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 ❤️
N

紫脑喵

Provides API access to AI models including Claude, GPT, and Gemini, with support for chat, image generation, and coding tools.

GeminiGemini 2.5 Flash LiteGeminiGemini 2.5 Flash Lite ThinkingDeepSeekDeepSeek V3.2MinimaxMiniMax-M2.1

紫脑喵 offers 4 LLM API models.

API pricing per token ranges from $0.010 to $75.00/M (input).

Speed benchmark average: 157 tok/s.

紫脑喵 interface preview
Avg Speed157.45 tok/s
Latency5.65 s
Total Tests20
Models4
Updated4/11/2026
Created At3/10/2026
Website

API Endpoints

  • newapi.aisonnet.org
OverviewPerformance4Pricing213Tests4Embed

Supported Models

ModelSpeedLatencyTests
Geminigemini-2.5-flash-lite-preview-09-2025
345.45 tok/s
2.47s
5
Geminigemini-2.5-flash-lite-preview-09-2025-thinking
203.81 tok/s
7.20s
5
DeepSeekdeepseek-v3.2
53.05 tok/s
3.36s
5
Minimaxminimax-m2.1
27.49 tok/s
9.56s
5