Perplexity Fast Search trades 0.24 relevance points for much lower ranking compute

perplexity_ai · x · 2026-09-25

Perplexity detailed Fast Search, a new preset in its Search API that spends less compute on ranking than the default, aimed at day-to-day agentic tasks.

Internal tests on long-tail and broad-coverage queries show it scores only 0.24 points lower on relevance and about 3 percentage points lower on answer availability — a small quality trade for cheaper, faster search.

Related event: Perplexity Launches Fast Search, Powered by Its In-House Photon Engine(6 posts)→

Original post →

More from Infra

Infra channel →