a2-highgpu-8g

    $41.5794/hr

    ~$30352.99/month on-demand in southamerica-east1

    The a2-highgpu-8g is an Accelerator optimized instance with 96 vCPUs and 680 GiB of memory, 8x NVIDIA nvidia-tesla-a100 with up to 32 Gbps bandwidth, starting at $41.579 per hour or $33.471 per hour with spot instances.

    Last updated: Jan 15, 2026, 12:04 PM UTC

    Pricing Options

    CUD

    Committed Use Discounts

    1 Year
    $38.1047/hr
    ~$27816.46/mo
    Save 8%
    3 Year
    $35.4761/hr
    ~$25897.52/mo
    Save 15%

    Spot Pricing

    Up to 90% savings - flexible workloads

    Spot Price
    $33.4710/hr
    ~$24433.83/mo
    Save 20%

    a2-highgpu family

    Switch between sizes in southamerica-east1

    SizevCPUMem
    a2-highgpu-1g1285
    a2-highgpu-2g24170
    a2-highgpu-4g48340
    a2-highgpu-8g96680

    Instance Specifications

    Detailed hardware and capabilities for a2-highgpu-8g

    Processor

    Architecturex86_64
    vCPUs96
    Memory680 GiB
    Memory per vCPU7.08 GiB

    Network

    PerformanceUp to 32 Gbps
    Bandwidth32 Gbps
    Max Interfaces8
    Enhanced Networking

    Storage

    Persistent Disk Only

    GPU

    Count8
    ManufacturerNVIDIA
    Modelnvidia-tesla-a100
    Memory40 GiB
    Total GPU Memory320 GiB

    Capabilities

    Familya2-highgpu
    GenerationCurrent
    Burstable

    Regional Pricing Comparison

    Compare a2-highgpu-8g (Linux) pricing across all regions - sorted by cost

    Current region (southamerica-east1)Other regions
    💡 Click any bar to open that region in a new tab