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
Infini AI logo

Infini AI

Website
Updated 12/8/2025
Infini AI interface preview
Performance Stats
Avg Speed
54.46t/s
Latency
0.74s
Total Tests
9
Models
2

About Infini AI

Provides cloud-based AI services including ComfyUI deployment, model APIs, and compute solutions for enterprise applications.

QwenQwen2.5QwenQwen2

Infini AI offers a cloud platform for AI development and deployment. Key services include:

  • ComfyUI Cloud Deployment: Enterprise-grade production API services for ComfyUI workflows with flexible pricing.
  • Model API Services: Multiple optimized models for various scenarios, supporting M*N configurations across different chips.
  • Compute Solutions: Cost-effective compute resources for AI training and inference, including self-developed inference engines to improve efficiency.
  • Managed Services: Compute resource management, scheduling, monitoring, and consulting for hardware and software optimization.
  • Use Cases: Supports clients like Mootion, Semir, and Liepin for applications in 3D content generation, robotics, and academic research, focusing on operational stability and accelerated iteration.*

Supported Models

ModelSpeedLatencyTests
qwen2.5-7b-instruct
54.46 t/s
0.74s
5
qwen2.5-7b-instruct
54.46 t/s
0.74s
5

Recent Test Records

TimeModelSpeedLatency
Jul 18, 04:34 PMUnknown
-
-s
Jul 17, 07:03 PMqwen2.5-7b-instruct
54.46 t/s
0.74s
May 16, 02:10 AMUnknown
-
-s
Mar 3, 09:11 PMUnknown
-
-s
Feb 20, 02:04 PMUnknown
-
-s