Flash

Flash·Apps & Agents·2026-11-18 20:08

Perplexity Launches Multiagent: Up to 16 Agents Cross-Check Across Models

Perplexity introduced Multiagent on Nov 17: a new effort level for its Computer platform in which a lead agent directs up to 16 supporting agents running on Claude, GPT and Gemini models, cross-checking each other's work before a single answer.

A person at a desk facing several monitors with colorful chat windows side by side in a bright workspace
AI-generated illustration

What happened

Multiagent sits at the top of Perplexity Computer's effort ladder, above Ultra, introduced in September; users select it on the web through the effort slider and can name the models they want in their query; the lead agent breaks the task down and assigns subtasks, supporting agents share evidence in real time and check each other's work, and the lead assembles a single answer.

In Perplexity's example the lead is Claude Fable 5.2, and the default supporting team is Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Carbon; Fable 5.2 and GPT-6 Astra join as supporting agents only when the user requests them or a particular task component calls for them.

Availability and pricing: web only, for Perplexity Max subscribers; Max costs $167 a month billed annually and includes 10,000 Computer credits a month; Perplexity has not disclosed how many credits a Multiagent run consumes, nor published accuracy or speed comparisons.

Key facts

  1. Launch: Nov 17, a new effort level for the Computer platform, above Ultra
  2. Scale: A lead agent plus up to 16 supporting agents
  3. Lead: Claude Fable 5.2 in the example, handling planning and task breakdown
  4. Default team: Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Carbon
  5. Method: Agents share evidence in real time and cross-check each other, with the lead assembling one answer
  6. Scope: Web only, for Max subscribers; Max is $167 a month billed annually and includes 10,000 credits a month
  7. Not disclosed: Credits per Multiagent run, plus accuracy and speed comparisons

Why it matters

a lead agent plus up to 16 supporting agents run across three vendors' flagship models and cross-check before answering; Perplexity published no accuracy or speed figures.
Useful Tap if this story helped you
Send to a friendMakes a share image for X, WeChat, Telegram and more

SourcesUnite.ai (Nov 17, 2026); AI Daily Post (Nov 18, 2026). This article is compiled from public information and does not constitute investment advice.

From HIMIAO Horizon · himiao.ai

Grab todayOpenAI Codex for Students: $100 in Free CreditsHIMIAO Picks →

Follow HIMIAO Horizon

No sign-up · Unsubscribe any time

Email

Notifications

A ping on your phone or computer when the brief is out. No email needed.

HIMIAO PicksWeekly freebies: one email every Friday, a 5-minute read

Comments

  1. Loading comments…
Ask the cat