Source: Exa search API docs

Exa's reference for its own-index, embeddings-based web search API: search types and latency, content options (highlights, text, summary), filters and freshness control.

Contents

Summary

Exa runs its own web index and returns ranked results plus page content in one request, with modes from a ~300 ms cached lookup to multi-step “deep” research.

Key claims

  • type: auto (default, ~1 s), lite (~300 ms, $4 per 1,000 requests, cached content only, never fetches live), deep-lite (~4 s, light synthesis), deep (4-15 s, multi-step search with synthesis). Legacy fast, instant, deep-reasoning are superseded.
  • The query is natural language; docs advise describing subject, source type and period.
  • numResults 1-100 (default 10), no pagination; category (company, news, publication, financial report, people, personal site); includeDomains / excludeDomains up to 1,200 with path prefixes and wildcards; published-date bounds.
  • Content: highlights (query-relevant excerpts, the recommended default), text (full clean body, cap with maxCharacters), summary (LLM per result, extra cost), outputSchema for a synthesized answer with grounding and confidence.
  • Freshness: maxAgeHours (replaces deprecated livecrawl): positive N uses cache younger than N hours, 0 forces content fetched within 60 seconds, -1 cache only. It controls content age, not publication date.
  • Pricing (exa.ai/pricing, 2026-11), per 1,000 requests with up to 10 results: lite $4, auto $7, deep-lite $12, deep $12; each extra result $1 per 1,000; /contents $1 per 1,000 pages per content type; AI page summaries $1 per 1,000 pages.
  • Responses include an estimated costDollars breakdown; a neural cost line suggests embedding-based retrieval (the docs do not detail the index).

Feeds

Web search APIs

Suggest changes →