# Andi AI Search API Docs

- [Andi AI Search API](https://docs.andiai.com/index.md): Web search API for AI agents, RAG pipelines, and search applications. Structured, accurate results from a web index of tens of billions of pages.
- [Quickstart](https://docs.andiai.com/getting-started/quickstart.md): Set up Andi web search and page fetch in your agent or application. One-line agent install, CLI, or manual API key setup.
- [CLI](https://docs.andiai.com/getting-started/cli.md): Search the web, fetch pages, and run a local MCP server from the command line with the Andi CLI.
- [Build with AI agents](https://docs.andiai.com/resources/ai-agents.md): Connect AI agents to Andi web search via MCP, and to the Andi docs via MCP, llms.txt, and markdown content negotiation. Optimized for Claude Code, Cursor, VS Code, and other AI tools.
- [Authentication](https://docs.andiai.com/getting-started/authentication.md): Authenticate with the Andi AI Search API using API keys in the x-api-key header.
- [Search modes](https://docs.andiai.com/search/search-modes.md): Andi sets the right search effort for every query automatically — or you can pin the effort level yourself with searchMode.
- [Fast mode](https://docs.andiai.com/search/fast-search.md): Search mode optimized for speed, returning results in ~1 second.
- [Deep mode](https://docs.andiai.com/search/deep-search.md): Searches your topic from multiple angles to find higher-quality results, with spell correction, in ~2–3 seconds.
- [Content retrieval](https://docs.andiai.com/search/content-retrieval.md): Fetch and extract clean content from any web page with the /api/v1/fetch endpoint.
- [News feeds](https://docs.andiai.com/search/news-feeds.md): Curated, ranked topic news feeds with the /api/v1/news/:topic endpoint — no query required.
- [Query parameters](https://docs.andiai.com/features/query-parameters.md): Complete reference for all Andi AI Search API query parameters.
- [Query operators](https://docs.andiai.com/features/query-operators.md): Use in-query operators to refine search results directly in the query string.
- [Filtering](https://docs.andiai.com/features/filtering.md): Filter Andi AI Search API results by domain, date range, file type, and content location.
- [Response format](https://docs.andiai.com/features/response-format.md): Structure of the Andi AI Search API response, including result types, metrics, and the context format for LLMs.
- [Error handling](https://docs.andiai.com/resources/error-handling.md): Error response format, status codes, and retry strategies for the Andi AI Search API.
- [Rate limits](https://docs.andiai.com/resources/rate-limits.md): Rate limit configuration and handling for the Andi AI Search API.
- [Basic search integration](https://docs.andiai.com/examples/basic-search.md): Build a complete search integration with environment variables, error handling, and response parsing.
- [RAG pipeline](https://docs.andiai.com/examples/rag-pipeline.md): Use Andi search results as retrieval context for a language model to generate grounded answers.
- [AI agent tool](https://docs.andiai.com/examples/ai-agent-tool.md): Connect an AI agent to Andi search via MCP, or define search and fetch as tools for any agent framework.
- [News monitoring](https://docs.andiai.com/examples/news-monitoring.md): Build automated news monitoring with date filtering, intent forcing, and domain restrictions.
- [Research assistant](https://docs.andiai.com/examples/research-assistant.md): Build a research assistant with multi-query search, result aggregation, and searchMode control.
- [API reference](https://docs.andiai.com/api-reference/introduction.md): Technical reference for the Andi AI Search API endpoints.
- [Search the web](https://docs.andiai.com/api-reference/search-the-web.md): Performs a web search and returns structured results. Search effort is set automatically per query by default (`searchMode=auto`), with fixed modes (low-cost, fast, balanced, deep, exhaustive) available for manual control. Supports domain and date filtering, query operators, and multiple output form…
- [Search the web (JSON body)](https://docs.andiai.com/api-reference/search-the-web-json-body.md): Same contract as `GET /api/v1/search`, but accepts parameters as a JSON body. Preferred for location-bearing requests because GET-style location encoding is awkward and keeps `latitude`/`longitude` out of HTTP access logs. All GET query parameters are accepted as body fields, plus optional location…
- [Fetch a web page](https://docs.andiai.com/api-reference/fetch-a-web-page.md): Fetches a single web page and returns clean extracted content (title, article text, metadata) as JSON, or LLM-ready markdown with format=context. The companion to /api/v1/search: search, pick a result, fetch it in full.
- [Get a curated news feed](https://docs.andiai.com/api-reference/get-a-curated-news-feed.md): Returns a curated, ranked news feed for a fixed topic — there is no query parameter, the topic path segment selects the feed. `results` are ordered by relevance (a semantic pass tuned to the topic, weighted toward fresher articles); `news` holds the same articles in strict reverse-chronological orde…

## OpenAPI Specs

- [openapi](/api-reference/openapi.json)

## Optional

- [AndiAI.com](https://andiai.com)
- [API Console](https://console.andiai.com)
- [Andi Search](https://andisearch.com)