LogoLMSpeed
  • Home
  • Free
  • Models
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
  • Input Price
  • Output Price
  • Reasoning
  • Coding
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️

Perplexity AI

Official

Perplexity AI offers Sonar family models and online LLM capabilities with real-time web search, accessible through developer APIs.

Perplexity AI offers 1 LLM API models.

Speed benchmark average: 104 tok/s.

OverviewPerformance1HealthEmbed
Avg Speed103.76 tok/s
Latency1.36 s
Updated4/16/2026
Created At1/18/2026
Website

API Endpoints

  • api.perplexity.ai

Data as of Apr 16, 2026, 02:17 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

Leaderboard Rankings

Health
100.0%#6/100
Healthy
Last checked 6/5/2026, 11:12:13 AM
Latency
16ms
Day
100%
Recent availability
Week
100%
Recent availability
Month
100%
Recent availability
Latency
90ms
7d avg: 106ms

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-0525/25100%99ms
2026-06-0453/53100%97ms
2026-06-0354/54100%76ms
2026-06-0259/59100%76ms
2026-06-0157/57100%119ms
2026-05-3160/60100%115ms
2026-05-3060/60100%138ms
2026-05-2959/59100%169ms
2026-05-2854/54100%55ms
2026-05-2761/61100%55ms
2026-05-2660/60100%79ms
2026-05-2560/60100%64ms
2026-05-2459/59100%134ms
2026-05-2356/56100%254ms
2026-05-2257/57100%264ms
2026-05-2159/59100%248ms
2026-05-2055/55100%284ms
2026-05-1952/52100%199ms

Recent Incidents

No incidents reported recently

Health Check Rules

  • Check target: the provider's dedicated health check URL, or its website URL as fallback.
  • Request method: HTTP GET with automatic redirect following.
  • Healthy criteria: HTTP status code 200–399 is considered healthy; any other status or network error is unhealthy.
  • Timeout: each check has a 5-second timeout. If the server does not respond within 5 s, the check is marked as failed.
  • Frequency: health checks run periodically via an automated cron job for all providers.