Overview

Clients use the OpenGPU Network to run computational tasks on distributed GPUs.

Why OpenGPU for Clients

OpenGPU is a task marketplace, not a GPU marketplace. You don't manage infrastructure. Just define your task, set time limits and rewards, and let providers compete to deliver results.

• Publish tasks, not rent GPUs

• No infrastructure management

• Providers compete for your work

• Pay only for completed tasks

How It Works

1. Create a Source — Define your execution environment (Docker container + requirements)

2. Publish Tasks — Submit jobs with payment to your Source

3. Get Results — Providers compete to execute; you receive results

Tools Available

Tool	Best For
Client App	Web-based source/task management
SDK	Programmatic integration
Relay	API access without blockchain (external)

Quick Paths

I want to run inference quickly: → Use Relay — API-based, no blockchain knowledge needed

I want to publish my own model: → Publishing Sources — Create a custom Source

I want to automate task submission: → Using the SDK — Programmatic access

Costs

• Pay per task in $OGPU

• Real-time competitive pricing

• No minimum commitments

• Payment held in escrow until completion

AI Agents

Clients can leverage AI agents to optimize task pricing and provider selection. See AI Agents for details.