ExaAI-native search API delivering high-quality web results for LLMs and agents

What's on our roadmap?

Build a (much) larger index Solve search. No, really.

Asked by Petros Georgiou · Feb 3, 2026

Does Exa have a crawler?

Exa crawls pages on the web, just like any other search engine. If a webpage has the noindex tag and is therefore not crawlable by any search engine, then Exa will not crawl that page.

Asked by Quang Nguyen · Jan 18, 2026

What security measures does Exa take?

We have robust policies and everything we do is either in standard cloud services, or built in house (e.g., we have our own vector database that we serve in house, our own GPU cluster, our own query model and our own search solution). In addition to this, we can offer unique security arrangements like zero data retention as part of a custom enterprise agreement. Learn more.

Asked by Mateusz Wozniak · Jan 17, 2026

How does similarity search work?

When you search using a URL, Exa crawls the URL, parses the main content from the HTML, and searches the index with that parsed content. The model chooses webpages which it predicts are talked about in similar ways to the prompt URL. That means the model considers a range of factors about the page, including the text style, the domain, and the main ideas inside the text. Similarity search is a natural extension for a semantic search engine like Exa, and something that’s difficult with traditional search engines.

Asked by Bianca Ferreira · Dec 28, 2025

How often is the index updated?

We update our index every hour, and are constantly adding batches of new links. We target the highest quality web pages. Our clients oftentimes request specific domains to be more deeply covered - if there is a use-case we can unlock by additional domain coverage in our index, please contact us.

Asked by Ren Nakamura · Dec 26, 2025