AI-native search engine and API (formerly Metaphor, now Exa) that finds content through semantic understanding rather than keyword matching.
AI-native search engine and API (formerly Metaphor, now Exa) that finds content through semantic understanding rather than keyword matching.
Metaphor, now rebranded as Exa, is a modern AI-powered search engine and API platform designed to give developers and AI agents access to high-quality web search, content extraction, and structured data retrieval. Unlike traditional search engines that rely on keyword matching, Exa uses neural network-based semantic understanding to find content based on meaning, context, and conceptual similarity. The platform maintains a massive web index of over 70 million companies and dedicated high-quality indexes for specific verticals including people, code documentation, financial data, and news, making it particularly powerful for enrichment and research workflows.
Exa is built primarily as a developer-first API platform, offering products including Search, Contents, Answer, and Websets. The Search API delivers results in under 180 milliseconds, making it suitable for powering real-time AI agent workflows. Its structured output capability allows developers to extract specific data fields from search results, enabling complex enrichment pipelines. The Highlights feature intelligently extracts the most relevant excerpts from web pages, helping reduce token budgets and LLM costs by over 50 percent when feeding results into language models.
The platform is trusted by leading AI companies including OpenRouter, Databricks, Flatfile, StackAI, and Anara for use cases ranging from powering coding agents to scientific research workflows. Exa offers enterprise-grade security with SOC 2 Type II certification, Zero Data Retention options for privacy-sensitive deployments, and Single Sign-On for team management. Whether you are building an AI agent that needs real-time web context, conducting deep research across the web, or assembling structured datasets from unstructured sources, Exa provides the infrastructure to do so programmatically at scale.
Was this helpful?
Highly regarded for its fast, developer-friendly semantic search API. Users praise the sub-200ms latency, structured output capabilities, and dedicated vertical indexes. Particularly valued by AI agent builders and RAG pipeline developers for token-efficient content extraction. Some users note usage-based costs can scale quickly for high-volume workloads.
Exa's Search API returns results in under 180ms and supports structured output extraction, allowing developers to define JSON schemas and receive clean, typed data directly from search results. This enables complex enrichment workflows â such as extracting company names, CEO names, and founding years â from Exa's database of over 70 million companies without additional scraping or parsing steps.
The Highlights feature extracts the most query-relevant excerpts from web pages, reducing the amount of text that needs to be sent to language models by over 50%. This is critical for AI agent and RAG pipeline builders who need to balance context quality with token costs, ensuring LLMs receive focused, relevant information rather than entire web pages.
Exa maintains industry-leading, curated web indexes for specific use cases including people, companies, code documentation, financial data, and news. These specialized indexes provide higher quality and more relevant results than general-purpose search for domain-specific queries, making them ideal for vertical AI applications and targeted research workflows.
Websets allows users to programmatically build structured, filtered collections of entities from web data based on defined criteria. This product turns Exa's search capabilities into a dataset assembly tool, useful for lead generation, competitive intelligence, market mapping, and creating curated training data at scale without manual research.
Exa provides SOC 2 Type II certified infrastructure with customizable Zero Data Retention policies that ensure queries and results are automatically purged according to organizational requirements. Combined with Single Sign-On team management, these features make Exa suitable for compliance-sensitive deployments in healthcare, finance, and government-adjacent industries.
$0/month
From $1 per 1,000 searches
Usage-based with volume discounts
Custom pricing
Ready to get started with Metaphor?
View Pricing Options âMetaphor works with these platforms and services:
We believe in transparent reviews. Here's what Metaphor doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
Exa has launched Websets as a new core product for building structured datasets from web search results. The platform now features structured output capabilities for extracting typed JSON data directly from search, dedicated vertical indexes covering 70M+ companies, and an MCP Server for integration with AI coding tools. Enterprise security features including SOC 2 Type II certification and Zero Data Retention have been added for compliance-sensitive deployments.
AI Search
Microsoft's free AI search assistant (now Copilot) combining GPT-powered conversational answers with web citations, image generation, and deep Microsoft 365 integration.
AI Search
Premium ad-free search engine with AI assistant, offering unbiased results, complete privacy, and personalized search customization through a subscription model.
Coding Agents
Revolutionary developer-focused AI search engine that delivers instant, accurate answers to coding questions with working code examples and technical explanations, transforming how programmers research and solve problems.
No reviews yet. Be the first to share your experience!
Get started with Metaphor and see if it's the right fit for your needs.
Get Started âTake our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack âExplore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates â