a2-highgpu-2g

    $7.8687/hr

    ~$5744.16/month on-demand in us-west4

    The a2-highgpu-2g is an Accelerator optimized instance with 24 vCPUs and 170 GiB of memory, 2x NVIDIA nvidia-tesla-a100 with up to 32 Gbps bandwidth, starting at $7.869 per hour or $6.869 per hour with spot instances.

    Last updated: Jan 16, 2026, 12:03 PM UTC

    Pricing Options

    CUD

    Committed Use Discounts

    1 Year
    $7.2524/hr
    ~$5294.24/mo
    Save 8%
    3 Year
    $6.7861/hr
    ~$4953.87/mo
    Save 14%

    Spot Pricing

    Up to 90% savings - flexible workloads

    Spot Price
    $6.8692/hr
    ~$5014.55/mo
    Save 13%

    a2-highgpu family

    Switch between sizes in us-west4

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

    Instance Specifications

    Detailed hardware and capabilities for a2-highgpu-2g

    Processor

    Architecturex86_64
    vCPUs24
    Memory170 GiB
    Memory per vCPU7.08 GiB

    Network

    PerformanceUp to 32 Gbps
    Bandwidth32 Gbps
    Max Interfaces8
    Enhanced Networking

    Storage

    Persistent Disk Only

    GPU

    Count2
    ManufacturerNVIDIA
    Modelnvidia-tesla-a100
    Memory40 GiB
    Total GPU Memory80 GiB

    Capabilities

    Familya2-highgpu
    GenerationCurrent
    Burstable

    Regional Pricing Comparison

    Compare a2-highgpu-2g (Linux) pricing across all regions - sorted by cost

    Current region (us-west4)Other regions
    💡 Click any bar to open that region in a new tab