Perplexity announces hybrid AI system that decides what runs locally or in the cloud
Perplexity just shipped an orchestrator that automatically routes AI tasks between your device and the cloud. Latency down, costs optimized, no user friction.

Why it matters
Hybrid inference is becoming table stakes for AI product strategy. This move signals how real-world AI deployment is shifting from cloud-only to intelligent local-cloud routing, directly impacting inference costs and user experience for founders building on-device features.
The key facts
4 to knowPerplexity launches hybrid orchestrator system
Automatically routes tasks between local device and cloud models
Combines on-device and cloud AI processing
Announced June 3, 2026
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Perplexity has announced an orchestrator that combines AI models running on your own computer with powerful cloud models and automatically decides which task gets processed where.