Perplexity Multiagent
Up to 16 AI agents working as one team
At a glance
- Category
- AI Agents
- Product type
- Multi-agent assistant
- Status
- Available (new effort level for Comet)
- Launch
- November 17, 2026
- Pricing
- Not publicly verified
Overview
On November 17, 2026 Perplexity launched Multiagent, a new effort level for its Comet agent platform: a lead agent (Claude Fable 5.2) splits work across as many as 16 agents running on different models.
Why it matters
Launched Nov 17: a lead agent splitting work across up to 16 model-diverse sub-agents — a high-profile step toward consumer-grade coordinated multi-agent systems.
Problem it solves
How it works
Key capabilities
- Lead agent orchestration
- Up to 16 parallel agents
- Model-diverse sub-agents
- Launched Nov 17
Integrations
Pricing & plans
Not independently verified in this research pass — see the official pricing page for current plans.
View official pricing ↗Use cases
- Deep research
- Complex multi-step tasks
- Parallelized agent workflows
Who should use it
- • Researchers and analysts running deep multi-step tasks
- • Power users wanting parallelized agent work
May not suit
- • Simple single-shot questions where one model is faster
Independent editorial analysis
Strengths & limitations
Strengths
- +Parallelizes complex tasks across many agents
- +Model-diverse sub-agents (Opus, GPT, Gemini)
- +Consumer-accessible, not just a developer SDK
Limitations
- –Multi-agent runs can be slower and costlier per task
- –Quality depends on task decomposition; not verified across domains
Editorial assessment by aitoolslist.ai, distinct from vendor claims.
Alternatives & comparison
| Option | Positioning | When to prefer |
|---|---|---|
| Perplexity Multiagent | Up to 16 AI agents working as one team | Featured pick this edition |
| ChatGPT agents | Agentic assistant | For a tightly integrated OpenAI ecosystem. |
| Google ADK | Developer agent framework | When you need to build custom multi-agent systems. |
| Manus | Autonomous task agent | For hands-off end-to-end task completion. |
Comparison reflects positioning; pricing and spec parity are not independently verified across all options.
Edition intelligence · AI Agents
Why it was selected this edition
The edition's highest-profile AI-agent launch (Nov 17), notable for coordinated model-diverse multi-agent execution.
Claim-level transparency
Research & verification
Our verification scope is explicit. A checked website does not mean the whole product has been independently audited.
| Official website | Confirmed | https://www.perplexity.ai |
| Launch / announcement | Confirmed | |
| Product capabilities | Cross-checked | From cited sources |
| Pricing | Unverified | See official pricing page |
| Performance benchmarks | Unavailable |