Overview
개발자를 위한 Perplexity의 원시 웹 검색 API: AI 에이전트 및 RAG 파이프라인의 근거 마련을 위해 도메인, 날짜, 언어 필터를 포함하여 Perplexity 자체 인덱스에서 추출한 제목, URL, 스니펫, 날짜가 포함된 순위 웹 결과를 반환합니다. Sonar 답변 API와는 별개입니다.
BuildBecomes the API
Perplexity Search API
개발자를 위한 Perplexity의 원시 웹 검색 API: AI 에이전트 및 RAG 파이프라인의 근거 마련을 위해 도메인, 날짜, 언어 필터를 포함하여 Perplexity 자체 인덱스에서 추출한 제목, URL, 스니펫, 날짜가 포함된 순위 웹 결과를 반환합니다. Sonar 답변 API와는 별개입니다.
유료 · API
요금제
Standard Search$1.00/1,000 requests
Real-time web search results · Ranked results · Domain filtering · Multi-query support
Fast Search$1.00/1,000 requests
Lower latency results · Basic search parameters
대안 비교
- Tavily Search APIAI-native search and content extraction API built specifically for LLM pipelines and autonomous agents.
- Exa Search APINeural web search and content retrieval API providing structured, LLM-ready web data for AI agents.
- Brave Search APIIndependent web index API providing real-time search queries and structured results for AI applications and agents.
Perplexity Search API
유료 · API
이 글이 마음에 드셨나요? 매일 아침 이런 글을 메일로 받아보세요.
하루 한 통 · 두 번의 클릭으로 구독 취소 · 제3자 추적 없음
Stork Quadrant
Becomes the API· 32/100
Replaceable as a UI, but kept alive as the API the agents call.
“This is a search index API competing against Google, Bing, Brave, and Exa — all of which have larger indexes, longer track records, and stronger developer trust. Perplexity doesn't own proprietary data; they crawl the same web. The only differentiator is index freshness and ranking quality, neither of which is a durable moat. This will get squeezed from above by Google and from below by cheaper alternatives.”
Defensibility · 0/100
- Physical-world coupling
- Regulatory moat
- Network liquidity
- Proprietary refreshing data
- High-trust catastrophic workflows
- Multi-party coordination
- Brand / community / taste
An LLM alone could replace
- Return ranked web results with titles, URLs, and snippets — Google Search API, Bing Search API, and Brave Search API all do this today
- Filter results by domain, date, and language — standard capability in every major search API
- Ground an LLM response with fresh web content — any search API plus an LLM prompt does this
- Power a RAG pipeline with web retrieval — commodity pattern, no Perplexity-specific advantage
Agent-Readiness · 70/100
- Verified MCP
- Listed on agent surfaces— anthropic_directory, cursor
- Usage-based pricing— pricing page heuristic match: https://docs.perplexity.ai/pricing
- Headless agent auth— https://docs.perplexity.ai/docs (api-key auth)
- Public OpenAPI— https://docs.perplexity.ai/openapi.json
- Active changelog— https://docs.perplexity.ai/changelog (2026-11-10)
- llms.txt— https://docs.perplexity.ai/llms.txt
How to defend
Stop selling raw search results and become the answer layer with verifiable citations that agents can trust — own the liability for factual grounding, not just the retrieval. Alternatively, build vertical indexes (legal, medical, financial) with proprietary crawl agreements that competitors can't replicate.
- Ship an MCP server and list it on Stork — biggest single point gain (+25).