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

# Available models

> Choose a model for your session and understand which choices your workspace allows

You choose the model Athena uses for a session from the model picker beside the message composer. Use it when you want to change the model for your next request or compare how different models handle the same task. Your choices depend on your deployment and workspace model restrictions.

<Frame caption="How to choose a model and a reasoning effort">
  <video controls muted playsInline preload="metadata" className="w-full aspect-video" poster="/images/how-to/athena-howto-choose-model-poster.jpg" src="https://mintcdn.com/athenaintelligence-e46bc9d3/qz43AKUFD_YQXkyW/images/how-to/athena-howto-choose-model.mp4?fit=max&auto=format&n=qz43AKUFD_YQXkyW&q=85&s=7a5905539882feae27623565937c6b0c" data-path="images/how-to/athena-howto-choose-model.mp4" />
</Frame>

<Accordion title="Steps in this video">
  1. Open the model picker
  2. Find a model family
  3. Open Configure variants
  4. Choose an effort
  5. Check the model
  6. Send your message
</Accordion>

## Choose a model

1. Open a session and find the model picker beside the message composer. It shows the selected model's name or icon.
2. Open the picker. The shortcut cards **Balanced**, **Fast** and **Best** set a model for you, and a **Selected** row shows your current choice. To pick a family yourself, browse the families under **Featured** and the provider groups.
3. Select a model family. To choose a particular variant, select the arrow beside the family to **Configure variants** and pick an option. Choosing a **Mode** or an **Effort** closes the picker; choosing a **Speed** keeps it open.
4. Check the selected model in the composer before you send your next request. On a narrow window the composer shows the model's icon instead of its name.

Use **Search models...** to jump to a model by name. Search results are a flat list without variant controls, so browse the families when you want to set a mode, speed or effort.

## Model families

You can find these current families in the catalog when your workspace allows them. This is a guide to the families, rather than a promise that every model appears in your picker.

| Provider | Current families and examples |
| - | - |
| OpenAI | GPT 6 Astra, GPT 6.1 Sol, GPT 6 Sol, GPT 6 Luna; GPT 5.6 Sol, GPT 5.6 Terra, GPT 5.6 Luna; GPT 5.5 and GPT 5.4 |
| Anthropic | Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6; Claude Sonnet 5.5, Claude Sonnet 5, Claude Sonnet 4.6; Claude Haiku 5.5 and Claude Haiku 4.5 |
| Google | Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3.1 Flash Lite, Gemini 3 Flash |

## Good to know

You do not need to be a workspace owner to choose an allowed model. A workspace can allow only approved models or block particular models. Your deployment can also restrict the catalog. These restrictions apply to individual variants, so a family can appear with fewer effort or speed choices.

The picker can mark a previously selected model **Unavailable**. Choose an available model before continuing. Each model has its own input and output limits; choosing a family does not give every variant the same capabilities.

## Related links

* [Your account](../your-account.mdx)
* [Your first chat](../getting-started/your-first-chat.mdx)
* [Working with Athena](../getting-started/working-with-athena.mdx)


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