g2-standard-12

    $1.0004/hr

    ~$730.30/month on-demand in us-central1

    The g2-standard-12 is an Accelerator optimized instance with 12 vCPUs and 48 GiB of memory, 1x NVIDIA nvidia-l4 with up to 32 Gbps bandwidth, starting at $1.000 per hour or $0.736 per hour with spot instances.

    Last updated: Jan 14, 2026, 09:17 PM UTC

    Pricing Options

    CUD

    Committed Use Discounts

    1 Year
    $0.8375/hr
    ~$611.36/mo
    Save 16%
    3 Year
    $0.7582/hr
    ~$553.49/mo
    Save 24%

    Spot Pricing

    Up to 90% savings - flexible workloads

    Spot Price
    $0.7362/hr
    ~$537.46/mo
    Save 26%

    g2-standard family

    Switch between sizes in us-central1

    SizevCPUMem
    g2-standard-4416
    g2-standard-8832
    g2-standard-121248
    g2-standard-161664
    g2-standard-242496
    g2-standard-3232128
    g2-standard-4848192
    g2-standard-9696384

    Instance Specifications

    Detailed hardware and capabilities for g2-standard-12

    Processor

    Architecturex86_64
    vCPUs12
    Memory48 GiB
    Memory per vCPU4.00 GiB

    Network

    PerformanceUp to 32 Gbps
    Bandwidth32 Gbps
    Max Interfaces8
    Enhanced Networking

    Storage

    Persistent Disk Only

    GPU

    Count1
    ManufacturerNVIDIA
    Modelnvidia-l4
    Memory24 GiB
    Total GPU Memory24 GiB

    Capabilities

    Familyg2-standard
    GenerationCurrent
    Burstable

    Regional Pricing Comparison

    Compare g2-standard-12 (Linux) pricing across all regions - sorted by cost

    Current region (us-central1)Other regions
    💡 Click any bar to open that region in a new tab