ProductPerplexityConfirmed
Story 2 of 15 in the Monday 16 November editionPerplexity launches Monitor API for scheduled web and page webhooks
Available through the Perplexity API and API Console with existing Search and Agent API keys, billing $1 per 1,000 search runs or $1 per 1,000 fetched page URLs.

Perplexity introduced the Perplexity Monitor API on 17 November 2026 across the Perplexity API and API Console, sharing the same API key used for its Search, Context and Agent APIs. Priced at $1 per 1,000 succeeded search runs ($0.001 per run) or $1 per 1,000 counted URLs fetched in page runs ($0.001 per URL), the service replaces custom polling scripts with managed web topic and page-diff watchers.
Perplexity Decider filtering, 24 KiB page diffs and v1-signed webhook retries
Monitors run on fixed intervals such as every 15 minutes, hourly, daily or weekly, on custom cron expressions or on demand, and support two target modes: Search monitors (queries up to 1,000 characters, up to 20 results and optional 20-host include or exclude domain filters) and Page monitors tracking text snapshots across up to 10 public URLs. Developers can attach and edit a plain-language goal at any time without recreating the monitor.
Before firing an event, Perplexity Decider grades Search candidates against four configurable thresholds (relevance, source legitimacy, novelty and time-window freshness) and scores Page unified diffs (truncated cleanly at 24 KiB with full added and removed line counts) for goal meaningfulness, returning a 0-to-1 confidence score. Updates arrive over v1-signed webhooks (monitor.changes.detected, monitor.run.completed and monitor.paused) with seven automatic backoff retries spanning roughly 17.6 hours on timeouts, 429s or 5xx responses. Organisations enforcing zero data retention cannot create or run monitors.
Key details
- Billing rates
- $1 per 1,000 succeeded Search runs ($0.001/run); $1 per 1,000 counted URLs fetched in Page runs ($0.001/URL)
- Target limits
- Search query up to 1,000 chars (1-20 max_results, 20 include/exclude domains); Page mode up to 10 public URLs
- Page diff format
- Unified diff hunks with chg_ ID, RFC 3339 timestamps, line counts and 24 KiB truncation cap
- Webhook signing and retries
- webhook-timestamp + base64 v1 webhook-signature; 7 retries (5s, 5m, 30m, 2h, 5h, 10h) over ~17.6 hours
Release details & context
Eight-hour production benchmark and automatic pause safeguards
In an eight-hour internal evaluation across 60 production Search API topics spanning technology releases, corporate filings and regulatory updates, Perplexity reported that Monitor surfaced fresher goal-relevant items across a wider share of topics than competing Search API providers, including updates missed by every rival endpoint.
To prevent runaway spend or broken downstream receivers, the service automatically pauses a monitor and emits a monitor.paused event under four conditions: repeated receiver failures failing to return HTTP 2xx within 10 seconds (webhook_failing), persistent target read errors (source_failing), depleted account balance (insufficient_credits) or organisation policy blocks such as enabling zero data retention.
Common questions
Can developers modify a Perplexity Monitor’s relevance goal without losing its baseline history?
Yes, both the plain-language relevance goal and per-check confidence thresholds can be updated in place via the API or API Console without recreating the monitor or resetting deduplication state.
Does the Perplexity Monitor API work on accounts configured for zero data retention?
No, because cross-run deduplication and page snapshot diffing require persisted state, organisations requiring zero data retention are blocked from creating, resuming or executing monitors.
Sources
- PrimaryIntroducing Perplexity’s Monitor APIpplx.ai
- OfficialMonitor API Overview - Perplexity Docsdocs.perplexity.ai
- OfficialPerplexity API Platform Pricingdocs.perplexity.ai
- OfficialPage Monitoring - Perplexity Docsdocs.perplexity.ai
Perplexity release timeline (10 launches tracked)
- Perplexity introduces Teammates personal agent workforce for Max subscribers on the web
Perplexity launched Teammates for Max subscribers on the web, deploying persistent personal agents that coordinate across Computer tasks, memory and Slack.
- Perplexity red-teams 12 frontier models against its SPACE virtual-machine agent sandbox
Perplexity red-teams 12 frontier models on its SPACE VM sandbox, logging zero escapes while general models beat cyber-tuned variants.
- Perplexity releases open-weight Decider v1.3 models with locate spans
Perplexity releases Apache-licensed pplx-decider-v1.3 and Flash v1.3 on Hugging Face, OpenRouter and its API with character-span extraction via locate.
- Perplexity brings Teammates to the Perplexity Mac app for Max users
Perplexity rolls out Teammates in the Perplexity Mac app for Max subscribers to run solo or multi-agent QA, support and research tasks.

