Perplexity launches Monitor API for automated web-change tracking
Perplexity's Monitor API launches Nov. 16, 2026, with web monitoring at $1 per 1,000 successful runs, signed webhooks and strict data-retention limits for enterprises.
By Olivia Hart
4 min read

What's News
- Monitor API launched November 16, 2026.
- Web monitoring costs $1 per 1,000 successful runs.
- Page monitors cover 1 to 10 URLs, priced at $1 per 1,000 URLs fetched.
- Checks can run as often as every 15 minutes; run history lasts 90 days.
- Zero-data-retention organizations cannot create, resume or run monitors.
By Olivia Hart
Perplexity launched the Monitor API on November 16, 2026, with web monitoring priced at $1 per 1,000 successful runs. Perplexity says the service supports scheduled topic searches and webpage-change tracking, with filtered updates delivered through the API or signed webhooks. The company makes Monitor available through the API and API Console.
What can Monitor watch?
Perplexity says Monitor combines recurring checks, saved state, duplicate removal and change detection in one developer service. The company says teams often assemble those components themselves to watch for account funding, breaking API changes or competitor pricing updates.
Perplexity supports two modes:
- Search monitors run a single query to find new web and news results about a topic, company or question.
- Page monitors watch 1 to 10 known URLs, including pricing pages, changelogs and policy pages. Perplexity does not allow the modes to be combined.
Perplexity says Page monitoring creates an initial baseline and returns a text diff on later runs, isolating what changed. The company designed the service to pass relevant developments into applications and agents for downstream work.
Takeaway: Monitor bundles the machinery, but developers must choose either broad searches or specific pages.
How does Perplexity filter updates?
Perplexity Decider, a general-purpose classifier, returns “probability distributions over possible answers” rather than generating free-form responses, according to the company. Perplexity says Decider checks relevance, source legitimacy, new information and freshness for Search results.
For Page changes, Decider checks whether the change matters to the monitor’s optional plain-language goal. Perplexity sends an update only when every applicable check meets its threshold. Developers can adjust each threshold independently and revise the goal without recreating the monitor, the company says.
Perplexity includes a confidence score in updates. Search updates also carry a title and snippet, while metadata can route an event to a particular user, workspace or agent.
Takeaway: Threshold settings, not raw detection, determine which changes reach an application or agent.
What do schedules and delivery cost?
Perplexity allows checks every 15 minutes, hourly, daily, weekly or on a custom cron schedule. The first run becomes due immediately at creation, and developers can request manual runs or pause and resume monitors.
For Page monitors, the company charges $1 per 1,000 URLs fetched because one run can retrieve several pages. Perplexity defines a run as one scheduled or on-demand check and uses the same API key as the Search, Context and Agent APIs.
At one fetched URL per check, $1 covers 1,000 URLs; a 10-URL monitor reaches the same cost after 100 runs.
Perplexity makes webhooks optional because stored run results can be read through the API. Signed webhooks retry transient delivery failures automatically, but delivery is at least once and events can arrive out of order.
Receiving systems must deduplicate events and changes by their identifiers, according to the company’s documentation. Perplexity retains run history for 90 days.
Deleting a monitor removes its run history and saved state while stopping future scheduling. Perplexity says saved state identifies new findings and page changes across checks and deduplicates results.
Takeaway: The $1 rate is not a monthly cap, and at-least-once delivery leaves duplicate handling to customers.
Who can use Monitor under retention rules?
Organizations requiring zero data retention cannot create, resume or run monitors, according to Perplexity. The restriction blocks their use of the service’s central scheduling and state functions rather than merely limiting stored run results. Perplexity calls the exclusion material for enterprises with strict data-handling requirements.
Repeated source or webhook failures, insufficient credits or organizational policy can trigger an automatic pause, the company says.
Takeaway: Zero-retention organizations cannot use Monitor, while failures, exhausted credits or policy can still pause other monitors.
How strong is Perplexity’s evaluation evidence?
Perplexity reports that Monitor delivered “the most fresh, relevant results across the widest topic range” in an eight-hour evaluation against other Search API providers. The company says many results did not appear from any other provider tested.
Perplexity says the evaluation covered 60 topics drawn from production Search API queries, including company news, technology releases and regulation. A separate model assessed relevance and publication timing.
Perplexity does not name the competing providers in the published account or disclose an error rate. The company also provides no audited comparison, leaving the result a favorable claim rather than proof of an industry-wide advantage.
Takeaway: The eight-hour test supports Perplexity’s case for breadth, but it does not establish comparative accuracy.
How do changes reach business workflows?
Perplexity describes funding announcements, executive hires and product launches triggering account research, CRM updates and outreach through connected go-to-market agents. Equity research monitors can follow earnings releases, guidance changes, acquisitions and adverse media, the company says. Regulatory workflows can summarize and route changes on regulator websites to compliance teams, according to Perplexity.
Perplexity says Monitor gives agents a persistent input stream for external change. The company identifies filtered detection linked to workflow execution as the enterprise advantage.
Takeaway: The business case rests on triggering business workflows, not merely reporting that a page changed.
Source: unite.ai
More from Olivia Hart
Show full bio
Staff writer covering people, launches and day-to-day practice in entrepreneurship, startups and venture funding at Business Bearings.
2,205 articles