1B+ pages indexed · 5ms latency · 114 languages

Search API for
AI agents & apps

One API for web search, content extraction, image search, and AI answers. Built for agents, not browsers.

$
/api/v1/extract

Paste a URL and press Run

# Get a free API key (one command)
curl -X POST https://searchx.dev/api/v1/signup \
  -d '{"email":"you@example.com"}'
# → {"api_key": "sk-sx-...", "daily_limit": 3000}

# Search the web
curl https://searchx.dev/api/v1/search \
  -H "Authorization: Bearer sk-sx-YOUR_KEY" \
  -G -d "q=kubernetes deployment" -d "mode=hybrid"

# Extract any webpage (JS rendering supported)
curl https://searchx.dev/api/v1/extract \
  -H "Authorization: Bearer sk-sx-YOUR_KEY" \
  -G -d "url=https://react.dev" -d "render=js"

6 endpoints, one API key

Everything your agent needs to search, read, and understand the web.

GET /search

Web Search

Hybrid keyword + semantic search across 1B+ pages. BM25 + vector embeddings with RRF fusion.

GET /extract

Content Extraction

URL to clean markdown. Headless Chrome for SPAs. Metadata, outline, images, quality score.

GET /images/search

Image Search

Keyword + semantic image search. 600K+ images indexed. Alt text + vector similarity.

GET /answer

AI Answer

Direct answer with inline citations. LLM synthesized from top sources. One call replaces RAG.

GET /suggest

Autocomplete

Prefix search with fuzzy matching. Real-time query suggestions from the index.

POST /mcp

MCP Protocol

Native Model Context Protocol. Plug into Claude Desktop, Cursor, or any MCP-compatible agent.

1B+
Indexed pages
<5ms
Cached latency
114
Languages
$0
3K queries/day free

Why switch to SearchX

SearchXBing APIFirecrawlSerpAPI
Free tier3K/day (90K/mo)1K total500/mo100/mo
Search + ExtractBoth includedSearch onlyExtract onlySearch only
JS renderingIncludedNo$19+No
Semantic searchIncludedNoNoNo
AI answerBuilt-inNoNoNo
Image searchIncluded$5 add-onNo$50/mo
MCP protocolNativeNoYesNo

Clean JSON, zero HTML parsing

Every response is structured JSON. Titles, snippets, citations, metadata — ready for your LLM context window.

{
  "results": [
    {
      "title": "Kubernetes Deployment Guide",
      "url": "https://kubernetes.io/docs/...",
      "snippet": "A Deployment provides declarative updates...",
      "score": 1268.06,
      "domain": "kubernetes.io",
      "trust_score": 0.96,
      "citation": "[Kubernetes Deployment Guide](url) — kubernetes.io"
    }
  ],
  "total": 12840,
  "took_ms": 4
}