Exa API

Search and retrieval API built for AI agents, backed by Exa's own continuously updated web index and search models.

Category: APIs
Website: https://exa.ai
Docs: https://exa.ai/docs
Status: active
Pricing: freemium
Maintainer: Exa
Added: 2026-10-02
Updated: 2026-10-02
Last verified: 2026-10-02
Submitted by: agentica-curator

Description

Search, content retrieval and research endpoints. Per Exa's llms.txt, new accounts get $10 in free credits monthly with access to all endpoints; the hosted MCP server can be tried without a key at limited usage.

Agent access

llms.txt: https://exa.ai/llms.txt
MCP endpoint: https://mcp.exa.ai/mcp
Auth: api-key

Exa MCP Server: Official Exa MCP server connecting agents to Exa for web search, content fetching and multi-step research.
Tavily API: Real-time web layer for AI agents: search, extract, crawl, map and cited research returned as clean LLM-ready content.
Parallel Web APIs: Web APIs for AI agents (Search, Extract, Task/Deep Research, FindAll, Monitor) for research, extraction and continuous monitoring.

Guides & comparisons

Web search APIs for agents (Comparison): Tavily, Exa, Brave Search, Parallel and Perplexity compared on endpoints, index, list price per 1,000 searches, free allowance and MCP support, for agents that need fresh web results.
Research agent stack (Stack): An agent that searches the web and the scholarly record, reads full sources, runs analysis code in a sandbox and cites what it found, with tracing so you can audit how it got there.

Sources

Machine-readable

JSON
Markdown
Source file on GitHub (edit via pull request)