Docs·API

Perplexity AI

Sonar — LLM-native web search API for agents

perplexity.ai ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 14/09/2026, 10:35:20 am

210ms response

Uptime History100.00% uptime

2026-09-12Today

Uptime

100.00%

Avg Latency

329ms

P95 Latency

411ms

Fastest

194ms

Checks

150

Response Time

Last 60 checks

194ms min329ms avg863ms max

💰 Pricing

sonar-pro

Input: $3/1MOutput: $15/1M

sonar: $1/$1. +$5/1000 search requests for pro

⚡ Rate Limits

standard

RPM: 50

Standard tier. Enterprise: custom.

🤖 Models (1)

Model	Task	Context	Vision	Tools	JSON
Sonar Pro LLM-native web search. Not an LLM itself.	llm	—	—	—	—

Recent Checks

Showing last 15

Operational

210ms14 Sept, 10:35 am

Operational

241ms14 Sept, 09:52 am

Operational

238ms14 Sept, 09:42 am

Operational

289ms14 Sept, 09:34 am

Operational

335ms14 Sept, 09:20 am

Operational

210ms14 Sept, 09:09 am

Operational

315ms14 Sept, 08:53 am

Operational

402ms14 Sept, 08:42 am

Operational

336ms14 Sept, 08:34 am

Operational

249ms14 Sept, 08:23 am

Operational

304ms14 Sept, 07:52 am

Operational

298ms14 Sept, 07:42 am

Operational

411ms14 Sept, 07:34 am

Operational

318ms14 Sept, 07:20 am

Operational

300ms14 Sept, 07:09 am

API Quick Access

Health Latency Freshness Pricing Models

Other Search Providers

Tavily

AI-optimised web search built for LLM agents

Brave Search API

Independent web index — no Google/Bing dependency

Exa AI

Neural web search API — meaning-based, not keyword-based

Serper

Google Search API for agents — fast, cheap, no scraping

Visit Perplexity AI →View Pricing ← All Providers