a2-highgpu-4g

    $20.7897/hr

    ~$15176.50/month on-demand in southamerica-east1

    The a2-highgpu-4g is an Accelerator optimized instance with 48 vCPUs and 340 GiB of memory, 4x NVIDIA nvidia-tesla-a100 with up to 32 Gbps bandwidth, starting at $20.790 per hour or $16.736 per hour with spot instances.

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

    Pricing Options

    CUD

    Committed Use Discounts

    1 Year
    $19.0524/hr
    ~$13908.23/mo
    Save 8%
    3 Year
    $17.7380/hr
    ~$12948.76/mo
    Save 15%

    Spot Pricing

    Up to 90% savings - flexible workloads

    Spot Price
    $16.7355/hr
    ~$12216.92/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-4g

    Processor

    Architecturex86_64
    vCPUs48
    Memory340 GiB
    Memory per vCPU7.08 GiB

    Network

    PerformanceUp to 32 Gbps
    Bandwidth32 Gbps
    Max Interfaces8
    Enhanced Networking

    Storage

    Persistent Disk Only

    GPU

    Count4
    ManufacturerNVIDIA
    Modelnvidia-tesla-a100
    Memory40 GiB
    Total GPU Memory160 GiB

    Capabilities

    Familya2-highgpu
    GenerationCurrent
    Burstable

    Regional Pricing Comparison

    Compare a2-highgpu-4g (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