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.

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
- Launch: Nov 17, a new effort level for the Computer platform, above Ultra
- Scale: A lead agent plus up to 16 supporting agents
- Lead: Claude Fable 5.2 in the example, handling planning and task breakdown
- Default team: Claude Opus 5.5, GPT-6.1 Sol and Gemini 4 Carbon
- Method: Agents share evidence in real time and cross-check each other, with the lead assembling one answer
- Scope: Web only, for Max subscribers; Max is $167 a month billed annually and includes 10,000 credits a month
- 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.
Follow HIMIAO Horizon
No sign-up · Unsubscribe any timeNotifications
A ping on your phone or computer when the brief is out. No email needed.
Comments
Related
- Nov 15Anthropic Launches Claude Meetings: Claude Joins Google Meet Calls and Works Live
- Nov 15GitHub Copilot to Retire Six Models on Dec 14, With No Successor Yet for Kimi K3
- Nov 11Anthropic Gives Claude an Office Suite: Meetings, Sheets and Whiteboards
- Oct 22Claude Code vs Codex CLI vs Gemini CLI: Three Terminal Coding Agents Compared
- Oct 8Google Launches Universal Work Agent Gemini Agent, Running Gemini and Anthropic's Claude
Today
Nov 19 Thursday- Brief
- GitHubGitHub Weekly Vol.6: 7 Projects Worth a Look This Week
Tested or read — weeklyAll →
- Quiz
- Call
Latest news
All →- Nov 19MAI Code 2 vs Claude Opus 5.5 and GPT-6.1 Sol: $0.50 Input vs $4, Promo Price Until May 2027
- Nov 18Study: Frontier Models Can Be Tricked Into Marking Civilian Targets
- Nov 18Nvidia Reaffirms Open-Source Strategy, Hugging Face Deal on Track
- Nov 17Klarna Launches AI Assistant That Shops, Books and Runs Errands
- Nov 18Palo Alto to Buy Applied Compute for $4.5 Billion in All-Stock Deal
- Nov 18NGINX2Root Exposed: Five 9.2-Severity Flaws Let Attackers Run Code on Nginx Without Logging In
™