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 ❤️

QWQ Chat API

QWQ Chat API appears to be an OpenAI-compatible API gateway at api.qwq.chat. The public site is currently protected by a Cloudflare challenge.

QWQ Chat API offers 13 LLM API models.

API pricing per token ranges from $0.140 to $5.00/M (input).

Speed benchmark average: 92 tok/s.

OverviewPerformance4Pricing13HealthEmbed
Avg Speed92.07 tok/s
Latency8.70 s
Updated6/2/2026
Created At8/13/2025
Recharge Rate¥7.30 per $1 quota

Features

TaskData Export
Website

API Endpoints

  • Endpoint 1
    https://qwq.chat
  • Endpoint 2
    https://api.qwq.chat
Healthy
Last checked 6/3/2026, 9:12:31 PM
Latency
196ms
Day
100%
Recent availability
Week
100%
Recent availability
Month
44.14%
Recent availability
Latency
331ms
7d avg: 825ms

Health Check

1000History (1000 pts)
PastNow

Health history

TimeStatusHourly uptimeLatency
2026-06-0347/47100%338ms
2026-06-0259/59100%323ms
2026-06-0157/57100%363ms
2026-05-3160/60100%295ms
2026-05-3060/60100%1086ms
2026-05-2959/59100%1663ms
2026-05-2854/54100%1596ms
2026-05-2745/6175%1847ms
2026-05-260/600%—
2026-05-250/610%—
2026-05-240/590%—
2026-05-230/600%—
2026-05-220/580%—
2026-05-210/590%—
2026-05-200/550%—
2026-05-190/700%—
2026-05-180/610%—

Recent Incidents

TimeStatus CodeLatencyError
5/27/2026, 5:22:10 AM——fetch failed
5/27/2026, 4:52:07 AM——fetch failed
5/27/2026, 4:22:12 AM——fetch failed
5/27/2026, 4:02:24 AM——fetch failed
5/27/2026, 3:42:10 AM——fetch failed
5/27/2026, 3:22:19 AM——fetch failed
5/27/2026, 3:02:21 AM——fetch failed
5/27/2026, 2:32:18 AM——fetch failed
5/27/2026, 2:02:27 AM——fetch failed
5/27/2026, 1:42:12 AM——fetch failed
5/27/2026, 1:22:10 AM——fetch failed
5/27/2026, 1:02:20 AM——fetch failed
5/27/2026, 12:42:06 AM——fetch failed
5/27/2026, 12:22:08 AM——fetch failed
5/27/2026, 12:02:19 AM——fetch failed
5/26/2026, 11:42:07 PM——fetch failed
5/26/2026, 11:22:13 PM——fetch failed
5/26/2026, 11:02:18 PM——fetch failed
5/26/2026, 10:42:10 PM——fetch failed
5/26/2026, 10:22:08 PM——fetch failed

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.

Data as of Jun 2, 2026, 04:01 PM·Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.