Last Updated: July 9, 2025
Deploy from the SaladCloud Portal.

​
Overview

This recipe streamlines the process of deploying Sogni Fast Workers on SaladCloud. Sogni is a decentralized AI inference network that enables you to contribute compute power and earn rewards by running on-chain workers. You will need a Sogni API Key and NFT Token ID to use this recipe. For more information about Sogni’s decentralized network and how to obtain these credentials, visit Sogni.ai and read the Sogni Documentation. Two worker variants are available:
  • FLUX Worker - Optimized for FLUX model inference on the Sogni network
  • Stable Diffusion Worker - Optimized for Stable Diffusion model inference on the Sogni network
Both workers connect to the Sogni decentralized network and process inference requests from users worldwide, earning rewards for successful completions.

​
Getting Started

​
Prerequisites

Before deploying a Sogni worker, you’ll need:
  1. Sogni API Key - Obtain from the Sogni platform
  2. NFT Token ID - Required for worker authentication on the network
  3. SaladCloud Account - For deploying the worker infrastructure
Visit Sogni.ai to learn more about their platform and obtain the necessary credentials.

​
Worker Configuration

When deploying this recipe, you’ll configure:
  • Your Sogni API credentials
  • The specific worker variant (FLUX or Stable Diffusion)
  • Resource allocation for optimal performance

​
How To Use This Recipe

​
Replica Count

The recipe must use only one replica per deployment. Each worker represents a single node on the Sogni decentralized network.

​
Authentication

This recipe uses Sogni’s authentication system with your API key and NFT Token ID. No additional SaladCloud gateway authentication is required for the worker itself.

​
Logging

SaladCloud offers a simple built-in method to view logs from the portal, to facilitate monitoring your worker’s performance. For production workloads, we highly recommend connecting an external logging source, such as Axiom, to track earnings and inference statistics.

​
Deploy It And Wait

When you deploy the recipe, SaladCloud will find a qualified node and begin the process of downloading the container image to the host machine. It may take up to tens of minutes to download to some machines, depending on the network conditions of that particular node. Remember, these are residential PCs with residential internet connections, and performance will vary across different nodes. Eventually, you will see your instance enter the running state and show a green checkmark in the “Ready” column. At this time, your worker will connect to the Sogni network and begin processing inference requests, earning rewards for successful completions. You will find helpful links and information in the readme on the container group page once deployed.

​
Learn More

For detailed information about Sogni’s decentralized AI network, earnings potential, and worker management:

​
Source Code

Github Repository