Skip to main content

Serverless API

Introduction​

The CSGHub Serverless API provides a fast and efficient way to access models from the Transcendent Community, supporting various tasks such as text, image, and speech processing. Without the need for deployment or infrastructure maintenance, you can quickly conduct tests and prototype development.

Why Choose the Public Inference Instance?​

The Serverless API is adaptable to various machine learning tasks, making it ideal for prototyping, testing, and experimentation. Key features include:

  • ⚡ Quick Start: Access directly from the model page, free to use.
  • 🚀 Production-Grade API: Offers high-performance inference capabilities with automatic scaling.
  • 💡 Instant Prototyping: No setup required to access powerful models.
  • 🎯 Diverse Use Cases: A single API supporting text, image, and speech tasks.
  • 🔧 Developer-Friendly: Simple API design with fast response times.

Key Features​

  • Supports tasks such as text generation and image generation.
  • Powered by GPU acceleration, significantly boosting inference speed.
  • Runs large-scale models without requiring complex deployments.
  • Production-ready platform with built-in auto-scaling, load balancing, and caching optimization.

How to Use​

For models with Serverless API enabled, users can directly find the Public Inference Instance entry on the model details page and use it immediately.

Public Inference Instance

If you want to create your own inference instance, refer to EndPoint.