> ## Documentation Index
> Fetch the complete documentation index at: https://docs-agents.fpt.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Model

> The brain the agent thinks and answers with

Every agent runs on a language model. The model decides how deeply the agent can reason, how much context it holds and how much each turn costs.

<img src="https://mintcdn.com/fpt-62e894b4/OEIa1zuMs6GjYr6X/images/en_model_list.jpg?fit=max&auto=format&n=OEIa1zuMs6GjYr6X&q=85&s=4dd119698d9869b6fdc8338ad75e4d86" alt="Agent model" width="1562" height="784" data-path="images/en_model_list.jpg" />

## What the Model screen shows

* **Connected** - the model the agent is running on, with figures such as context window and maximum output length.
* **Workspace models** - the list of models the workspace allows. Click **Use** on a card to switch the agent over.

Each card carries capability labels - **Reasoning** (for multi-step thinking) or **Vision** (can read images), for example - so you can tell at a glance which model suits the job.

## Choosing the right one

| What the agent does | Favour |
| - | - |
| FAQ answers, quick lookups, high volume | A small, fast model |
| Analysis, planning, multi-step work | A model strong at reasoning |
| Long documents, lots of context | A model with a large context window |
| Images, screenshots, scanned documents | A model with the vision label |

<Tip>
  After switching models, run **Test chat** through a few familiar scenarios. The same Instructions can read very differently to two different models.
</Tip>

## How to switch an agent's model

<Steps>
  <Step title="Open the Model section">
    On the agent page, go to the Agent builder tab. The Configuration column on the right shows the model the agent is running on.
  </Step>

  <Step title="Look at the alternatives">
    Click the Model box for a short list, or click View all models to open the workspace's full catalogue with figures to compare - context window, output length and capability labels.

    <img src="https://mintcdn.com/fpt-62e894b4/OEIa1zuMs6GjYr6X/images/en_model_dropdown.jpg?fit=max&auto=format&n=OEIa1zuMs6GjYr6X&q=85&s=798c6c42de512ce309a6fdccbbbf4592" alt="Model dropdown" width="1562" height="784" data-path="images/en_model_dropdown.jpg" />
  </Step>

  <Step title="Click Use">
    Click Use on the model you want. The agent switches over immediately - there is nothing else to save.

    <img src="https://mintcdn.com/fpt-62e894b4/OEIa1zuMs6GjYr6X/images/en_model_list.jpg?fit=max&auto=format&n=OEIa1zuMs6GjYr6X&q=85&s=4dd119698d9869b6fdc8338ad75e4d86" alt="Model list" width="1562" height="784" data-path="images/en_model_list.jpg" />
  </Step>
</Steps>

<Note>
  There is no add, remove or enable/disable for models at the agent level. The catalogue is a fixed workspace list (Resources > Models), and an agent always runs exactly one model at a time - so switching is the only action there is.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.