a2-highgpu-8g

    $37.7839/hr

    ~$27582.28/month on-demand in asia-east2

    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 $37.784 per hour or $30.789 per hour with spot instances.

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

    Pricing Options

    CUD

    Committed Use Discounts

    1 Year
    $34.7211/hr
    ~$25346.39/mo
    Save 8%
    3 Year
    $32.4040/hr
    ~$23654.94/mo
    Save 14%

    Spot Pricing

    Up to 90% savings - flexible workloads

    Spot Price
    $30.7886/hr
    ~$22475.66/mo
    Save 19%

    a2-highgpu family

    Switch between sizes in asia-east2

    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 (asia-east2)Other regions
    💡 Click any bar to open that region in a new tab