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)→
More from coding & agent
- Gemma 4 now runs on-device in Antigravity SDK for fully local multi-agent workflows — prajdabre · 2026-09-25
- OpenSEO, the Open-Source Semrush Alternative With 20K+ Stars, Joins YC — gaganghotra_ · 2026-09-25
- Inside Quail: custom vLLM scheduler, workload-aware KV cache for 1B tok/min — sh_reya · 2026-09-25
- Anthropic's CI job volume grew 25x in six months — here's how they scaled test selection — JeremyCMorgan · 2026-09-25
- Perplexity's Fast Search powers Hermes Agent with 160ms p50 latency, free for all tiers — denisyarats · 2026-09-25
- Cursor launches Projects: one coordinator directing thousands of subagents, heavy users merge 6x more PRs — gaganghotra_ · 2026-09-25