway/models/nemotron-3-super-120b-a12b/faq)

## [Copy link to heading](#throughput)Throughput24 hours

1W

1D

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the [docs](https://vercel.com/docs/ai-gateway/models-and-providers/metrics) for more info.