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 ❤️
W

Harui

Relay

Harui appears to expose an OpenAI-compatible API gateway at www.harui.edu.kg, although the public site content is unstable and does not currently provide a clear provider landing page.

OpenAIGPT-5.1OpenAIGPT-5.3 CodexQwenQwen3 InstructDeepSeekDeepSeek V3MoonshotAIKimi K2

Harui offers 9 LLM API models.

Speed benchmark average: 63 tok/s.

Harui is an API aggregator, offering models from multiple vendors.

Harui interface preview
OverviewPerformance9HealthEmbed
Avg Speed62.75 tok/s
Latency2.44 s
Updated4/26/2026
Created At8/13/2025
Website

API Endpoints

  • www.harui.edu.kg
Unhealthy
Last checked 6/5/2026, 9:04:20 AM
Day
0%
Recent availability
Week
0%
Recent availability
Month
0%
Recent availability
Latency
—

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-050/200%—
2026-06-040/540%—
2026-06-030/540%—
2026-06-020/590%—
2026-06-010/570%—
2026-05-310/600%—
2026-05-300/600%—
2026-05-290/590%—
2026-05-280/540%—
2026-05-270/610%—
2026-05-260/600%—
2026-05-250/610%—
2026-05-240/590%—
2026-05-230/590%—
2026-05-220/580%—
2026-05-210/590%—
2026-05-200/550%—
2026-05-190/510%—

Recent Incidents

TimeStatus CodeLatencyError
6/5/2026, 9:04:20 AM——fetch failed
6/5/2026, 8:34:22 AM——fetch failed
6/5/2026, 8:04:19 AM——fetch failed
6/5/2026, 7:34:06 AM——fetch failed
6/5/2026, 7:14:07 AM——fetch failed
6/5/2026, 6:44:03 AM——fetch failed
6/5/2026, 6:14:00 AM——fetch failed
6/5/2026, 5:43:59 AM——fetch failed
6/5/2026, 5:14:06 AM——fetch failed
6/5/2026, 4:44:14 AM——fetch failed
6/5/2026, 4:14:03 AM——fetch failed
6/5/2026, 3:54:00 AM——fetch failed
6/5/2026, 3:23:58 AM——fetch failed
6/5/2026, 2:54:02 AM——fetch failed
6/5/2026, 2:24:04 AM——fetch failed
6/5/2026, 1:53:56 AM——fetch failed
6/5/2026, 1:23:59 AM——fetch failed
6/5/2026, 12:53:54 AM——fetch failed
6/5/2026, 12:34:01 AM——fetch failed
6/5/2026, 12:13:58 AM——fetch failed

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.

Data as of Apr 26, 2026, 07:38 AM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.