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。
AIHubMix logo

AIHubMix

A unified API gateway providing access to multiple large language models and AI services through a single interface.

Categories

中转站
GeminiGemini 2.0 FlashGeminiGemini 3 FlashDeepSeekDeepSeek V3GeminiGemini 3.1 ProChatGLMZai GLM 4 7DoubaoDoubao Seed 1 8QwenQwen2.5 InstructDeepSeekDeepSeek V3.2

AIHubMix offers 232 LLM API models.

Speed benchmark average: 66 tok/s.

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

AIHubMix interface preview
Avg Speed66.47 tok/s
Latency13.29 s
Total Tests75
Models14
Updated4/18/2026
Created At12/7/2025
Versionv1.0.0
Online SinceApr 17, 2026, 05:44 PM
Website

API Endpoints

  • Historical / Unverified
    https://aihubmix.com

Login Methods

GitHub

Supported Models

ModelSpeedLatencyTests
Geminigemini-2.0-flash
163.32 tok/s
0.59s
5
Geminigemini-3-flash-preview
155.47 tok/s
7.06s
5
Grokgrok-4-1-fast-non-reasoning
108.12 tok/s
1.01s
5
Geminisophnet-mimo-v2-flash
104.20 tok/s
1.22s
5
DeepSeekDeepSeek-V3-Fast
79.64 tok/s
0.89s
5
Geminigemini-3.1-pro-preview
69.84 tok/s
25.06s
5
ChatGLMzai-glm-4.7
47.80 tok/s
41.22s
5
Doubaodoubao-seed-1-8-251228
46.32 tok/s
23.71s
5
Qwenalicloud-qwen3-max-2026-01-23
40.59 tok/s
1.26s
5
ChatGLMcoding-glm-5.1
32.33 tok/s
41.57s
5
QwenQwen/Qwen2.5-72B-Instruct
32.01 tok/s
1.03s
10
DeepSeekDeepSeek-V3
29.76 tok/s
1.44s
5
DeepSeekdeepseek-v3.2
27.93 tok/s
1.52s
5
ChatGLMcoding-glm-4.7-free
27.71 tok/s
50.72s
5

Available Models

218 models available (last updated: 4/16/2026)

AiHubmix-Phi-4-mini-reasoningMicrosoftAiHubmix-Phi-4-reasoningMicrosoftByteDance-Seed/Seed-OSS-36B-InstructDoubaoDeepSeek-R1DeepSeekDeepSeek-V3-FastDeepSeekDeepSeek-V3.1-FastDeepSeekDeepSeek-V3.1-TerminusDeepSeekDeepSeek-V3.1-ThinkDeepSeekKimi-K2-0905Moonshot AIQwen/QwQ-32BQwenQwen/Qwen2.5-VL-32B-InstructQwenQwen/Qwen2.5-VL-72B-InstructQwenaihub-Phi-4Microsoftaihub-Phi-4-multimodal-instructMicrosoftaihubmix-routerOpenAIanthropic-opus-4-6Anthropicbai-qwen3-vl-235b-a22b-instructQwenbaidu/ERNIE-4.5-300B-A47BBaiducc-MiniMax-M2Minimaxcc-deepseek-v3.1DeepSeek
Showing 20 of 218 models.

Leaderboard Rankings

Health
100.0%#24/100
OverviewPerformance232PricingTests75HealthEmbed