{"version":1,"type":"story","url":"https://digestai.news/story/perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe","json":"https://digestai.news/story/perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe.json","markdown":"https://digestai.news/story/perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe.md","slug":"perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe","headline":"Perplexity adds live web searches to Decisions API for real-time answers","summary":"Perplexity launched live web grounding in its Decisions API on November 4, 2026, letting developers fetch real-time data before the model returns structured probabilities. The feature searches up to 10 URLs per question—limited to one second per search—before appending results as evidence. It targets dynamic decisions like executive roles, software updates, or event statuses, where answers may change after training data was captured.\n\nPerplexity claims accuracy jumped from 56.4% to 97.3% on 328 true/false claims when using live grounding, though latency nearly tripled (median 366 ms vs. 139 ms). On Parallel Web Systems’ benchmark, the grounded model achieved 86% accuracy on 100 public questions, surpassing its own previous score. Searches cost $0.001 each, with a $0.10 cap for 100 questions, but retrieved evidence also counts toward token limits. The API supports Python 0.44.0+ and TypeScript 0.39.0+, though type definitions for search results are still pending.","keyPoints":["Live web grounding fetches up to 10 URLs per question before model answers, adding real-time evidence to probability outputs","Perplexity reports 97.3% accuracy on 328 claims with grounding, up from 56.4%, but latency rises to 366 ms median","Searches cost $0.001 each, capped at $0.10 for 100 questions, with retrieved data counted toward token limits"],"whyItMatters":"Real-time web grounding lets developers build systems that adapt to live data, critical for financial checks, event confirmations, or dependency tracking where stale info causes errors. The tradeoff of higher latency and costs may limit adoption to high-stakes workflows.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Perplexity","Parallel Web Systems"],"models":["pplx-decider-v1.2","pplx-decider-flash-v1.2"],"people":[]},"firstPublishedAt":"2026-11-04T21:22:03Z","updatedAt":"2026-11-04T21:22:03Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"Unite.AI","title":"Perplexity Adds Live Web Grounding to Its Decisions API","url":"https://unite.ai/perplexity-adds-live-web-grounding-to-its-decisions-api","publishedAt":"2026-11-04T21:22:03Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Perplexity adds live web searches to Decisions API for real-time answers\", 4 November 2026, https://digestai.news/story/perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe","publisher":"Digest AI","title":"Perplexity adds live web searches to Decisions API for real-time answers","datePublished":"2026-11-04T21:22:03Z","url":"https://digestai.news/story/perplexity-adds-live-web-searches-to-decisions-api-for-real-time-answe"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}