Perplexity's Fast Search costs $1 per 1,000 requests at 200 ms, 5x cheaper than standard search

AravSrinivas · x · 2026-09-25

Perplexity CEO Arav Srinivas announced Fast Search for its Search API: setting searchtype: "fast" returns lower-latency (200 ms) results at $1 per 1,000 requests, versus $5 for standard web search — a 5x cost cut.

Docs suggest using fast for day-to-day agentic work (tool calls inside agent loops, high-volume retrieval, latency-sensitive apps) and keeping default web search for rare, difficult, or ambiguous questions. Response format is unchanged. One gotcha: Python SDK 0.43.4/0.43.5 fails validation if you pass searchtype="fast" directly — you must use extrabody.

Related event: Perplexity Launches Fast Search Powered by In-House Rust Engine Photon(11 posts)→

Original post →

More from coding & agent

coding & agent channel →