LogoLMSpeed
  • Home
  • Free
  • Categories
  • Models
  • Docs
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2025 LMSpeed All Rights Reserved.
BACK TO INDEX
AIHubMix logo

AIHubMix

Website
Updated 12/8/2025
AIHubMix interface preview
Performance Stats
Avg Speed
67.35t/s
Latency
1.00s
Total Tests
25
Models
5

About AIHubMix

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

DeepSeekDeepSeek-V3QwenQwen2.5QwenQwen2

AIHubMix offers a unified API gateway that aggregates access to various large language models and AI services. It provides a single interface for developers to interact with models from providers like OpenAI, Anthropic, Google, DeepSeek, Qwen, and others. Key capabilities include model aggregation, unified API endpoints, and support for text, vision, and video models. The platform features an app store with community-developed applications and offers promotional discounts. Recent model additions include GPT-5.1, Claude Opus 4.5, Gemini 3 Pro, and various video generation models like Sora-2 and Veo-3.1. Use cases include AI application development, model testing, and accessing multiple AI services through one integration.

Supported Models

ModelSpeedLatencyTests
gemini-2.0-flash
163.32 t/s
0.59s
5
DeepSeek-V3-Fast
79.64 t/s
0.89s
5
Qwen/Qwen2.5-72B-Instruct
32.01 t/s
1.03s
10
Qwen/Qwen2.5-72B-Instruct
32.01 t/s
1.03s
10
DeepSeek-V3
29.76 t/s
1.44s
5

Recent Test Records

TimeModelSpeedLatency
Sep 13, 12:54 PMQwen/Qwen2.5-72B-Instruct
32.44 t/s
1.01s
Sep 13, 12:52 PMQwen/Qwen2.5-72B-Instruct
31.58 t/s
1.05s
Sep 13, 12:49 PMgemini-2.0-flash
163.32 t/s
0.59s
Sep 13, 12:46 PMDeepSeek-V3-Fast
79.64 t/s
0.89s
Sep 13, 12:43 PMDeepSeek-V3
29.76 t/s
1.44s