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

# Model Options 

Choose between a variety of AI model options to handle your requests

Tracely supports models from **OpenAI (GPT)**, **Anthropic (Claude)**, and **Google (Gemini)**. Which models appear in the dropdown is controlled in your **Settings** - you can use the default set or choose exactly which models to show in list of options.

<Frame>
  <img src=" alt="App Model Options Dropdown" title="App Model Options Dropdown" className="mx-auto" style={{ width:"78%" }} width="452" height="210" data-path="images/app/App_ModelOptions_Dropdown.png" />
</Frame>

***

## **Choosing a model**

* **Default pick:** **Auto** lets Tracely choose which model to use depending on your task. We recommend using Auto, GPT 5.5, or Claude Sonnet 4.6 for most tasks.
* **Fast / cheap:** Pair **Fast** input mode with a “mini” or “flash” model (e.g. **gpt-5.4-mini**, **claude-4.5-haiku**) for quick answers.
* **Hard problems:** Use **Thinking** input mode with a top-tier model (**gpt-5.5**, **claude-4.8-opus**) when you need deep reasoning or complex code.

Different models have different context limits (how much of your project and chat history they can use at once). If you have a very large project or long conversation, a model with a larger context (e.g. latest GPT/Claude models) may handle it better.