{"slug": "perplexity-search-api-review", "title": "Perplexity Search API Review", "summary": "Perplexity's Search API, launched in September 2025, returns raw ranked web results from Perplexity's own index of hundreds of billions of webpages at $5 per 1,000 standard requests or $1 per 1,000 in fast mode, with up to five queries per request billed as one. The API supports filtering by up to 20 domains, up to 20 language codes, country, publication and last-updated date ranges, and returns 1 to 20 results per query, with official Python (perplexityai) and TypeScript (@perplexity-ai/perplexity_ai) SDKs and integrations with n8n, Haystack, Mastra and Composio. Perplexity ended Sonar Chat Completions on September 27, 2026 and directs developers wanting cited written answers to its Agent API, where the web_search tool costs $2.50 per 1,000 calls plus model token costs; the pricing page lists no free tier.", "body_md": "Perplexity's raw web search API: ranked results with titles, URLs, snippets and dates from Perplexity's own index, for grounding AI agents and RAG pipelines.\n\nThe Perplexity Search API, launched in September 2025, gives developers the raw search layer behind Perplexity: you send a query and get back ranked web results (title, URL, snippet, publication and last-updated dates) instead of a written answer. Perplexity says the results come from its own index of hundreds of billions of webpages, updated continuously. You decide what to do with the results, which makes it a building block for agents and retrieval-augmented generation (RAG) rather than a chatbot.\n\nOne request can carry up to five queries and still bills as a single request. Results can be filtered by domain (up to 20), language (up to 20 language codes), country, publication date range, last-updated date range and recency, and you can ask for between 1 and 20 results. Official SDKs exist for Python (perplexityai) and TypeScript (@perplexity-ai/perplexity_ai), and Perplexity lists integrations with n8n, Haystack, Mastra and Composio.\n\nThis is not the Sonar API. Perplexity ended Sonar Chat Completions on September 27, 2026 and now points developers who want a cited, written answer to its Agent API, which can call web search as a tool.\n\nPerplexity Search API pricing\n\nOption\n\nPrice\n\nNotes\n\nSearch (standard)\n\n$5 per 1,000 requests\n\nUp to 5 queries per request bill as one request; extracted text is not charged extra\n\nSearch (search_type: fast)\n\n$1 per 1,000 requests\n\nLower-latency mode\n\nAgent API web_search tool\n\n$2.50 per 1,000 calls\n\nPlus model token costs, when search runs inside the Agent API\n\nThe pricing page does not state a free tier for the Search API. At 10,000 searches a month, standard search costs $50 and fast search $10.\n\nPrices checked on the vendor's pricing page on November 10, 2026. See Perplexity API pricing.\n\nKey features of Perplexity Search API\n\nWhat Perplexity's own docs list:\n\nRanked web results with title, URL, snippet, date and last-updated date\n\nResults from Perplexity's own index, not a resold Google or Bing feed\n\nMulti-query: up to 5 queries in one request, billed once\n\nFilters: up to 20 domains, up to 20 languages, country\n\nDate filters: published after or before, last updated after or before, recency\n\n1 to 20 results per query; fast mode for lower latency\n\nSDKs for Python and TypeScript; integrations with n8n, Haystack, Mastra and Composio\n\nWho the Perplexity Search API is best for\n\nIt suits developers who want raw, fresh results from an independent index with precise control over language, country and dates, for example a multilingual research agent or a news-monitoring pipeline. Fast mode at $1 per 1,000 requests is among the cheapest raw search on the market.\n\nIf you want meaning-based discovery of similar pages, Exa is the stronger fit. If you want a drop-in tool for LangChain-style agent frameworks, Tavily needs less glue. If you need Google's exact results pages, use a SERP API such as SearchApi or SerpApi. Our web search API comparison puts all eight side by side.\n\nPros\n\n+Fast mode costs $1 per 1,000 requests\n\n+Own index, not a resold Google or Bing feed\n\n+Richest language, country and date filters among search APIs\n\n+Five queries per request for the price of one\n\nCons\n\n−No free tier listed on the pricing page\n\n−Returns results only; you build the answer layer yourself\n\n−No published latency figures\n\nPerplexity Search API FAQ\n\nHow much does the Perplexity Search API cost?\n\n$5 per 1,000 requests for standard search and $1 per 1,000 with the fast search type. Up to five queries in one request bill as a single request. Prices checked on the vendor's pricing page on November 10, 2026.\n\nIs the Perplexity Search API free?\n\nPerplexity's pricing page does not list a free tier for the Search API. You pay per request from the first call.\n\nWhat is the difference between the Perplexity Search API and Sonar?\n\nThe Search API returns raw ranked results that you process yourself. Sonar returned a written, cited answer; Perplexity ended Sonar Chat Completions on September 27, 2026 and now points that use case to its Agent API.\n\nDoes the Perplexity Search API use Google results?\n\nNo. Perplexity says results come from its own index of hundreds of billions of webpages, not from Google or Bing.\n\nWhich filters does the Perplexity Search API support?\n\nDomain (up to 20), language (up to 20 codes), country, published-date range, last-updated range and recency, plus 1 to 20 results per query.\n\nEnjoying this? Get one like it in your inbox each morning.\n\nSubscribe\n\none email a day · unsubscribe in two clicks · no third-party tracking\n\nStork Quadrant\n\nBecomes the API· 32/100\n\nReplaceable as a UI, but kept alive as the API the agents call.\n\n“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.”\n\nDefensibility · 0/100\n\nPhysical-world coupling\n\nRegulatory moat\n\nNetwork liquidity\n\nProprietary refreshing data\n\nHigh-trust catastrophic workflows\n\nMulti-party coordination\n\nBrand / community / taste\n\nAn LLM alone could replace\n\nReturn ranked web results with titles, URLs, and snippets — Google Search API, Bing Search API, and Brave Search API all do this today\n\nFilter results by domain, date, and language — standard capability in every major search API\n\nGround an LLM response with fresh web content — any search API plus an LLM prompt does this\n\nPower a RAG pipeline with web retrieval — commodity pattern, no Perplexity-specific advantage\n\nAgent-Readiness · 70/100\n\n·Verified MCP\n\n✓Listed on agent surfaces— anthropic_directory, cursor\n\nStop 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.\n\n→Ship an MCP server and list it on Stork — biggest single point gain (+25).", "url": "https://wpnews.pro/news/perplexity-search-api-review", "canonical_source": "https://www.stork.ai/en/perplexity-search-api", "published_at": "2026-11-12 05:47:53+00:00", "updated_at": "2026-11-12 06:22:33.883955+00:00", "lang": "en", "topics": ["ai-search", "ai-agents", "ai-tools", "developer-tools", "artificial-intelligence"], "entities": ["Perplexity", "Perplexity Search API", "Sonar API", "Agent API", "n8n", "Haystack", "Mastra", "Composio"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/perplexity-search-api-review", "markdown": "https://wpnews.pro/news/perplexity-search-api-review.md", "text": "https://wpnews.pro/news/perplexity-search-api-review.txt", "jsonld": "https://wpnews.pro/news/perplexity-search-api-review.jsonld"}}