LogoLMSpeed
  • Home
  • Free
  • 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
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 ❤️
首页交流 QQ 群：1034193296，欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等，获取最新测速动态与反馈支持。
Harui logo

Harui

Educational institution website providing academic information and resources.

Categories

中转站
OpenAIGPT-5.1MoonshotAIKimi K2OpenAIGPT-5.3 CodexQwenQwen3 InstructDeepSeekDeepSeek V3

Harui offers 9 LLM API models.

Speed benchmark average: 99 tok/s.

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

Harui interface preview
Avg Speed99.08 tok/s
Latency3.97 s
Total Tests50
Models9
Updated4/16/2026
Created At8/13/2025
Website

API Endpoints

  • Historical / Unverified
    https://www.harui.edu.kg

Recent Test Records

TimeModelSpeedLatency
Feb 16, 03:21 AM
Gemini[V]gemini-3-pro-preview
103.25 tok/s
13.47s
Feb 16, 03:20 AM
Gemini[V]gemini-3-flash-preview
162.58 tok/s
5.82s
Feb 16, 03:19 AM
Gemini[V]gemini-2.5-flash-lite
301.65 tok/s
1.25s
Feb 16, 03:14 AM
OpenAIgpt-5.1
178.53 tok/s
6.62s
Feb 16, 03:12 AM
OpenAIgpt-5.3-codex
45.72 tok/s
4.38s
Sep 20, 01:13 PM
QwenQwen3-235B-A22B-Instruct-2507
43.21 tok/s
1.05s
Sep 2, 02:25 PM
DeepSeekDeepSeek-v3
33.73 tok/s
1.42s
Aug 28, 01:08 PM
DeepSeekDeepSeek-v3
38.01 tok/s
1.29s
Aug 1, 08:42 AM
MoonshotAIKimi-K2
49.72 tok/s
1.05s
Aug 1, 08:35 AM
DeepSeekDeepSeek-v3:3nGcHxhAPkkDukSuJhLGUX
34.42 tok/s
3.40s
OverviewPerformance9PricingTests50HealthEmbed