ml.p4de.24xlarge

    $31.5641/hr

    ~$23041.80/month on-demand in N. Virginia (us-east-1)

    The ml.p4de.24xlarge is a GPU Accelerated SageMaker ML instance with 96 vCPUs and 1152 GiB of memory with 8 GPU, starting at $31.564 per hour.

    Last updated: Feb 10, 2026, 05:00 AM UTC

    All pricing cards update to show this payment type

    Pricing Options

    On-Demand

    Pay as you go - no commitment

    Hourly Rate
    $31.5641/hr
    ~$23041.80/mo

    Reserved 1yr

    One year commitment

    Not available

    Reserved 3yr

    Three year commitment

    Not available

    Instance Specifications

    Detailed hardware and capabilities for ml.p4de.24xlarge

    Processor

    vCPUs96
    Memory1152 GiB
    Instance FamilyP4DE
    ArchitectureN/A
    Clock Speed3 GHz
    Current Gen

    GPU & Accelerator

    Has GPU
    GPU Count8
    GPU NameA100
    GPU ManufacturerNVIDIA
    GPU Memory640 GiB

    Networking

    Network Performance400 Gigabit
    Network Bandwidth100 Gbps
    Max Network Interfaces60
    IPv6 Support
    ENA Support

    EBS (Elastic Block Store)

    EBS Optimizeddefault
    Baseline IOPS80,000 IOPS
    Max IOPS80,000 IOPS
    Baseline Bandwidth19,000 Mbps
    Max Bandwidth19,000 Mbps

    Instance Storage

    Instance Storage
    Storage Size8,000 GB
    Storage Typessd
    NVMe

    Regional Pricing Comparison

    Compare ml.p4de.24xlarge pricing across all regions - sorted by cost

    Current region (us-east-1)Other regions
    Click any bar to open that region in a new tab