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

# Choosing the Right Model

> Two decisions: what the model does, and how private the call is. This page points you at both.

## By Task

| You want to                 | Use                                   | More                                                 |
| :-------------------------- | :------------------------------------ | :--------------------------------------------------- |
| Generate or discuss text    | A chat model                          | [Model Families](/models/model-families)             |
| Work a problem step by step | A reasoning-capable model             | [Reasoning](/features/reasoning)                     |
| Ask about an image          | A vision-capable model, with `--file` | [Image Input](/features/multimodal/image-input)      |
| Ask about a document        | Any model, with `--file`              | [PDF Input](/features/multimodal/pdf-input)          |
| Pull in current information | Any model, with web search on         | [Web Search](/features/server-side-tools/web-search) |
| Compare several answers     | Fusion                                | [Fusion](/commands/fusion)                           |

Smaller models are faster and cheaper, and usually enough. Reasoning costs extra tokens and time, so save it for problems that genuinely need the steps.

## By Privacy Level

The level rides with the model you pick, so this is the same act as choosing the model. Take the lightest level that fits the call.

| Level                                        | Take it when              | What it gives you                                  |
| :------------------------------------------- | :------------------------ | :------------------------------------------------- |
| [Anonymous](/privacy/levels/anonymous)       | Routine work              | Frontier models, with your identity detached       |
| [Private](/privacy/levels/private)           | You want no data retained | Zero data retention enforced upstream              |
| [Confidential](/privacy/levels/confidential) | You want attested privacy | Sealed execution with an attestation you can check |

A call that cannot be served at the level you asked for fails rather than quietly dropping to a weaker one. Full ladder: [Privacy Levels](/privacy/levels).

## Then Set It

`models` browses the catalog, `model` sets a default, `--model` overrides one call. Syntax is on [Choosing a Model](/commands/choosing-a-model). None of it changes the model your harness runs.

## Related Resources

<CardGroup cols={3}>
  <Card title="Model List" icon="object-ungroup" href="/models/all-models">
    The current catalog, grouped by privacy level.
  </Card>

  <Card title="Choosing a Model" icon="terminal" href="/commands/choosing-a-model">
    The command syntax for browsing and setting your model.
  </Card>

  <Card title="Pricing" icon="money-bills" href="/models/pricing">
    How cost is structured and where to read per-model rates.
  </Card>
</CardGroup>