How much does Exa cost?

Exa offers a free tier. Paid usage includes Search at $7 per 1k requests, Agent runs from $0.012 to $1.00, Contents at $1 per 1k pages, and Deep Search at $12–15 per 1k requests.

What is Exa best for?

It is best for wiring web retrieval into AI agents. It returns clean, schema-shaped, token-efficient results and offers vertical indexes for companies, people, and code repositories.

Does Exa support open-source or self-hosted options?

No, Exa is proprietary and API-only. If you need a self-hosted or open-source search stack, or retrieval purely over internal documents, you should skip it and look elsewhere.

How does Exa reduce token usage?

Exa includes a Highlights mode that extracts relevant page excerpts. This allows callers to cut up to 90% of the tokens they would otherwise feed to a model.

What integrations does Exa support?

Exa provides an MCP server for plug-in use from clients like Claude and Cursor. It is designed for AI agents and LLM applications, with cited users including Cognition, HubSpot, and Monday.com.

Exa

✓ Editorially verified

Web search API built for AI agents, with structured outputs and token-efficient highlights.

Freemium· Free Tier: Free · Search: $7/1k requests · Agent: $0.012–$1.00/run · Contents: $1/1k pages per content type · Deep Search: $12–15/1k requestsRAGProprietary neural + keyword search8.0 / 10

Visit website →

In short

Exa is a web search API for AI agents offering structured JSON outputs and token-efficient highlights. It supports vertical indexes for companies, people, and code with usage-based pricing.

Best for

Pick Exa if you are wiring web retrieval into an AI agent and want a single API that returns clean, schema-shaped, token-efficient results.

Skip if

Skip it if you need a self-hosted or open-source search stack, or your retrieval is purely over internal documents.

Exa (formerly Metaphor) is a web search and retrieval API designed for AI agents and LLM applications that need fresh, structured web data. It offers fast keyword-and-neural search, automated crawling, JSON outputs against custom schemas, and a Highlights mode that extracts the relevant excerpts of a page so callers can cut up to 90% of tokens they would otherwise feed to a model. A Deep Research mode lets you trade latency for thoroughness.

The target customer is anyone building retrieval into an agent stack: Cognition, Cursor, HubSpot and Monday.com are cited on the homepage. Beyond general web search, Exa has vertical indexes for companies, people, and code repositories, which is the differentiator versus rolling your own SerpAPI + scraper pipeline. Pricing is usage-based with a free playground; production tiers are paid and enterprise plans include SSO, SOC 2 Type II, and zero-retention options.

It is proprietary and API-only, with an MCP server for plug-in use from Claude, Cursor and similar clients. If you want a pure open-source self-hosted search, look elsewhere; if you want managed retrieval that drops into an agent in an afternoon, this is one of the cleaner options.

Editor's take

Exa has quietly become the default web-search layer for serious agent builders, and the rebrand from Metaphor reflects that maturity. The Highlights and structured-output features pay for themselves in token savings alone, and the vertical indexes are a real moat. Worth a benchmark against your current SerpAPI + scraper stack.

— The AI Tool Bible editorial team

Pros

✅ Purpose-built for LLM/agent use, not retrofitted consumer search
✅ Highlights mode dramatically cuts tokens sent to the model
✅ Structured JSON outputs against custom schemas
✅ Vertical indexes for companies, people, and code
✅ SOC 2 Type II with zero-retention enterprise option

Cons

⚠️ Proprietary, closed source
⚠️ Pricing not transparent on homepage beyond the free playground
⚠️ Coverage and freshness depend on Exa's crawl, not yours

Use cases

agent-web-searchrag-retrievalcompany-researchpeople-searchcode-searchdeep-research

Frequently asked

How much does Exa cost?: Exa offers a free tier. Paid usage includes Search at $7 per 1k requests, Agent runs from $0.012 to $1.00, Contents at $1 per 1k pages, and Deep Search at $12–15 per 1k requests.
What is Exa best for?: It is best for wiring web retrieval into AI agents. It returns clean, schema-shaped, token-efficient results and offers vertical indexes for companies, people, and code repositories.
Does Exa support open-source or self-hosted options?: No, Exa is proprietary and API-only. If you need a self-hosted or open-source search stack, or retrieval purely over internal documents, you should skip it and look elsewhere.
How does Exa reduce token usage?: Exa includes a Highlights mode that extracts relevant page excerpts. This allows callers to cut up to 90% of the tokens they would otherwise feed to a model.
What integrations does Exa support?: Exa provides an MCP server for plug-in use from clients like Claude and Cursor. It is designed for AI agents and LLM applications, with cited users including Cognition, HubSpot, and Monday.com.