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 ❤️
Groq logo

Groq

Groq provides fast and low-cost AI inference through its LPU architecture and GroqCloud platform.

Categories

Country美国免费试用
OpenAIGPT-OSSQwenQwen3ChatGLMGLM-4.5 Air

Groq offers 5 LLM API models.

Speed benchmark average: 324 tok/s.

Groq interface preview
Avg Speed238.35 tok/s
Latency5.65 s
Total Tests45
Models5
Updated12/8/2025
Created At12/8/2025
Website

API Endpoints

  • api.groq.com
OverviewPerformance5PricingTests9Embed

Recent Test Records

TimeModelSpeedLatency
Dec 16, 11:17 AM
OpenAIopenai/gpt-oss-120b
446.44 tok/s
0.34s
Dec 12, 12:40 AM
Qwenqwen/qwen3-32b
310.21 tok/s
0.18s
Dec 12, 12:39 AM
OpenAIopenai/gpt-oss-20b
755.20 tok/s
0.47s
Dec 12, 12:38 AM
OpenAIopenai/gpt-oss-120b
466.94 tok/s
0.28s
Dec 8, 06:30 AM
Qwenfree:Qwen3-30B-A3B
18.89 tok/s
12.00s
Dec 8, 06:24 AM
Qwenfree:Qwen3-30B-A3B
23.01 tok/s
7.66s
Dec 8, 06:24 AM
Qwenfree:Qwen3-30B-A3B
19.23 tok/s
4.74s
Dec 8, 06:22 AM
ChatGLMglm-4.5-air
76.86 tok/s
8.82s
Dec 8, 06:22 AM
Qwenfree:Qwen3-30B-A3B
28.39 tok/s
16.37s