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。
Cerebras logo

Cerebras

Provides AI inference and training APIs leveraging Cerebras hardware for large-scale model deployment.

Categories

官方 API
MetaAILlama3 1OpenAIGPT-OSSMetaAILlama 3 3QwenQwen 3 InstructChatGLMZai GLM 4 7

Cerebras offers 5 LLM API models.

Speed benchmark average: 1216 tok/s.

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

Cerebras interface preview
Avg Speed1216.13 tok/s
Latency4.79 s
Total Tests30
Models5
Updated4/16/2026
Created At12/25/2025
Website

API Endpoints

  • api.cerebras.ai

Recent Test Records

TimeModelSpeedLatency
Jan 13, 04:32 PM
ChatGLMzai-glm-4.7
400.04 tok/s
3.57s
Dec 25, 02:21 PM
Qwenqwen-3-235b-a22b-instruct-2507
722.60 tok/s
12.10s
Dec 25, 02:12 PM
Qwenqwen-3-235b-a22b-instruct-2507
737.18 tok/s
12.09s
Dec 25, 02:06 PM
MetaAIllama3.1-8b
2142.09 tok/s
0.19s
Dec 25, 02:06 PM
OpenAIgpt-oss-120b
1920.13 tok/s
0.54s
Dec 25, 02:02 PM
MetaAIllama-3.3-70b
1374.74 tok/s
0.25s

Leaderboard Rankings

Health
100.0%#28/100
OverviewPerformance5PricingTests30HealthEmbed