How to Use Brave Leo AI with Venice API: A Privacy-First Browser AI Assistant

How to Use Brave Leo AI with Venice API: A Privacy-First Browser AI Assistant

Connect Brave's Leo AI to Venice's private API for uncensored browsing assistance. Get AI help directly in your browser without sacrificing privacy or creative freedom.

Venice.ai

Brave Browser is an open-source, fast, private and secure web browser that offers an ad-free browsing experience. Brave recently introduced Leo AI, a smart AI assistant built directly into the browser that can answer questions, summarize pages, and create new content. This AI assistant doesn't store chat history, making it a perfect match for Venice API to ensure user data isn't saved by the LLM provider.

This guide demonstrates how to connect Brave's Leo AI to Venice's API infrastructure for enhanced browsing capabilities while maintaining complete privacy.

The benefits of integrating Brave Leo with Venice

By integrating Brave Leo with Venice API instead of mainstream AI providers, you gain several advantages:

  • Complete privacy: Your browsing data and prompts are never stored

  • Uncensored responses: Receive answers without artificial restrictions

  • Free ongoing inference through VVV staking

  • Browser-native AI assistance without relying on third-party extensions

Step-by-step Brave Leo integration with Venice API

1. Download and install Brave browser. Ensure that you are using Version 1.76.52 or greater to utilize the Leo AI functionality.

2. Click the "Leo AI" icon on the top right to access Leo, and then the gear icon on the bottom right to access the settings menu.

3. Click the "Leo" tab on the left side, and then scroll down to the "Bring your own model" section.

4. Grab your API key from Venice.ai (follow instructions in our docs).

5. Go to the model endpoints list and click "try it" next to GET /models to see all of the available models through the API. We recommend to use the default model as a starting place (llama-3.3-70b).

6. Go back to Brave browser settings and click "Add new model" to begin the configuration:

  • Label: Venice.AI

  • Model request name: llama-3.3-70b [or model id selected from prior step]

  • Server endpoint: https://api.venice.ai/api/v1/chat/completions

  • Context size: 4000 [this can be increased based on your choosing]

  • API Key: [your Venice API key identified from prior step]

  • System Prompt: [you can customize your system prompt to best fit your needs, or leave empty]

If you want to enable web search from Venice, you can enable it using model feature suffix syntax: llama-3.3-70b:enable_web_search=auto . Click here to learn more.

7. Click "Add model". Your configuration will now be displayed within the "Bring your own model" section. Change the "Default model for new conversation" to "Venice.AI".

8. Exit the settings page and go back to the Leo AI assistant. Click the 3 dots on the top bar to ensure you are using the "Venice.AI" model configuration.

9. You can now start using Leo AI. Exit the settings and begin using Leo by asking it to summarize a webpage.

Getting the most out of your Brave Leo and Venice API integration

Venice's API integration with Brave Leo provides powerful, private AI assistance directly in your browser without storing or tracking your conversations. This makes it ideal for:

  • Summarizing articles and research papers

  • Analyzing complex web content

  • Getting explanations of technical documentation

  • Creating content while browsing

For more information and support:

Venice's API access through VVV staking provides ongoing, private access to AI capabilities without per-request fees or data collection.

Back to all posts
Room