← Back to directory

Exa

Web search, built for AI agents

Visit Exa

Exa is a search API built specifically for AI agents and applications, rather than for humans clicking through blue links. It returns clean, structured, token-efficient web content - search results, extracted page contents, and multi-step agent research - designed to be consumed directly by LLMs.

Vendor's own claim
data/enrichmentobservability/evaluationresearch/evidence

Core capabilities

Vendor's own claim
  • Search API with multiple latency/depth tiers (fast, neural, and 'deep search' modes with reasoning)
  • Contents API that extracts clean, token-efficient page content and highlights from URLs (vendor claims up to 90% token reduction vs. raw HTML)
  • Structured Outputs - schema-based extraction across a claimed 70M+ company index and other verticals
  • Exa Agent API - a hosted multi-step web research agent accessible over the API, with fixed-effort or metered pricing tiers
  • Websets - a workflow for turning a natural-language query into a curated, enriched list of people/companies (sourcing use case)
  • Exa Connect - integrations with third-party data partners (e.g.
  • Answer API for direct question-answering grounded in web search

API & agent surface

From official docs
Authentication
API key, sent either as Bearer token or x-api-key header (Authorization: Bearer $EXA_API_KEY)
Base URL
https://api.exa.ai
Rate limits
Default limits documented per endpoint: /search 10 QPS, /contents 100 QPS, /answer 10 QPS; higher limits available on Enterprise plans.
Notable endpoints
  • POST /search - neural/keyword web search with configurable depth
  • POST /contents - content extraction and highlights from URLs
  • POST /answer - direct question answering grounded in search
  • Agent API endpoints for multi-step hosted research
MCP tools exposed
web_search_exaweb_fetch_exaweb_search_advanced_exaagent_run
Machine-readable spec
OpenAPI spec retrieved

Official skills & repos

From official docs

Published by the vendor themselves — not community forks.

From the vendor's channel

We raised $85M to build the search engine for AIsExa AI Labs

Pricing

From official docs
PlanPriceIncludedNotable
Search$7 / 1,000 requestsPay-as-you-go, credit-meteredFast/neural search, Multiple search depth options
Deep Search (lite)$12 / 1,000 requests
Deep Search (standard)$12 / 1,000 requests
Deep Search (reasoning)$15 / 1,000 requestsReasoning-augmented deep search
Contents$1 / 1,000 pages (per content type)Token-efficient content extraction, Highlights
Answer$5 / 1,000 requestsDirect question answering grounded in search
Monitors$15 / 1,000 requestsScheduled/recurring search monitoring
Agent API$0.012 - $1.00 per request (fixed-effort tiers: Minimal/Low/Medium/High/XHigh), or up to $5/run meteredHosted multi-step web research agent, Component-based metered billing option
EnterpriseContact salesVolume discounts, Higher rate limits, SLAs

Checked 2026-07-30 against their pricing page. Vendors change pricing without notice.

What is Exa

Vendor's own claim

Exa (formerly Metaphor Systems) is a San Francisco-based AI research lab, founded by Will Bryk and Jeff Wang, building what it calls a search engine 'for AI agents' rather than for human browsers.

Ideal customer profile

Vendor's own claim

Engineering teams building AI agents, coding assistants, or research/enrichment products that need real-time, LLM-ready web data via API - from solo developers prototyping on free credits up to enterprise buyers needing SOC 2, zero-data-retention, and SLA guarantees.

Who should look elsewhere

Our read

Teams seeking a point-and-click GTM execution product should note that the official material retrieved emphasizes search, contents, answer, agent, and Websets surfaces rather than CRM or outbound sequencing workflows. This pass did not retrieve a broader non-technical application beyond Websets. Usage-based, per-endpoint pricing also requires buyers to forecast workload by endpoint.

Exa alternatives

Our read

APIs that answer a query with retrieved web content, built to be called by an agent rather than read by a person.

Category: Search and research APIs. Membership is decided by 2 stated tests, not by category tags — see them and the full comparison.

Exa FAQ

Does Exa have an API?

Yes - Exa is API-first.

From official docs
Is there a free tier?

New accounts get $20 in free credits (about 2,800 searches per the vendor), and the MCP server can be used without an API key at a rate-limited free tier.

Vendor's own claim
How is Exa priced?

Usage-based, metered per product: $7/1k search requests, $1/1k content pages, $5/1k answer requests, $12 - 15/1k deep-search requests, plus separate Agent API and Enterprise pricing. There is no flat monthly subscription on the public pricing page.

From official docs
What is 'Deep Search' vs regular Search?

Deep Search is a higher-latency, higher-cost tier (lite/standard/reasoning) intended for more comprehensive, citation-backed research versus the faster default search endpoint.

Vendor's own claim
What are Websets?

A product for turning a natural-language query into a curated, enriched list of companies or people - targeted at sourcing/list-building use cases rather than single-query search.

Vendor's own claim
Does Exa offer SOC 2 or enterprise security controls?

The Enterprise plan page references SOC 2 Type II, Zero Data Retention, and SSO as available; the public vulnerability-disclosure policy confirms a formal security program but doesn't itself restate these certifications.

Vendor's own claim
How much setup does Exa take?

A first API call or MCP connection can happen in minutes with just an API key (or no key at all for basic MCP use); production integrations with structured outputs or the Agent API take longer to tune.

Our read

Verify before you buy

  • Exact current company headcount and total funding/valuation figures (about page gives partial, possibly time-sensitive figures not confirmed against a second source)
  • Discord member count / community size

Need help setting it up?

This page tells you whether Exa fits. Cheetah builds and runs the system it goes into — enrichment, sequencing, CRM and the joins between them.

Book a call →

The directory stays free. There is nothing gated behind this.