ml.p3.16xlarge

    $28.1520/hr

    ~$20550.96/month on-demand in N. Virginia (us-east-1)

    The ml.p3.16xlarge is a GPU Accelerated SageMaker ML instance with 64 vCPUs and 488 GiB of memory with 8 GPU, starting at $28.152 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
    $28.1520/hr
    ~$20550.96/mo

    Reserved 1yr

    One year commitment

    Not available

    Reserved 3yr

    Three year commitment

    Not available

    P3 Family

    Switch between sizes in N. Virginia (us-east-1)

    SizevCPUMem
    ml.p3.16xlarge64488
    ml.p3.2xlarge861
    ml.p3.8xlarge32244

    Instance Specifications

    Detailed hardware and capabilities for ml.p3.16xlarge

    Processor

    vCPUs64
    Memory488 GiB
    Instance FamilyP3
    Architecture64-bit
    Clock Speed2.3 GHz
    Current Gen

    GPU & Accelerator

    Has GPU
    GPU Count8
    GPU NameV100
    GPU ManufacturerNVIDIA
    GPU Memory128 GiB

    Networking

    Network Performance25 Gigabit
    Network Bandwidth5 Gbps
    Max Network Interfaces8
    IPv6 Support
    ENA Support

    EBS (Elastic Block Store)

    EBS Optimizeddefault
    Baseline IOPS80,000 IOPS
    Max IOPS80,000 IOPS
    Baseline Bandwidth14,000 Mbps
    Max Bandwidth14,000 Mbps

    Instance Storage

    Instance Storage

    Regional Pricing Comparison

    Compare ml.p3.16xlarge 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