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 ❤️
A

专盾Procdn

Relay

专盾Procdn provides an OpenAI-compatible API relay with CDN acceleration for accessing AI language models.

QwenQwen3GeminiGemini 2.5 Pro Non ThinkingDeepSeekDeepSeek V3

专盾Procdn offers 4 LLM API models.

Speed benchmark average: 87 tok/s.

专盾Procdn interface preview
OverviewPerformance4HealthEmbed
Avg Speed87.44 tok/s
Latency15.85 s
Updated4/16/2026
Created At8/13/2025
Website

API Endpoints

  • api2.dashi.party

Supported Models

ModelSpeedLatencyTests
QwenQwen/Qwen3-235B-A22B
116.62 tok/s
21.27s
30
Geminigemini-2.5-pro-non-thinking
37.42 tok/s
11.48s
9
DeepSeekPro/deepseek-ai/DeepSeek-V3
45.96 tok/s
2.69s
5
DeepSeekPro/deepseek-ai/DeepSeek-V3-G
43.89 tok/s
4.37s
5

Data as of Apr 16, 2026, 02:31 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.