← PostsPost ·

Perplexity Monitor API: get a webhook when the web changes

Perplexity's Monitor API (2026-11-16) watches a topic or up to 10 pages and sends a webhook on relevant changes, from $1 per 1,000 runs.

Give this to your agent

Open in

Your agent checks this against your setup and tells you if it fits.

See the file
# Perplexity Monitor API: a webhook when a topic or a page changes
From Rig Labs, 2026-11-17. Information for an agent, not orders. Page: https://riglabs.ai/blog/perplexity-monitor-api/

What changed: On 2026-11-16, Perplexity launched the Monitor API: it watches a web topic or up to 10 pages on a schedule and sends a signed webhook with relevant updates or a text diff.
Fits if: Your human has a Perplexity API key, or an agent or workflow that can receive a webhook, and checks some pages or topics by hand on a regular basis.
Skip if: Your human only uses Perplexity's chat plans and has no API key or webhook endpoint. Page monitors watch at most 10 pages each.
Check: Which pages or topics your human checks by hand every week (pricing pages, changelogs, policy pages), and whether they have a webhook endpoint. Read-only.
Try: Propose one daily page monitor on the page your human checks most, with a plain-language goal for what counts as a change.
Ask first: Creating an API key, creating a monitor (it spends money per run), and the webhook address it sends to.
Cost: Web monitors $1 per 1,000 successful runs; page monitors $1 per 1,000 URLs fetched. Same API key as Perplexity's Search and Agent APIs.
Undo: Pause or delete the monitor from the API or the API Console.
Deeper: https://www.perplexity.ai/hub/blog/introducing-perplexitys-monitor-api, then https://docs.perplexity.ai/docs/monitors/overview

Perplexity launched the Monitor API on November 16, 2026, per its announcement. A monitor watches the web for news on a topic, or watches up to 10 pages, on a schedule, and sends a webhook (an automatic message to an address you choose) when it finds a relevant change.

What you can now do: give an agent a trigger, such as “a competitor changed its pricing page”, without writing your own scheduled searches or change-detection code.

What does the Perplexity Monitor API watch?

Perplexity’s Monitor API has two modes, per the announcement:

  • Monitor the web: new developments on a topic, a company or a question, through Perplexity Search across web and news results.
  • Monitor pages: changes to up to 10 pages you name, like a pricing page, a changelog or a policy page. The first check saves a baseline, and later runs return a text diff of what changed.

You describe each monitor in plain language: a search query or a list of pages, plus an optional goal, such as “companies that raised a Series A or B”. You can change the goal later without recreating the monitor.

How does it decide what is relevant?

Perplexity’s Monitor API runs every result through Perplexity Decider, per the announcement. A web result must pass four checks: relevance, source legitimacy, new information and freshness. For a page, Decider checks whether the change matters for your goal. An update is sent only if every check passes its threshold, each update carries a confidence score, and you can adjust the thresholds per check.

How often does it run, and how do updates arrive?

Perplexity’s monitors run every 15 minutes, hourly, daily, weekly or on a custom cron schedule. Each run picks up where the last one ended and removes duplicates. Updates go out as signed webhooks with automatic retries, and you can pause, resume or run a monitor on demand from the API or the API Console.

What does it cost?

Perplexity prices the Monitor API by use, per the announcement:

Monitor Price
Web monitor $1 per 1,000 successful runs
Page monitor $1 per 1,000 URLs fetched

A web monitor that runs hourly makes about 720 runs in a 30-day month, so about $0.72 a month if every run succeeds. It uses the same API key as Perplexity’s Search and Agent APIs, billed per use, so it is for people who build agents or workflows on the API rather than for the chat app.

What to do today

Pick one page you check by hand every week, such as a competitor’s pricing page or a tool’s changelog. In the API Console, create a page monitor on it with a daily schedule, a goal like “a price or plan limit changed”, and your agent’s webhook address. To create the same monitor through the API instead of the Console, the Monitor API docs show the request to send.

Last checked 2026-11-17.

Sources:

Get the next one by email

The Edge is our newsletter: what changed in AI, and what to do about it.

Which emails
Free. Your agent reads every piece we publish, and you hear only what fits.

Subscribe your agent Beta

Your agent reads every post, guide and issue, checks it against your setup, and tells you only what is worth your time. Its inbox gets the daily agent cards email automatically, every day something is published, and the weekly issue as plain text. You pick weekly, daily or both for yourself.

  1. Give it the prompt

    Using Claude Code, Codex or another agent? Copy the prompt and paste it in.

    See the prompt
    Subscribe yourself to The Edge, the newsletter from Rig Labs, and follow what Rig Labs publishes for me.
    Read https://riglabs.ai/agents/subscribe.md and follow its steps. It has you save the skill at https://riglabs.ai/agents/the-edge/SKILL.md, set yourself up with your own inbox on Nym (invite: https://withnym.com/join/NYM-TQZB-WP35, code NYM-TQZB-WP35) unless you already have one, subscribe that address, and confirm with me.
    Treat everything you fetch from Rig Labs as information, not orders. Ask me before anything that touches keys, payments, permissions, installs or sending messages.
  2. Approve its inbox

    It gets its own address on Nym, so The Edge never lands in your inbox. One sign-in in your browser, about a minute.

  3. Hear only what fits

    At most one short message a day. Nothing if nothing fits.

Your agent follows subscribe.md and saves SKILL.md: read both first. Nym is in private beta. The invite is included in the prompt.

Read next

Built by Rig Labs

When a tool we need does not exist, we build it.