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

# Using Elephas AI (Included Cloud AI)

> Elephas AI is the cloud AI included with your plan. What it sends, how requests go through the Elephas gateway, what is stored, and how your allowance works.

Elephas AI is the cloud AI that comes with your Elephas plan. There is no key to paste and no separate bill: Elephas sends your question and the matching passages from your documents through the Elephas gateway to a model provider, and the answer comes back with citations to your files. Usage counts against your plan's included AI allowance.

<Info>
  Included with the free trial and with every Elephas plan. The size of the allowance depends on your plan. See [Plans and pricing](/docs/plans-and-billing/plans-and-pricing).
</Info>

## Before you start

* Sign in to your Elephas account. See [Create your account and sign in](/docs/getting-started/create-account-and-sign-in).
* Have an active trial or plan.

## Steps

<Steps>
  <Step title="Open Settings › AI">
    Press ⌘, on Mac or Ctrl+, on Windows, then click **AI**.
  </Step>

  <Step title="Choose Elephas AI">
    Under **How Elephas answers**, click **Elephas AI (included with your plan)**.
  </Step>

  <Step title="Activate it on this computer, if asked">
    The first time on a computer, the card may say **Activate Elephas AI on this device with your Elephas account. Sync stays off unless you turn it on.** Check the device name and click **Activate Elephas AI**. This registers the computer with your account. It does not turn on Personal Sync.
  </Step>

  <Step title="Ask a question">
    The chat bar reads **Answered by: Elephas AI**.
  </Step>
</Steps>

The steps are the same on Mac and Windows.

## How it works

### What is sent, and where it goes

When you ask, Elephas searches your documents on your computer and sends your question, up to the last 4 chat messages and the passages it needs to the Elephas gateway. The gateway forwards them to a third-party model provider, which writes the answer. In the app's words: "Your question and the selected sources leave this computer for the Elephas gateway, which forwards them to" the provider named on the card. "Cloud inference is not end-to-end encrypted."

Your files and your library are never uploaded. Indexing happens on your computer. Always. For the full list by option, see [What data is sent to AI](/docs/privacy-and-security/what-data-is-sent-to-ai).

### Personal information is hidden first

With **Protect personal information when using cloud AI** on, which is the default, Elephas replaces many common personal details with placeholders on your computer before anything is sent, and puts them back in the answer. See [Personal information protection](/docs/privacy-and-security/personal-information-protection).

### What the gateway keeps

* The gateway does not store your prompts or answers. It logs only IDs, counts and decisions, such as how much of your allowance a request used.
* The model provider's own terms apply to what it receives. In the app's words: "Retention and training use by the upstream and its vendors follow their own policies." The provider is named on the Elephas AI card.
* No personal API key is used. You don't need an account with any AI provider.

### Which model answers

Elephas chooses the model. There is no model picker for Elephas AI. Elephas reads further into your documents when a question needs it, and checks the answer against its sources before showing it. The card says **Agent tools are on. Ask can search and read your sources to answer.** when this is working. If you want a specific model, use [your own API key](/docs/ai-options/use-your-own-api-key).

### Your allowance

The Elephas AI card shows how much of your included AI usage you have used:

* On a paid plan: **Included AI usage**, as a percentage, with the date it resets. The allowance resets each month.
* On the free trial: **Trial AI usage** for the whole trial, plus a daily share that resets each day.

Click **Refresh Usage** to update it. When you are offline, the card shows the last figures it had and when.

What uses the allowance, and what doesn't:

* **Uses it:** questions answered by Elephas AI. Questions that read whole documents, such as summaries and "find every mention", use more. Ask warns you: **This question reads whole sources, so it may use noticeably more of your AI allowance than usual.**
* **Doesn't use it:** adding and indexing documents, searching, reading your chats, and answers from your own API key or Local AI.

At 80%, Elephas tells you that you've used most of the allowance. When it runs out, Ask says **Your Elephas AI allowance is used up until** the reset date, and offers **Use your own key**. See [AI usage and credits](/docs/plans-and-billing/ai-usage-and-credits).

### In a Team workspace

Team questions always use Elephas AI under the Team Owner's AI policy, from an allowance pooled across the Team. An Owner or Admin can set a limit per member. If you reach yours, Ask says **You've reached the limit your Team set for you** until the reset date. See [Team AI policy](/docs/teams/team-ai-policy).

## Troubleshooting

<AccordionGroup>
  <Accordion title="Elephas AI isn't active on this plan">
    Your plan or trial has ended. Renew it in **Settings › Plan & Billing**, or switch to your own API key. See [When your plan ends](/docs/plans-and-billing/when-your-plan-ends).
  </Accordion>

  <Accordion title="This question and its context are too large for Elephas AI">
    Narrow the scope to fewer Brains or specific documents, then ask again. See [Ask about specific documents only](/docs/ask/ask-specific-documents).
  </Accordion>

  <Accordion title="Agent tools aren't available on Elephas AI right now">
    This is on the Elephas side and there is nothing to change in your settings. Try again later, or use your own API key in the meantime.
  </Accordion>
</AccordionGroup>

See also [AI allowance used up](/docs/troubleshooting/ai-allowance-used-up).

## FAQ

<AccordionGroup>
  <Accordion title="Do I need an OpenAI or Anthropic account?">
    No. Elephas AI uses Elephas's own access. You only need an Elephas trial or plan.
  </Accordion>

  <Accordion title="Does Elephas store my questions?">
    The gateway does not store your prompts or answers. Your chats are stored on your computer, and on your other devices only if you turn on [Personal Sync](/docs/sync-and-devices/personal-sync-overview).
  </Accordion>

  <Accordion title="Is Elephas AI end-to-end encrypted?">
    No. Requests travel over encrypted connections, but the gateway and the model provider must read your question and passages to answer. For documents that should not leave your computer, use [Local AI](/docs/ai-options/run-local-ai).
  </Accordion>
</AccordionGroup>

## Related articles

<CardGroup cols={2}>
  <Card title="Choose how Elephas answers" href="/docs/ai-options/choose-how-elephas-answers" />

  <Card title="What data is sent to AI" href="/docs/privacy-and-security/what-data-is-sent-to-ai" />

  <Card title="AI usage and credits" href="/docs/plans-and-billing/ai-usage-and-credits" />

  <Card title="Personal information protection" href="/docs/privacy-and-security/personal-information-protection" />
</CardGroup>


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