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

# Models

> Browse the Gloo AI model catalog and compare pricing, speed, and capabilities in Studio.

The **Models** page in Studio is the catalog of models available through Gloo AI. Click **Models** in the Studio sidebar to open it. Use it to find a model, compare its price and capabilities, and jump straight into the Playground to try it.

For the same information in the docs, including model IDs for API requests, see [Supported Models](/api-guides/supported-models).

The prices on this page are the model's published rates. Direct endpoints add no platform fee: you pay the model's published rate (see the Models page and `GET /platform/v2/models`). Guarded endpoints add a 6.5% platform fee on top. See [Billing & Plans](/studio/billing).

## Explore the catalog

Scroll to **Explore curated models** to see the list. The page starts with a short overview of how Gloo AI approaches values alignment, safety, and intelligent routing.

* **Search:** Type in **Search models...** to match a model's name, description, provider, or tags.
* **Provider filters:** Click **Anthropic**, **OpenAI**, **Google**, or **Open Source** to show only those models. You can select more than one.
* **Tag filters:** Click one or more tag chips to narrow the list to models that have all of the selected tags.
* **Clear all:** Resets the search and filters.

The list shows a model count and, at first, only a few models. Click **View All** to expand it (and **Show Less** to collapse it). Searching or filtering shows every match.

On a desktop-width screen each row shows the model name, **Input Token Price**, **Output Token Price**, **Max Input / Context**, **Speed**, and **Reasoning**. Click a column heading to sort by it, and click again to reverse the order. On smaller screens some of these appear when you expand a row. Prices are per 1M tokens.

Click a row to expand it and read the model's description, then click **View details** to open its page.

## Model details

A model's page shows:

* **Header:** The model name, its provider family, a short description, and a quick summary of **Reasoning**, **Speed**, **Price** (input and output), and the **Input** and **Output** modalities.
* **Pricing:** Input and output prices per 1M tokens. If the model supports prompt caching, cache read and cache write prices are shown too, along with the savings compared to the regular input price. A **Quick comparison** compares its input price with other models from the same provider.
* **Modalities:** Whether text, image, audio, and video are supported as input, output, or both.
* **Features:** Whether the model supports **Streaming**, **Function calling**, **Vision**, and **Reasoning**.

Click **Try in Playground** to open the [Chat Playground](/studio/playground-chat) with that model selected. Click **All Models** to return to the catalog.

## Next Steps

> **[Chat Playground](/studio/playground-chat)**
>
> Try a model with your own prompts.

> **[Supported Models](/api-guides/supported-models)**
>
> Model IDs for API requests.

> **[Model Lifecycle](/api-guides/model-lifecycle)**
>
> How models are introduced and retired.


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