News Search Reference

​

Overview

​

Minimal Working Example

curl -X POST "https://api.exa.ai/search" \
  -H "Content-Type: application/json" \
  -H "x-api-key: $EXA_API_KEY" \
  -d '{"query": "AI regulation updates", "type": "auto", "contents": {"highlights": true}}'

from exa_py import Exa
exa = Exa()
result = exa.search("AI regulation updates", type="auto", contents={"highlights": True})

import Exa from "exa-js";
const exa = new Exa();
const result = await exa.search("AI regulation updates", { type: "auto", contents: { highlights: true } });

​

Supported Parameters

​

Query Patterns

"AI startup funding announcements"
"semiconductor supply chain disruptions"

"OpenAI product launches"
"Tesla quarterly earnings results"

"trade policy changes US China"
"climate summit agreements 2026"

{
  "query": "cybersecurity breaches",
  "type": "auto",
  "numResults": 20
}

​

Common Mistakes

​

Patterns and Gotchas

• News search is integrated into the main search endpoint. No category parameter needed. Just use descriptive news-related queries with type: "auto".
• includeDomains controls source quality. For trusted sources, restrict to ["reuters.com", "bbc.com", "nytimes.com"]. For trade press, use ["techcrunch.com", "theverge.com"].
• Use highlights for agent workflows. News articles are verbose. Highlights extract the key facts and quotes.
• Python SDK uses snake_case. numResults → num_results, maxCharacters → max_characters.
• News works well with deep search. Use type: "deep" with outputSchema to extract structured event summaries, sentiment, or entity mentions from news results.