# Perplexity Model Watcher

> Shows which AI model really answered each Perplexity reply — with an alert when it isn't the one you picked.

Canonical page: [https://chrome-stats.com/d/perplexity-model-watcher](https://chrome-stats.com/d/perplexity-model-watcher)

## Overview

- **ID:** `perplexity-model-watcher`
- **Platform:** Firefox
- **Type:** Firefox add-on
- **Status:** Available
- **Publisher:** MaxScorpy
- **Category:** privacy-security,search-tools
- **Daily users:** 8
- **Version:** 1.0.13
- **Last updated:** 2026-08-06
- **First published:** 2025-11-22
- **Size:** 31 KB
- **Data as of:** 2026-09-09
- **Store listing:** [Firefox Add-ons Store](https://addons.mozilla.org/firefox/addon/perplexity-model-watcher/)

## Description

Perplexity routes your question to different models and doesn't always
make it obvious which one actually wrote the answer — and sometimes it
isn't the model you selected. Perplexity Model Watcher reads the real
answer and shows the model that produced it, right on the response.

WHAT IT DOES
<ul><li>A small badge on each answer names the model that actually replied,
  with human-readable names instead of raw internal identifiers.</li><li>Mismatch alert: when the model that answered differs from the one you
  requested, the badge flags it — so you know when Perplexity quietly
  fell back to a different model.</li><li>Draggable badge: move it wherever it doesn't get in your way; its
  position is remembered between sessions. Minimize it to a compact pill
  when you just want a glance.</li><li>Survives Perplexity's single-page navigation and re-renders — the
  badge re-attaches itself as you move between threads and follow-ups.</li></ul>
WHY IT'S PRIVATE
<ul><li>Runs only on <a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/d56014dfcca4976afb34ef2cfec845953a971f256c2a62e220743696c8d4053f/http%3A//perplexity.ai" rel="nofollow">perplexity.ai</a>. It reads the answer stream on the page to
  identify the model — nothing is sent anywhere.</li><li>Zero telemetry, zero analytics, zero remote calls.</li><li>Only the "storage" permission, used to remember the badge position and
  your preferences locally.</li><li>AMO data_collection_permissions disclosure is set to "none".</li></ul>
CREDITS

Built on Model Watcher by the Model Watcher contributors
(<a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/fb4a40f66c196492c09c59109ff56d54c7e7702915a66fb6ffc72fb1933198b1/https%3A//github.com/apix7/perplexity-model-watcher" rel="nofollow">https://github.com/apix7/perplexity-model-watcher</a>), used under the MIT
License. The licence and an attribution notice ship inside the add-on
(LICENSE and <a href="https://prod.outgoing.prod.webservices.mozgcp.net/v1/cf243af8f6e43ddc893d64b4bc50f39fadb6c8e5a3b3f2a5122b46c1c3a04979/http%3A//NOTICE.md" rel="nofollow">NOTICE.md</a>). What this version changes: the answer stream is read
progressively and finalised on a quiet timeout, so the badge cannot stay stuck
on "analyzing" after a follow-up, and an explicit idle/active/done phase drives
it. The draggable, minimisable badge and its remembered position come from the
original project.

LANGUAGES

Interface in Russian; model names are shown as-is (GPT, Claude, Sonar,
Grok, etc.).

## Rankings

- #36,976 — Overall
- #44 — model
- #143 — answer

## Permissions and access

### Permissions

- `storage`

### Host permissions

- `*://*.perplexity.ai/*`

### Content script matches

- `*.perplexity.ai`

## Safety

- **Risk impact:** Moderate risk impact
- **Risk likelihood:** Moderate risk likelihood

### Analysis details

- Injects scripts into web pages, which may alter or extract site contents, resulting in a substantial risk.
- This extension has low user count. Unpopular extensions may not be stable or safe.

> Some risk analysis details are omitted from this free response. [Upgrade to view the full analysis](https://chrome-stats.com/pricing).

## Similar extensions and apps

- [Perplexity Usage & Model Watcher](https://chrome-stats.com/d/perplexity-usage-model-watcher) — 4 users
- [Perplexity Model Selector](https://chrome-stats.com/d/perplexity-model-selector) — 14 users
- [Complexity | Perplexity AI Supercharged](https://chrome-stats.com/d/complexity) — 2,930 users, 4.78 / 5
- [Perplexity Sidebar](https://chrome-stats.com/d/perplexity-sidebar) — 768 users, 3.43 / 5
- [PlexiEnhancer](https://chrome-stats.com/d/plexienhancer) — 1 users, 5.00 / 5
- [Perplexity AI Sidebar Chat](https://chrome-stats.com/d/perplexity-ai-sidebar-chat) — 42 users
- [Perplexity Table of Content](https://chrome-stats.com/d/pplx-toc) — 12 users, 5.00 / 5
- [AIMetrical - AI Usage Tracker & Privacy Shield](https://chrome-stats.com/d/aimetrical) — 1 users
- [AI智能答题助手 - 专业版](https://chrome-stats.com/d/ai%E6%99%BA%E8%83%BD%E7%AD%94%E9%A2%98%E5%8A%A9%E6%89%8B-%E4%B8%93%E4%B8%9A%E7%89%88) — 51 users, 5.00 / 5
- [LM Studio Chat Assistant](https://chrome-stats.com/d/lm-studio-chat-assistant) — 18 users, 1.50 / 5
- [AI Compare - 多模型并排对比](https://chrome-stats.com/d/ai-compare-%E5%A4%9A%E6%A8%A1%E5%9E%8B%E5%B9%B6%E6%8E%92%E5%AF%B9%E6%AF%94) — 10 users
- [TextMind AI](https://chrome-stats.com/d/textmind-ai) — 1 users

---

Source: [Chrome-Stats](https://chrome-stats.com/d/perplexity-model-watcher)