Power your search and AI apps with the fastest growing independent search engine since Bing. Access an index of billions of pages with a single call.
Get started for FREE for 1 query/second, 2,000 queries/month. Or check out the plan options below.
Feed results to AI models for inference
Deliver search results
Cache/store data to train AI models
Deliver real-time search suggestions or automated spelling corrections
Brave is one of only a few global, independent search providers, and it’s the fastest growing search engine since Bing.
Get access to high-quality data that’s actually usable. Build everything from search engines to AI apps. As the default engine in the Brave browser, Brave Search is consistently refreshed with new data via its Web Discovery Project contribution framework.
The Brave Search API brings an easy, consistent data structure, and full access to the entire index.
Brave Search API access is far cheaper than the Bing API. It’s free for up to 2,000 monthly calls, and offers multiple, affordable subscription tiers.
Some of the best search and AI apps are being powered by the fastest growing independent search engine since Bing.
Or contact the Brave BizDev team if your company needs a bespoke, large-data solution: [email protected]
The Brave Search API provides accurate search results for our academic citation services. It delivers high-quality data at a reasonable price, and with intuitive data structuring. Its speed and precision have been crucial.
The Brave Search API is powered by Brave Search, a fully independent search engine serving tens of millions of queries per day. Try Brave Search at search.brave.com.
The Brave Search API can replace several competing options that may have smaller indexes (Tavily or Exa), higher latencies (SerpAPI or Serper), higher pricing (Bing), or more limited access (Google). It can also serve as a complement to localized API options like Baidu, Naver, Yahoo, and Yandex. The Brave Search API is powered by Brave Search, a completely independent index of the Web, which is tuned to reduce SEO spam and increase quality and recency of results.
Yes. Brave Search fetches tens of millions of webpages every day, offering extensive coverage of recent events around the world.
Yes. For more info, please check out our help page about API privacy and security.
Whatever your needs, the Brave Search API offers plans to meet them. You can sign up for free and try the API, then choose the right plan once you assess the API’s capabilities. If your company needs a bespoke, large-data solution, contact <[email protected].>.
The Brave Search API offers a ranked list of webpages that are publicly available; this list also includes information to support why the webpage is relevant to the query (for instance via query-dependent snippets based on the content of the webpage).
The Brave Search API does not grant any rights to third-party content such as webpages. Customers who access URLs displayed in the Brave Search API must ensure their access to those webpages complies with the copyright terms of the page publishers.
Yes, every search engine that has its own index necessarily has its own Web crawler. The Brave Search crawler does not advertise a differentiated user-agent because we must avoid discrimination from websites that allow only Google to crawl them. However, if a domain or page is not crawlable by any search engine (it has a noindex tag), or if it is not crawlable by googlebot, then Brave Search’s bot will not crawl it either.
Brave Search’s crawler is partially powered by information provided by users enrolled in the Web Discovery Project (WDP) option in Brave browser’s search settings, which is an off-by-default (aka opt-in), privacy-preserving system. WDP has multiple mechanisms to prevent Brave from knowing who is contributing what (WDP is also open-source for auditing and inspection by anyone).
Schema enriched Web results
The enriched set of structured data about a webpage that better represents and describes the page. For example, a standard (non-enriched) search result for a Rotten Tomatoes movie review page might contain basic info like URL, title, and synopsis. By contrast, Brave’s schema-enriched result for the same movie page might include this basic info plus a thumbnail image; attributes like release date, director, actors, and rating; and even show review scores. Beyond movies, Brave Search can enrich search results with many types of data, on many kinds of pages, including for videos, articles, products, recipes, software, books, contact information, and more.
Discussions
Discussions is a feature in Brave that is designed to easily serve discussion-based results around searches where there are heavy SEO results. The Brave Search ranking algorithm detects cases where discussion forums would provide an alternative or complementary viewpoint to the organic search results. This is done by computing a “discussion_worthiness” score, which is based on a variety of signals. Learn more.
Goggles
Goggles enable any individual—or community of people—to alter the ranking of Brave Search by using a set of instructions (rules and filters). Anyone can create, apply, or extend a Goggle. Essentially Goggles act as a custom re-ranking on top of the Brave search index. Learn more.
Sep 22, 2023
An application programming interface, or API, is a set of code that takes inputs, and produces outputs according to specific rules. In this quick primer, learn how search engine APIs work, and how they can power the AI applications you use everyday.
Go to guidesDec 15, 2023
Training data is the starting point for any machine learning (ML) approach to artificial intelligence (AI). Most major large language models (LLMs) are first pre-trained on vast amounts of raw text to "learn" how to predict language. But for that raw-text training data to be useful, it needs to be diverse. In this article, we'll explore how the Brave Search API can supply just such a diversity of data, and help you build better AI.
Go to guidesSep 22, 2023
Many apps and websites have search functionality. To power this search, developers often rely on search engine APIs. In this quick primer, we'll introduce the Brave Search API, and the key factors that set it apart from the competition.
Go to guidesSep 22, 2023
Brave Search is the fastest growing search engine since Bing, with over 8 billion annualized searches. In this side-by-side comparison, we'll explore how the Brave Search API stacks up against the Bing API.
Go to guidesMay 6, 2025
This guide covers the steps required to enable Brave Search as a tool to be used in the Claude desktop app using the Model Context Protocol (MCP). Since both Brave’s and Anthropic’s products are evolving quickly, it’s best to always check official documentation for the most up-to-date information and instructions. In order to use MCP, you will need to have Node.js installed on your computer. Please note that some Windows users have encountered issues with MCP when using a node installer, rather than node version manager.
Go to guidesMay 6, 2025
This guide will help you get set up with the Brave Search API in Dify, an open-source platform designed to simplify AI application development, and offer real-time, accurate search results as part of AI agent orchestration. Dify offers an intuitive interface that brings together AI workflows, RAG pipelines, and agent capabilities, empowering developers to rapidly move from initial concept to production-ready applications. Sign-up and create a key for Brave Search API Register or login to a Brave Search API account.
Go to guidesMay 6, 2025
This guide covers the steps to enable Brave Search via the official Brave Search community node in n8n.io, a flexible and community-driven automation platform. Please note, this covers the local version of n8n. Sign-up and create a key for Brave Search API Register or login to a Brave Search API account. For use with n8n, you must ensure you are subscribed to one of the Data for AI plans, which are found under the Subscriptions tab in the left hand menu of the dashboard.
Go to guidesMay 6, 2025
OpenAI’s release of ChatGPT 3.5 was an inflection point for the broad adoption of generative artificial intelligence. Since then, there’s been an explosion of new AI business ventures from startups all the way to Big Tech, building across a wide range of vertical and horizontal markets. Today, Generative AI has already made its way into a significant share of the software we use day to day. There are various ways to divide and categorize the sprawling AI market, but we chose a method that allowed for effective grouping based on the primary business function of each company.
Go to guidesMay 2, 2024
This guide covers the steps required to enable Brave Search as the default search engine in Open WebUI, a free and extensible self-hosted AI interface. Since both Brave Search API and any Open WebUI frameworks or libraries can evolve quickly, it’s best to always check the official documentation for the most up-to-date details. 1. Install Open WebUI using Docker Follow the official documentation to install Open WebUI on your choice Linux, Mac, or Windows: https://docs.
Go to guides
Open the installer from Chrome's downloads (it should be in the upper right corner of this window).
If you're prompted to, click “Yes” in the User Access Control dialog.
Wait for the installation to finish, then import your browser settings from Chrome.
If your download didn’t start automatically, click here.
