​

Contents Endpoint Reference

​

Canonical Docs Links

• Base docs URL: https://exa.ai/docs
• Contents reference: /reference/get-contents
• Contents coding-agent reference: /reference/contents-api-guide-for-coding-agents
• Contents best practices: /reference/contents-best-practices
• Content freshness: /reference/livecrawling-contents

​

Contents

• Overview
• Request shape
• Top-level content fields
• Freshness controls
• Response and statuses
• Critical pitfalls

​

Overview

• you already know the URLs
• you need clean extraction without first running a search query
• freshness and crawl behavior matter enough to control directly
• you want the search endpoint and contents endpoint separated into two explicit calls

​

Request Shape

POST https://api.exa.ai/contents
{
  "urls": ["https://arxiv.org/abs/2307.06435"],
  "highlights": {
    "query": "methodology"
  }
}

​

Core Request Parameters

​

Top-Level Content Fields

• on the search endpoint, content fields are nested inside contents
• on the contents endpoint, text, highlights, and summary are top-level request fields

from exa_py import Exa

exa = Exa(api_key="YOUR_EXA_API_KEY")
result = exa.get_contents(
    ["https://docs.exa.ai"],
    highlights=True
)

​

Content Field Behavior

​

Freshness Controls

​

Response and Statuses

{
  "results": [
    {
      "url": "https://example.com",
      "text": "..."
    }
  ],
  "statuses": [
    { "id": "https://example.com", "status": "success" },
    { "id": "https://bad.example", "status": "error" }
  ]
}

​

Critical Pitfalls

1. Do not wrap text, highlights, or summary inside a contents object on /contents.
2. Do not assume HTTP 200 means every URL succeeded; inspect statuses.
3. Do not add stream: true; the contents endpoint does not support streaming.
4. Prefer maxAgeHours over older livecrawl strings in new examples.
5. In Python SDK calls, remember snake_case inside nested options such as max_characters and max_age_hours.