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。
GPT Load (Shiho) logo

GPT Load (Shiho)

GPT Load is an OpenAI-compatible API load balancing service, distributing requests across multiple AI model providers.

Categories

中转站
MetaAILlama3 1MetaAILlama 4 Scout 16e InstructQwenQwen 3 CoderMetaAILlama 3 3OpenAIGPT-OSSMetaAILlama 4 Maverick 128e InstructQwenQwen 3 InstructQwenQwen 3GeminiGemini 2.5 Flash

GPT Load (Shiho) offers 10 LLM API models.

Speed benchmark average: 961 tok/s.

GPT Load (Shiho) is an API aggregator, offering models from multiple vendors.

GPT Load (Shiho) interface preview
Avg Speed960.66 tok/s
Latency1.12 s
Total Tests55
Models10
Updated4/16/2026
Created At12/7/2025
Website

API Endpoints

  • gpt-load.shiho.top

Supported Models

ModelSpeedLatencyTests
MetaAIllama3.1-8b
1976.01 tok/s
0.35s
10
MetaAIllama-4-scout-17b-16e-instruct
937.94 tok/s
0.36s
5
Qwenqwen-3-coder-480b
894.38 tok/s
0.35s
5
MetaAIllama-3.3-70b
890.30 tok/s
0.51s
5
OpenAIgpt-oss-120b
846.32 tok/s
0.70s
5
MetaAIllama-4-maverick-17b-128e-instruct
825.70 tok/s
0.41s
5
Qwenqwen-3-235b-a22b-instruct-2507
754.92 tok/s
0.45s
5
Qwenqwen-3-32b
705.04 tok/s
0.40s
5
Qwenqwen-3-235b-a22b-thinking-2507
579.82 tok/s
0.44s
5
Geminimodels/gemini-2.5-flash
180.81 tok/s
7.98s
5
OverviewPerformance10PricingTests55HealthEmbed