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。
A

丰思理 AI

丰思理 AI delivers an OpenAI-compatible API relay with seamless access to a wide range of AI models.

Categories

中转站
GeminiGemini 3 FlashMinimaxMiniMax-M2.5

丰思理 AI offers 15 LLM API models.

API pricing is $75.00/M per token (input).

Speed benchmark average: 107 tok/s.

Avg Speed106.94 tok/s
Latency6.97 s
Total Tests60
Models6
Updated4/16/2026
Created At3/29/2026
Website

API Endpoints

  • ai.fengsili.online

Supported Models

ModelSpeedLatencyTests
Geminigoogle/gemini-3-flash:free
159.63 tok/s
5.75s
5
Geminiaskcodi/gemini-3-flash
158.39 tok/s
6.36s
25
kilo/trinity-large-thinking
107.58 tok/s
1.94s
5
xiaomi/mimo-v2-pro
57.64 tok/s
2.62s
10
Minimaxkilo/minimax-m2.5
49.09 tok/s
9.38s
5
kilo/dola-seed-2.0-pro
29.90 tok/s
14.78s
10

Leaderboard Rankings

Speed
162.6 tokens/s#14/100
Latency
2.69 s#70/100
OverviewPerformance6Pricing15Tests60HealthEmbed