Skip to content
NewA calmer, faster ZeroHour

Perplexity launches Monitor API to watch the web on a schedule

Original title: Perplexity's new Monitor API turns web search from a one-off query into a nonstop watchdog

The Decoderby Jonathan Kemper ()3 min read1
AI summary · x-ai/grok-4.7Summaries by Vani AI

Web monitors cost $1 per 1,000 runs and page monitors $1 per 1,000 URLs; updates fire only after a decision model clears every threshold.

Perplexity released a Monitor API that runs scheduled web or page checks and notifies apps and agents by signed webhook when its decision model judges a change relevant. Web monitors search on a schedule; page monitors track up to 10 URLs and return text diffs against a stored baseline. Schedules range from every 15 minutes to weekly or a custom cron. The API is available now and uses the same key as the Search, Context, and Agent APIs.

Unconfirmed: Perplexity describes the comparison figures as early internal results, not an independent benchmark.

Key facts
  • A single request sets the search query, goal, schedule, and webhook URL.
  • Web results must pass relevance, credibility, novelty, and timeliness checks.
  • Perplexity says an eight-hour internal test returned 63 fresh pages versus 20 for Firecrawl.
  • Developers can pause, resume, or manually trigger monitors through the API or console.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

3 min read at the-decoder.com

Perplexity is launching a Monitor API that searches the web on a schedule and alerts agents via webhook only when relevant changes occur. Its own decision model filters out unimportant results. For Perplexity, the API is part of a broader strategy to stand out from an increasingly interchangeable chatbot business through developer tools.

The Decoder

By Jonathan Kemper · the-decoder.com

Read the full article at The Decoder

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.