ml.p5.48xlarge

    $63.2960/hr

    ~$46206.08/month on-demand in N. Virginia (us-east-1)

    The ml.p5.48xlarge is a GPU Accelerated SageMaker ML instance with 192 vCPUs and 2 GiB of memory with 8 GPU, starting at $63.296 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
    $63.2960/hr
    ~$46206.08/mo

    Reserved 1yr

    One year commitment

    Not available

    Reserved 3yr

    Three year commitment

    Not available

    Instance Specifications

    Detailed hardware and capabilities for ml.p5.48xlarge

    Processor

    vCPUs192
    Memory2 GiB
    Instance FamilyP5
    ArchitectureN/A
    Current Gen

    GPU & Accelerator

    Has GPU
    GPU Count8
    GPU NameH100
    GPU ManufacturerNVIDIA
    GPU Memory640 GiB

    Networking

    Network PerformanceN/A
    Network Bandwidth100 Gbps
    Max Network Interfaces64
    IPv6 Support
    ENA Support

    EBS (Elastic Block Store)

    EBS Optimizeddefault
    Baseline IOPS260,000 IOPS
    Max IOPS260,000 IOPS
    Baseline Bandwidth80,000 Mbps
    Max Bandwidth80,000 Mbps

    Instance Storage

    Instance Storage
    Storage Size30,400 GB
    Storage Typessd
    NVMe

    Regional Pricing Comparison

    Compare ml.p5.48xlarge 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