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 ❤️

YUNWU API

🇨🇳CountryChinaRelay

A unified API gateway providing access to multiple large language models with direct connectivity in China.

OpenAIGPT-5 MiniOpenAIGPT-5.4 NanoDeepSeekDeepSeek V4 FlashOpenAIGPT-5 NanoOpenAIGPT-5.4 MiniOpenAIGPT-4oGeminiGemini 2.5 Pro ThinkingClaudeClaude Sonnet 4.5GeminiGemini 2.5 Flash LiteQwenQwen3 Coder Instruct

YUNWU API offers 711 LLM API models.

Speed benchmark average: 113 tok/s.

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

YUNWU API interface preview
OverviewPerformance711HealthEmbed
Avg Speed113.00 tok/s
Latency4.51 s
Updated4/22/2026
Created At8/13/2025
Recharge Rate¥0.50 per $1 quota

Features

DrawingTaskData ExportCheck-in

API Endpoints

  • Main Site
    https://yunwu.ai

    US high-defense load balancing site cluster

  • CF Site
    https://api.apiplus.org

    Global CDN, average domestic access speed

  • Domestic Server
    https://api3.wlai.vip

    Domestic high-defense server line

  • No-Login Page API Interface
    https://api.zhongzhuan.chat

    Convenient for reselling KEYs

  • Endpoint 5Historical / Unverified
    https://yunwu.zeabur.app

Login Methods

GitHubLinuxDO
Website

Data as of Apr 22, 2026, 04:11 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

Healthy
Last checked 6/5/2026, 11:34:10 AM
Latency
995ms
Day
100%
Recent availability
Week
100%
Recent availability
Month
100%
Recent availability
Latency
1340ms
7d avg: 1313ms

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-0525/25100%1267ms
2026-06-0454/54100%1383ms
2026-06-0354/54100%1509ms
2026-06-0259/59100%1308ms
2026-06-0157/57100%1333ms
2026-05-3160/60100%1231ms
2026-05-3060/60100%1217ms
2026-05-2959/59100%1295ms
2026-05-2854/54100%1223ms
2026-05-2761/61100%1331ms
2026-05-2660/60100%1268ms
2026-05-2561/61100%1240ms
2026-05-2459/59100%1249ms
2026-05-2359/59100%1211ms
2026-05-2258/58100%1369ms
2026-05-2159/59100%1252ms
2026-05-2055/55100%1357ms
2026-05-1946/46100%1370ms

Recent Incidents

No incidents reported recently

Health Check Rules

  • Check target: the provider's dedicated health check URL, or its website URL as fallback.
  • Request method: HTTP GET with automatic redirect following.
  • Healthy criteria: HTTP status code 200–399 is considered healthy; any other status or network error is unhealthy.
  • Timeout: each check has a 5-second timeout. If the server does not respond within 5 s, the check is marked as failed.
  • Frequency: health checks run periodically via an automated cron job for all providers.