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。
A

LLM.PM

LLM.PM provides an API proxy for accessing multiple AI models through unified endpoints.

Categories

中转站
MoonshotAIKimi K2 Instruct

LLM.PM offers 3 LLM API models.

Speed benchmark average: 149 tok/s.

Avg Speed149.30 tok/s
Latency0.94 s
Total Tests15
Models3
Updated4/16/2026
Created At12/7/2025
Website

API Endpoints

  • Historical / Unverified
    https://api-proxy.me

Supported Models

ModelSpeedLatencyTests
Grokgrok-4-fast-non-reasoning
167.62 tok/s
0.90s
5
MoonshotAImoonshotai/kimi-k2-instruct
149.26 tok/s
0.49s
5
MoonshotAImoonshotai/kimi-k2-instruct-0905
131.03 tok/s
1.43s
5
OverviewPerformance3PricingTests15HealthEmbed