# Nemotron 3 Super

## Best for

Coordinating agents, planning work, and combining their results

## When not to use

Image, audio, or video. Not the high-volume routine worker — pair it with a lighter model for that. Context served here is 262,144 tokens, not a million.

## Overview

Nemotron 3 Super is a 120B hybrid Mamba-Transformer mixture-of-experts model, with 12B active parameters per forward pass. It is designed to coordinate multi-agent systems: routing work, planning, and bringing results together. It uses four experts per pass and has a 262,144-token context window with tool calling. For routine, high-volume tasks, NVIDIA recommends pairing it with a smaller model such as Nemotron 3 Nano. The weights, training data, and recipes are open source.

| | |
| --- | --- |
| API identifier | `nemotron3-super` |
| Developer | NVIDIA |
| Context window | 262,144 tokens |
| Supports | text, reasoning, tool-use |
| Status | Serving |

## Rates

USD per 1M tokens, on-demand tier.

| Input | Cached input | Output |
| --- | --- | --- |
| $0.12 | $0.06 | $0.52 |

## Call it

Put `nemotron3-super` in the `model` field. The same request works against the Anthropic Messages API — see [API Compatibility](https://inference.boundless.network/docs/api-compatibility).

```bash
curl https://api.inference.boundless.network/v1/chat/completions \
  -H "Authorization: Bearer $BOUNDLESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nemotron3-super",
    "messages": [{
      "content": "Say hello",
      "role": "user"
    }]
  }'
```

Every model we serve is listed at [Models](https://inference.boundless.network/models); the rate card in full is on [Pricing](https://inference.boundless.network/docs/pricing).