> For the complete documentation index, see [llms.txt](https://docs.lleverage.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.lleverage.ai/administer-and-govern/security-and-assurance/ai-providers.md).

# AI providers

The companies whose AI models and services process what you send to Lleverage, and what each one receives.

Lleverage's agent, its Workflows and the Lleverage apps for iPhone, iPad and Android use AI models and services that other companies run. When you use them, what you type, say and record, and the files you attach, go to the provider doing that part of the work, which processes it on Lleverage's behalf. This page lists those providers.

The [Lleverage privacy policy](https://legal.lleverage.ai/privacy-policy) explains how Lleverage handles your information.

### AI models

The agent and Workflows run on models from these providers. Which one handles a message depends on the model chosen for the agent or for the Workflow step.

| Provider            | What it receives                                                                                 |
| ------------------- | ------------------------------------------------------------------------------------------------ |
| OpenAI              | Messages, context and attachments sent to OpenAI's models.                                       |
| Anthropic           | Messages, context and attachments sent to Anthropic's Claude models.                             |
| Amazon Web Services | Messages, context and attachments sent to the models Lleverage uses on AWS, Claude among them.   |
| Google              | Messages, context and attachments sent to Google's Gemini models.                                |
| Nebius              | Messages, context and attachments sent to the open models Lleverage uses on Nebius, such as GLM. |

### Speech and voice

| Provider   | What it receives                                                                                                                       |
| ---------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| ElevenLabs | Your voice while you dictate, and meeting recordings, which it turns into text and splits by speaker.                                  |
| OpenAI     | Your voice during a call with the agent in the Lleverage app or on the web. The call's audio goes straight from your device to OpenAI. |

### Files and the web

| Provider     | What it receives                                                          |
| ------------ | ------------------------------------------------------------------------- |
| Unstructured | Files Lleverage reads for their text and layout.                          |
| OpenAI       | Text from files and knowledge, which it turns into embeddings for search. |
| Firecrawl    | The addresses of web pages the agent or a Workflow is asked to read.      |
| SerpAPI      | Search terms when the agent or a Workflow searches the web.               |

### Your organisation's own provider accounts

An organisation can connect its own account with a model provider in [AI models](/administer-and-govern/control/ai-models.md). Requests made through that connection go to that provider under the organisation's own agreement with it.

### Changes to this list

Lleverage updates this page when it adds or changes a provider.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.lleverage.ai/administer-and-govern/security-and-assurance/ai-providers.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.