a2-highgpu-2g
$7.3468/hr
~$5363.14/month on-demand in us-central1
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 $7.347 per hour or $6.548 per hour with spot instances.
Last updated: Jan 14, 2026, 09:17 PM UTC
Pricing Options
CUD
Committed Use Discounts
1 Year
$6.7995/hr
~$4963.64/mo
Save 7%
3 Year
$6.3855/hr
~$4661.41/mo
Save 13%
Spot Pricing
Up to 90% savings - flexible workloads
Spot Price
$6.5481/hr
~$4780.12/mo
Save 11%
a2-highgpu family
Switch between sizes in us-central1
| Size | vCPU | Mem |
|---|---|---|
| a2-highgpu-1g | 12 | 85 |
| a2-highgpu-2g | 24 | 170 |
| a2-highgpu-4g | 48 | 340 |
| a2-highgpu-8g | 96 | 680 |
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-central1)Other regions
💡 Click any bar to open that region in a new tab