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

Sub2API

Relay

A subscription-based API conversion platform providing unified access to multiple AI models through a single API key.

OpenAIGPT-5.2

Sub2API offers 3 LLM API models.

Speed benchmark average: 45 tok/s.

Sub2API interface preview
OverviewPerformance3HealthEmbed
Avg Speed44.95 tok/s
Latency1.62 s
Updated4/16/2026
Created At2/25/2026
Website

API Endpoints

  • api.123nhh.me

Health Check

Embed this health check image to show the provider's latest availability snapshot.

Sub2API Health Check

One-Click Speed Test

Launch speed test directly via URL parameters, automatically fill the form and start 5-round conversation speed test

baseUrl · The base URL of the OpenAI-compatible API endpoint to testapiKey · The API key for the endpointmodelId · The model ID to test
Learn more about one-click speed test
https://lmspeed.net/en?baseUrl=https%3A%2F%2Fapi.groq.com%2Fopenai%2Fv1&apiKey=gsk_xxx&modelId=llama-3.1-70b-versatile

Supported Models

Embed this supported models image to show the provider's model performance snapshot.

Sub2API Supported Models

Recent Test Records

Embed this recent tests image to show the provider's latest benchmark snapshot.

Sub2API Recent Test Records

Data as of Apr 16, 2026, 02:40 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.