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

# Brave Leo

> Connect Brave Leo to the Venice API for private, browser-native AI chat, page summaries, and optional web search.

[Brave Leo](https://brave.com/leo/) is the AI assistant built into Brave Browser. Leo's Bring Your Own Model (BYOM) feature can connect directly to Venice's OpenAI-compatible chat completions endpoint, letting you use Venice models for chat and page-aware assistance without installing an extension.

<CardGroup cols={3}>
  <Card title="Browser Native" icon="browser">
    Chat, summarize pages, and explain selected text in Brave
  </Card>

  <Card title="Direct Connection" icon="plug">
    Send BYOM requests directly from Brave to Venice
  </Card>

  <Card title="Privacy Choice" icon="shield-halved">
    Choose a Venice model with the privacy tier you need
  </Card>
</CardGroup>

## Prerequisites

* Brave Browser 1.69 or later on Windows, macOS, or Linux
* A Venice API key from [venice.ai/settings/api](https://venice.ai/settings/api)
* A model ID from the [Venice text model catalog](/models/text)

<Note>
  Brave's BYOM feature is available on desktop. The model ID must match a Venice model ID exactly.
</Note>

## Setup

<Steps>
  <Step title="Open Leo settings">
    Open `brave://settings/leo-ai`, or open Leo from Brave's sidebar, select the settings icon, and navigate to **Leo**.
  </Step>

  <Step title="Add a custom model">
    Scroll to **Bring your own model** and select **Add new model**.
  </Step>

  <Step title="Configure the Venice endpoint">
    Enter the following values:

    | Field              | Value                                                  |
    | ------------------ | ------------------------------------------------------ |
    | Label              | `Venice AI`                                            |
    | Model request name | A model ID from the [text model catalog](/models/text) |
    | Server endpoint    | `https://api.venice.ai/api/v1/chat/completions`        |
    | API key            | Your Venice API key                                    |

    If Brave displays **Context size**, set it to the context window supported by your selected model. You can also add an optional system prompt.

    Enter the API key itself without a `Bearer` prefix. Brave adds the authorization header to each request.
  </Step>

  <Step title="Save and select Venice">
    Select **Add model**, then set **Venice AI** as the default model for new conversations or choose it from Leo's model selector.
  </Step>

  <Step title="Test the connection">
    Open Leo on a webpage and send a prompt such as:

    ```txt theme={"system"}
    Summarize this page in five bullet points.
    ```

    Leo sends the conversation and relevant page content directly to the Venice endpoint.
  </Step>
</Steps>

## Enable Venice web search

Brave does not expose Venice-specific request-body parameters in BYOM. To enable Venice web search, append a [model feature suffix](/api-reference/endpoint/chat/model_feature_suffix) to the model ID in **Model request name**:

```txt theme={"system"}
<model-id>:enable_web_search=auto
```

To always enable search and include citations, use:

```txt theme={"system"}
<model-id>:enable_web_search=on&enable_web_citations=true
```

<Info>
  Web search has additional usage-based pricing. See [API pricing](/overview/pricing) for current rates.
</Info>

## Privacy

When you use a remote BYOM endpoint, Brave connects directly to that provider. Requests bypass Brave's servers, so Brave's proxy and server-side retention protections do not apply to those requests.

Venice does not store or log prompt and response content at its proxy. The selected model determines the runtime privacy tier:

* **Private** models use zero-data-retention infrastructure.
* **Anonymized** models hide identifying information from the upstream provider, but the provider can process the prompt.
* **TEE** and **E2EE** models add hardware-backed isolation or client-side encryption where supported.

Check the model's privacy label in the [text model catalog](/models/text) and read [Venice privacy](/overview/privacy) before sending sensitive information.

Brave may keep Leo chat history in local browser storage. You can clear Leo data, use a temporary chat, or disable local chat history in Brave's Leo settings.

## Configuration notes

* Brave requires the full endpoint path: `https://api.venice.ai/api/v1/chat/completions`.
* Model IDs and availability change over time. Copy the current ID from the [text model catalog](/models/text).
* Context size should not exceed the selected model's supported context window.
* Page summaries can send page content to Venice as part of the prompt.
* Remote Venice requests require an internet connection and consume Venice API credits or your available DIEM allowance.

## Troubleshooting

<AccordionGroup>
  <Accordion title="401 or authentication error">
    Confirm that the key comes from [venice.ai/settings/api](https://venice.ai/settings/api). Paste the raw key without `Bearer` and remove any leading or trailing spaces.
  </Accordion>

  <Accordion title="Model not found">
    Copy the model ID exactly from the [text model catalog](/models/text). If you added a feature suffix, first test the model without the suffix.
  </Accordion>

  <Accordion title="Network error or no streamed response">
    Confirm that the server endpoint includes `/api/v1/chat/completions`. Brave Leo expects an OpenAI-compatible streaming response.
  </Accordion>

  <Accordion title="Page summaries lack page context">
    Check Leo's permission to use page content and make sure the current page is accessible to the browser. Internal Brave pages and some protected pages cannot be summarized.
  </Accordion>
</AccordionGroup>

## Resources

<CardGroup cols={2}>
  <Card title="Brave BYOM Guide" icon="book" href="https://support.brave.com/hc/en-us/articles/34070140231821-How-do-I-use-the-Bring-Your-Own-Model-BYOM-with-Brave-Leo">
    Official Brave setup and privacy details
  </Card>

  <Card title="Venice Text Models" icon="list" href="/models/text">
    Browse current model IDs and privacy tiers
  </Card>

  <Card title="Model Feature Suffixes" icon="sliders" href="/api-reference/endpoint/chat/model_feature_suffix">
    Enable web search and other Venice features
  </Card>

  <Card title="Generate an API Key" icon="key" href="/guides/getting-started/generating-api-key">
    Create and securely store a Venice API key
  </Card>
</CardGroup>