← All providers
Docs·API
Perplexity AI

Perplexity AI

Search

Sonar — LLM-native web search API for agents

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

Operational

All systems responding normally

Last checked 15/07/2026, 11:18:22 pm

225ms response

Uptime History100.00% uptime
2026-07-11Today

Uptime

100.00%

Avg Latency

205ms

P95 Latency

262ms

Fastest

71ms

Checks

150

Response Time

Last 60 checks
71ms min205ms avg405ms 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)

ModelTaskContextVisionToolsJSON
Sonar Pro

LLM-native web search. Not an LLM itself.

llm————

Recent Checks

Showing last 15
Operational
225ms15 July, 11:18 pm
Operational
81ms15 July, 10:42 pm
Operational
212ms15 July, 10:07 pm
Operational
405ms15 July, 09:37 pm
Operational
131ms15 July, 08:59 pm
Operational
224ms15 July, 08:12 pm
Operational
117ms15 July, 07:23 pm
Operational
247ms15 July, 06:37 pm
Operational
233ms15 July, 05:40 pm
Operational
256ms15 July, 04:56 pm
Operational
215ms15 July, 03:59 pm
Operational
237ms15 July, 03:09 pm
Operational
145ms15 July, 02:02 pm
Operational
350ms15 July, 12:50 pm
Operational
88ms15 July, 11:48 am

API Quick Access

HealthLatencyFreshnessPricingModels

Other Search Providers

Tavily

Tavily

AI-optimised web search built for LLM agents

Brave Search API

Brave Search API

Independent web index — no Google/Bing dependency

Exa AI

Exa AI

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

Serper

Serper

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

Visit Perplexity AI →View Pricing← All Providers