# Nemotron in Taskade

> Which Nemotron models you can use in Taskade, what each one is good at, and how to pick between them.

- Source: https://www.taskade.com/docs/models/nemotron
- Section: Models
- Updated: 2026-10-17
- Index of all pages: https://www.taskade.com/docs/llms.txt

Nemotron in Taskade is an efficient mixture-of-experts model aimed at agent work.

## Nemotron models available today

| Model | Good at | Speed | Intelligence | Cost | Availability |
| --- | --- | --- | --- | --- | --- |
| Nemotron 3 Super | Efficient mixture-of-experts for agents | Fast | High | Medium | Every paid plan |

## How to pick within Nemotron

- **Nemotron 3 Super** when you want agent throughput at a moderate cost band.

## How Nemotron performs

Nemotron 3 Super took one TSK-1 app test in August 2026. It wrote a plan for the app but built none, so its score stays open until a new test. See the [Nemotron page](https://www.taskade.com/tsk/nemotron) for the details.

## Set it on an agent or a chat

Open the model menu in the builder chat or on an agent. In the builder chat, open **More models** and choose from the provider groups. In the agent editor, choose from **All Models**. The choice applies only to that surface. An AI step in an automation offers TSK-Auto and the rungs only.

If you do not want to pin a model, a [rung](https://www.taskade.com/docs/models#tsk-rungs) sets a speed-to-depth trade-off and follows the catalog forward as models change.

## Next steps

- Compare every family in the [full catalog](https://www.taskade.com/docs/models/custom-engine).
- Read [how Taskade picks a model](https://www.taskade.com/docs/models) for Auto and the rungs.
- Open each Nemotron model from the [NVIDIA models page](https://www.taskade.com/models/nvidia) to see its plans and test results.