Yotta Labs
  • COMPANY
    • About
    • Mission
    • FAQs
  • PRODUCTS
    • Quickstart
    • GPU Instances
    • AI Explorer
      • Text Generation
      • Image Generation
      • Audio Generation
      • Pricing
    • Inference
      • Introduction
      • User Interface
      • Broker Node
      • GPU Worker
        • Quickstart
        • Core Concept
        • Troubleshoot
        • Supported Devices
        • FAQs
      • Pricing
    • Fine-Tune
    • Billing
  • Technology
    • Parallelism Strategies
    • Decentralized Scheduling
    • Memory Optimization
    • Proactive Communication
    • Fault Tolerance
    • Computation Validation
    • White Paper
  • TOKENOMICS
    • Overview
    • Payment & Fee
    • Staking
    • GPU Incentive
    • Community
    • Governance
Powered by GitBook
On this page
  • Prerequisites
  • Steps to Launch a GPU Instance
  • Pricing

Was this helpful?

  1. PRODUCTS

GPU Instances

GPU instances empower your computing tasks by providing high-performance hardware tailored for intensive workloads such as machine learning, data processing, and 3D rendering. Yotta Labs offers a simp

PreviousQuickstartNextAI Explorer

Last updated 2 months ago

Was this helpful?

Prerequisites

  • Basic Computing Knowledge: Familiarity with cloud platforms and launching virtual instances is helpful.

Steps to Launch a GPU Instance

  1. Navigate to the Instances section from the left-hand menu

  1. Select Your Instance Type Choose the best GPU type for your workload from the available options (e.g., NVIDIA A10, T4, or RTX 4090). Each instance is optimized for different performance needs.

  1. Choose Your Region Select the region closest to you for reduced latency and improved performance.

  1. Configure Your Instance

  • Allocate CPU, RAM, and storage resources based on your workload requirements.

  • Set a custom instance name to identify your project.

  1. Launch the Instance Click “Confirm” to start your instance. Yotta Labs will handle the provisioning.

  2. Access and Install Software Use SSH to connect to your instance and install required GPU drivers or additional software.

  3. Validate the Setup Test your instance to ensure the GPU is configured correctly for your application.

Pricing

  • Pricing Model:

    • Users can allocate machines using their balance under the Billing page.

    • When the machine(s) are running, balance will be deducted.

    • All running instances will be terminated one the balance drop to close to $0.

    • Users can "pause" running machines if they don't need to use the machines. (Note: not every data center supports this feature. Only available in a few locations)

  • Prices start from:

    • Oregon, USA

      • 1x T4 (16GB) 4 CPU cores, 16 GB RAM, 256 GB SSD: $0.33 / hr

      • 4x T4 (16GB) 48 CPU cores, 192 GB RAM, 256 GB SSD: $2.53 / hr

      • 1x A10 (24GB) 8 CPU cores, 32 GB RAM, 256 GB SSD: $0.8 / hr

      • 4x A10 (24GB) 48 CPU cores, 192 GB RAM, 256 GB SSD: $3.61 / hr

      • x86 1 CPU cores, 1 GB RAM, 45 GB SSD: $0.05 / hr

      • x86 4 CPU cores, 16 GB RAM, 128 GB SSD: $0.23 / hr

      • 1x RTX 4090 (24GB) 4 CPU cores, 16 GB RAM, 256 GB SSD: $0.37 / hr

    • Virginia, USA

      • 1x A100 (40GB SXM4) 30 CPU cores, 200 GB RAM, 512 GB SSD: $15.47 / hr

      • 8x A800 (80GB SXM4) 240 CPU cores, 1.76 TB RAM, 20 TB SSD: $15.47 / hr

    • Utah, USA

      • 1x H100 (80GB PCle) 26 CPU cores, 200 GB RAM, 1 TB SSD: $2.69 / hr

      • 8x H100 (80GB SXM5) 208 CPU cores, 1.76 TB RAM, 22 TB SSD: $25.83 / hr

instances
select instance type
select region
confirmation