Nebula Block
  • Overview
  • Getting Started
    • Quickstart
    • Account Setup
    • Billing Information
    • Deploy Products
  • Core Services
    • Inference API (Serverless Endpoints)
      • Text Generation
      • Text Generation (Vision)
      • Image Generation
      • Embedding Generation
      • Model List
    • GPU Instances
      • Quickstart
    • Object Storage
      • Get Started
      • Tutorials
        • Linux/Mac
        • Windows
      • SDK
        • Golang
        • Python
        • Java
    • SSH Keys
      • Quickstart
  • API Reference
    • Platform API
      • Authentication
      • Instances
        • List Images
        • List Products
        • Create GPU Instance
        • List User Instances
        • List Deleted User Instances
        • User Instance Detail
        • Delete GPU Instance
        • Start GPU Instance
        • Stop GPU Instance
        • Reboot GPU Instance
      • SSH Keys
        • Create SSH Key
        • List SSH Keys
        • Rename SSH Key
        • Delete SSH Key
      • API Keys
        • Create API Key
        • List API Keys
        • Delete API Key
      • Billing
        • Get Credit Balance
        • List Invoices
        • Download Invoice
        • Get Payment History
    • Inference API (OpenAI Compatible)
      • List Serverless Models
      • Generate Text
      • Generate Text (Vision)
      • Generate Images
      • Generate Embeddings
  • Tier
  • Referral
  • Glossary
  • Contact Us
Powered by GitBook
On this page
  • Summary
  • Serverless Endpoints
  • Dedicated Endpoints
  • GPU Instances
  1. Getting Started

Deploy Products

Summary

There are 3 main products at Nebula Block:

  • Serverless Endpoints

  • Dedicated Endpoints.

  • GPU Instances

Serverless Endpoints

These are endpoints that host various generative AI models immediately available to use.

For more details, see here.

Dedicated Endpoints

Dedicated endpoints are like serverless endpoints, but far more customizable. That is, you can select the hardware and the desired model (one of ours or even your own!) and we'll deploy it on its own server. Unlike the serverless endpoints above, the server on your dedicated endpoint will serve your workloads exclusively.

For more details, see here.

GPU Instances

GPU instances consist of on-demand GPU virtual machines, customizable with a variety of configurations to suit you and your needs for any project.

For more details, see here.

PreviousBilling InformationNextCore Services

Last updated 2 months ago