ml.inf2.8xlarge

    $2.3600/hr

    ~$1722.80/month on-demand in N. Virginia (us-east-1)

    The ml.inf2.8xlarge is a ML Accelerated SageMaker ML instance with 32 vCPUs and 128 GiB of memory with N/A GPU, starting at $2.360 per hour.

    Last updated: Feb 11, 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
    $2.3600/hr
    ~$1722.80/mo

    Reserved 1yr

    One year commitment

    Not available

    Reserved 3yr

    Three year commitment

    Not available

    Inf2 Family

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

    SizevCPUMem
    ml.inf2.24xlarge96384
    ml.inf2.48xlarge192768
    ml.inf2.8xlarge32128
    ml.inf2.xlarge416

    Instance Specifications

    Detailed hardware and capabilities for ml.inf2.8xlarge

    Processor

    vCPUs32
    Memory128 GiB
    Instance FamilyINF2
    Architecture64-bit
    Clock Speed2.95 GHz
    Current Gen

    GPU & Accelerator

    Has GPU
    GPU CountN/A
    GPU MemoryNA

    Networking

    Network PerformanceUp to 25 Gigabit
    Network Bandwidth16.67 Gbps
    Max Network Interfaces8
    IPv6 Support
    ENA Support

    EBS (Elastic Block Store)

    EBS Optimizeddefault
    Baseline IOPS40,000 IOPS
    Max IOPS40,000 IOPS
    Baseline Bandwidth10,000 Mbps
    Max Bandwidth10,000 Mbps

    Instance Storage

    Instance Storage

    Regional Pricing Comparison

    Compare ml.inf2.8xlarge 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