Early Access

Search API for
AI Agents

Access an AI-powered index of 14B+ pages through a single API. Two search modes, structured JSON responses, and output formats built for LLMs.

Fast & Deep modes Sub-second fast response RAG-ready output

Request Early Access Read the Docs

Already have access? Open Console

terminal

$ curl -s "https://api.andiai.com/v1/search?q=best+hiking+trails" \
  -H "x-api-key: your_key" | jq .


  "results": [
    
      "title": "Best Hiking Trails in the US",
      "link": "https://example.com/trails",
      "desc": "From Zion Narrows to...",
      "source": "example.com"
    ,
    // ... more results
  ],
  "results_type": "search"

14B+

Pages indexed

Independent benchmarks

<1¢

Per query

<1s

Fast mode response

Two Search Modes

Set the depth parameter to control the trade-off between speed and detail.

Fast Mode

Sub-second multi-query web search. Returns ranked results with metadata detail and depth that you control. Default mode — best for real-time applications.

depth=fast · ~0.5–1s · 10 results default

Deep Mode

Extended search with cascading queries + 1000s of API sources. Reads deeper into the web and keeps searching for more thorough results. Best for research and complex queries.

depth=deep · ~2–3s · extended sources

Built for AI Agents & Developers

Every surface — API responses, documentation, this website — is built for programmatic consumption. Whether you're an AI agent, a coding tool, or a developer with curl.

Docs MCP Server

Connect Claude Code, Cursor, or VS Code to docs.andiai.com/mcp and your coding tools can search the API docs while you build.

LLM-Optimized Output

format=context returns search results as markdown built for LLM context windows. Feed directly into RAG pipelines and AI agents.

Markdown Content Negotiation

Accept: text/markdown on both docs and this site returns clean markdown with YAML frontmatter — ~30x smaller than HTML.

llms.txt Discovery

Standard /llms.txt and /llms-full.txt files on both docs and marketing site for agent discovery. Our search crawlers also index llms.txt to understand the agentic web.

AI Crawler Friendly

robots.txt explicitly allows GPTBot, ClaudeBot, PerplexityBot and more. We want AI to read our content. When we crawl, we respect robots.txt and try to be good netizens.

Standards Compatible

Google CSE and OpenSearch-compatible /v1/opensearch endpoint as well as our AI-friendly /v1/search. Migrate from an existing search API with minimal code changes.

Get Started

Get your API key

Request early access and create a key in the API Console.

Read the docs

Quickstart, parameters, response formats, and code examples at docs.andiai.com.

Make your first query

One curl command to search 14 billion pages.

quickstart

$ curl "https://api.andiai.com/v1/search?q=your+query" \
  -H "x-api-key: YOUR_API_KEY"

Start Building

Get access to 14 billion pages of web content through a single API. Fast and Deep search modes, structured for AI agents.