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

# Models

> Match the right model and effort level to each task.

Mesa gives you a choice of AI models and effort levels for every conversation. Matching them to the task at hand gets you better results while making the most of your usage allocation.

## Select a model and effort level

Use the dropdown above the chat box on the home page to pick a model and effort level before you send your message.

<Frame>
  <img src="https://mintcdn.com/calderapbc/B_vZrKRxRHJJVCf4/images/Screenshot-2026-06-27-at-8.20.15-AM.png?fit=max&auto=format&n=B_vZrKRxRHJJVCf4&q=85&s=45ccba24dc5e954be3413baf315a0234" alt="" width="2494" height="1770" data-path="images/Screenshot-2026-06-27-at-8.20.15-AM.png" />
</Frame>

## Compare models

| Model                | Best for                                              | Usage  |
| -------------------- | ----------------------------------------------------- | ------ |
| **Claude Opus 4.8**  | Corpus research, document drafting, and complex tasks | Higher |
| **GPT 5.5**          | Corpus research, document drafting, and complex tasks | Higher |
| **Claude Sonnet 5**  | Short questions and simpler tasks                     | Lower  |
| **GPT 5.4 Mini**     | Short questions and simpler tasks                     | Lower  |
| **Gemini 3.5 Flash** | Quick questions and simpler tasks                     | Lower  |

## Compare effort levels

| Effort level      | Best for                                                            |
| ----------------- | ------------------------------------------------------------------- |
| **Deep Research** | Large context, many files or documents, and deliverable-style tasks |
| **Balanced**      | Intermediate document drafting and specific investigations          |
| **Fast**          | Quick questions and simple requests                                 |

## Which combination should you pick?

* **Quick lookup or simple question**: a lighter model on **Fast**. You'll get an answer in seconds without dipping into your allocation.
* **Drafting a document or investigating a specific issue**: a higher-capability model on **Balanced**.
* **Comprehensive research, many documents, or a polished deliverable**: a higher-capability model on **Deep Research**. Pair it with [Notifications](/notifications) so you don't have to wait at the screen.

<Tip>
  Higher-capability models and effort levels consume more of your allocation. See [Usage](/usage) to check how much you have left.
</Tip>

## Related articles

<Card title="Usage" href="/usage" horizontal>
  Track daily and weekly usage so you can plan your work.
</Card>

<Card title="Writing effective prompts" href="/prompting" horizontal>
  A well-written prompt matters as much as the model you pick.
</Card>

<Card title="Exhaustive search" href="/exhaustive-search" horizontal>
  Use a comprehensive search mode when completeness matters more than speed.
</Card>