Search APIs for AI agents

Brave — news-only search over the Brave index: recent articles with source, age, and breaking flags. Pass `q`; optional `count` (1-50), `country`…

Brave — keyword web search over Brave's own independent index (not Google/Bing). Pass `q`; optional `count` (1-20), `offset` (pagination), `country`…

Cloro via Monid: ChatGPT's consumer-app answer to a prompt, as a logged-out user in a chosen country (or US state): answer text, cited sources, citation…

Cloro via Monid: Microsoft Copilot's consumer-app answer to a prompt in a chosen country (or US state), with cited sources.

Cloro via Monid: Gemini's consumer-app answer to a prompt in a chosen country (or US state), with cited sources and citation pills.

Cloro via Monid: Google AI Mode's answer to a prompt in a chosen country, with the sources it cites in order.

Cloro via Monid: Google News results for a query in a chosen country: headline, source, date, link and snippet.

Cloro via Monid: The Google results page for a query in a chosen country as JSON: organic results, People Also Ask, related searches, local pack, ads; include…

Exa — retrieve content for URLs or document IDs via our API key. Charges 0.1¢ per (url or id) × content field requested.

Exa — semantic web search via our API key. numResults up to 100. For people/lead discovery set category:"people" with an open ICP query.

Linkup — DEEP agentic search: iterative multi-query retrieval for hard or multi-hop questions where one-pass search misses. Same params as linkup/search (`q`…

Linkup — AI web search returning a cited answer or ranked results. Pass `q`; optional `outputType` (sourcedAnswer default — synthesized answer with sources |…

Parallel — Extract clean content from URLs via x402. Charges 1¢ per URL in `urls`.

Parallel — AI-powered web search via x402 (1¢ flat).

Parallel — Start an async AI research task. Pricing depends on `processor`: pro 10¢, ultra 30¢. Returns { run_id }; poll task-status until completed.

Parallel — Poll an async task by run_id. Free per vendor docs; returns the same payload until status flips to completed.

Perplexity — web search over Perplexity's own retrieval index, the one behind its answer engine, returning ranked results with snippets plus `date` and…

Serper — Google News results: recent articles with source, date, and thumbnail. Pass `q`; optional `num`, `page`, `gl`, `hl`, `location`, `tbs` (freshness…

Serper — real Google web results: organic ranks with snippets, knowledge graph, people-also-ask, related searches. Pass `q`; optional `num` (1-100 results)…

Tavily — extract clean page content (JS handled) from up to 5 URLs you already have, in one 1¢ call. Pass `urls` (array, ≤5); optional `format` (markdown…

Tavily — AI-native web search tuned for RAG: ranked results with relevance scores, optional LLM answer synthesis. Pass `query`; optional `topic`…

Valyu — search arXiv and PubMed directly and get the paper text back, not a link to it. Pass `query`; optional `max_num_results` (1-10)…

Valyu — web search returning ranked results with full-text excerpts already extracted (no follow-up scrape for the body text). Pass `query`; optional…