Skip to main content
New to Exa? Try the Coding Agent Quickstart to get started in under a minute.
The official JavaScript SDK for Exa. Search the web, get page contents, find similar pages, and get answers with citations.

Get API Key

Get your API key from the dashboard

​
Install

bash npm install exa-js

​
Quick Start

import Exa from "exa-js";

const exa = new Exa(); // reads EXA_API_KEY from environment
Search the web and get page contents in one call. 
const result = await exa.search("blog post about artificial intelligence", {
  contents: {
    highlights: {
      maxCharacters: 4000,
    },
  },
});

const result = await exa.search("interesting articles about space", {
  numResults: 10,
  includeDomains: ["nasa.gov", "space.com"],
  startPublishedDate: "2024-01-01",
  contents: {
    highlights: {
      maxCharacters: 4000,
    },
  },
});

const structuredResult = await exa.search("Who is the CEO of OpenAI?", {
  type: "deep",
  systemPrompt: "Prefer official sources and avoid duplicate results",
  outputSchema: {
    type: "object",
    properties: {
      leader: { type: "string" },
      title: { type: "string" },
      sourceCount: { type: "number" },
    },
    required: ["leader", "title"],
  },
  contents: {
    highlights: {
      maxCharacters: 4000,
    },
  },
});

console.log(structuredResult.output?.content);
outputSchema and systemPrompt work across all search types. Keep outputSchema focused on output.content, and use systemPrompt to guide the final returned result. For more demanding synthesis, prefer reasoning-focused search types like deep-lite, deep, deep-reasoning, or deep-max. Do not include citations/confidence in your schema; Exa returns grounding automatically in output.grounding. Including citation/confidence fields in outputSchema duplicates data, reduces structure quality, and is usually less reliable.
Reasoning-focused search variants:
  • deep-lite: lowest-latency deep-search mode
  • deep: light mode
  • deep-reasoning: base reasoning mode
  • deep-max: maximum-effort deep-search mode
Need streaming structured synthesis? The raw /search endpoint supports stream: true together with outputSchema and returns OpenAI-compatible SSE chunks. See the Search API guide.

​
Get Contents

Get text, summaries, or highlights from URLs. 
const { results } = await exa.getContents(["https://openai.com/research"], {
  text: true,
});

const { results } = await exa.getContents(["https://stripe.com/docs/api"], {
  summary: true,
});

const { results } = await exa.getContents(["https://arxiv.org/abs/2303.08774"], {
  highlights: {
    maxCharacters: 2000,
  },
});

​
Find Similar

Find pages similar to a URL. 
const result = await exa.findSimilar("https://paulgraham.com/greatwork.html", {
  contents: {
    text: true,
  },
});

const result = await exa.findSimilar(
  "https://waitbutwhy.com/2015/01/artificial-intelligence-revolution-1.html",
  {
    excludeSourceDomain: true,
    contents: {
      text: true,
    },
  },
);

​
Answer

Get answers to questions with citations. 
const response = await exa.answer("What caused the 2008 financial crisis?");
console.log(response.answer);

for await (const chunk of exa.streamAnswer("Explain quantum computing")) {
  if (chunk.content) {
    process.stdout.write(chunk.content);
  }
}

​
Research

Run research tasks with structured output. 
const task = await exa.research.create({
  instructions: "Find the top 5 AI startups founded in 2024",
  outputSchema: {
    type: "object",
    properties: {
      startups: { type: "array", items: { type: "string" } },
    },
  },
});

const result = await exa.research.pollUntilFinished(task.researchId);

​
TypeScript

Full TypeScript support with types for all methods. 
import Exa from "exa-js";
import type { SearchResponse, RegularSearchOptions } from "exa-js";

​
Resources

  • GitHub - View source code
  • npm - View package