r8a.48xlarge
Amazon EC2 · R8a family
The r8a.48xlarge is a memory optimized Amazon EC2 instance type with 192 vCPUs and 1,536 GiB of memory, running on AMD EPYC 9R45 Processor with 75 Gigabit networking, starting at $15.34 per hour on demand.
- vCPUs
- 192
- memory
- 1,536 GiB
- processor
- AMD
- on-demand
- $15.34
- spot
- –
- regions
- 9
dedicated
8 GiB per vCPU
x86-64
$11,196/mo · us-east-1
not offered
across 3 areas
r8a.48xlarge price by region
9 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved
| US East (N. Virginia)us-east-1cheapestreferenceNorth America | $15.34 |
| US East (Ohio)us-east-2cheapestNorth America | $15.34 |
| US West (Oregon)us-west-2cheapestNorth America | $15.34 |
| Asia Pacific (Taipei)ap-east-2Asia | $16.65 |
| Canada (Central)ca-central-1North America | $16.80 |
| EU (Ireland)eu-west-1Europe | $17.16 |
| EU (Spain)eu-south-2Europe | $17.16 |
| Asia Pacific (Tokyo)ap-northeast-1Asia | $18.50 |
| EU (Frankfurt)eu-central-1Europe | $18.50 |
Specifications
compute
- vCPUs
- 192
- Memory
- 1,536 GiB
- Memory per vCPU
- 8 GiB
- Processor
- AMD EPYC 9R45 Processor
- CPU vendor
- AMD
- Architecture
- x86-64
- Burstable CPU
- No
storage & network
- Local storage
- Network storage only
- Storage detail
- EBS only
- Network
- 75 Gigabit
- Peak bandwidth
- 75 Gbps
aws details
- API name
r8a.48xlarge- Family
- R8a
- Category
- Memory optimized
- Generation
- Current
- Regions
- 9 (Asia, Europe, North America)
- Cheapest region
- US East (N. Virginia) · $15.34/hr
- Dedicated EBS throughput
- 60000 Mbps
- Enhanced networking
- Yes
- Normalization size factor
- 384
- Processor features
- AMD Turbo; AVX; AVX2; AVX512
- Spot interruption rate (us-east-1)
- <5%
- Spot savings vs on-demand (us-east-1)
- 63%
r8a.48xlarge equivalents on other clouds
closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region
| Provider | Instance | vCPU | Memory | Processor | On-demand | vs r8a.48xlarge |
|---|---|---|---|---|---|---|
| AWS | r8a.48xlarge | 192 | 1,536 GiB | AMD EPYC 9R45 Processor | $15.34 | – |
| Azure | E192s v7 | 192 | 1,536 GiB | Intel Xeon 6 (Granite Rapids) | $16.67 | +9% |
| E192ds v7 | 192 | 1,536 GiB | Intel Xeon 6 (Granite Rapids) | $19.96 | +30% | |
| Google Cloud | c3-highmem-192-metal | 192 | 1,536 GiB | Intel Sapphire Rapids | $12.70 | -17% |
| z3-highmem-192-highlssd-metal | 192 | 1,536 GiB | Intel Sapphire Rapids | $27.65 | +80% | |
| Vultr | vbm-64c-1536gb-amd128 vCPU (1.5× less) | 128 | 1,536 GiB | AMD EPYC 9354 | $4.007 | -74% |
| vx1-g-192c-768g768 GiB (2× less) | 192 | 768 GiB | AMD EPYC | $5.76 | -62% |
R8a family sizes
| Size | vCPU | Memory | Local storage | On-demand | Monthly |
|---|---|---|---|---|---|
| r8a.medium | 1 | 8 GiB | – | $0.0799 | $58.31 |
| r8a.large | 2 | 16 GiB | – | $0.1598 | $117 |
| r8a.xlarge | 4 | 32 GiB | – | $0.3195 | $233 |
| r8a.2xlarge | 8 | 64 GiB | – | $0.639 | $466 |
| r8a.4xlarge | 16 | 128 GiB | – | $1.278 | $933 |
| r8a.8xlarge | 32 | 256 GiB | – | $2.556 | $1,866 |
| r8a.12xlarge | 48 | 384 GiB | – | $3.834 | $2,799 |
| r8a.16xlarge | 64 | 512 GiB | – | $5.112 | $3,732 |
| r8a.24xlarge | 96 | 768 GiB | – | $7.668 | $5,598 |
| r8a.metal-24xl | 96 | 768 GiB | – | $7.668 | $5,598 |
| r8a.48xlarge | 192 | 1,536 GiB | – | $15.34 | $11,196 |
| r8a.metal-48xl | 192 | 1,536 GiB | – | $15.34 | $11,196 |
Similar instance types on AWS
other AWS families with a similar shape, cheapest first
r8a.48xlarge FAQ
How much does r8a.48xlarge cost?
r8a.48xlarge costs $15.34 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $11,196 per month. Across 9 regions the Linux on-demand price ranges from $15.34 in US East (N. Virginia) to $18.50 in EU (Frankfurt). With Windows it costs $24.17 per hour.
How many vCPUs and how much memory does r8a.48xlarge have?
r8a.48xlarge has 192 vCPUs and 1,536 GiB of memory (8 GiB per vCPU), running on AMD EPYC 9R45 Processor. It is a memory optimized instance type in the R8a family.
What are the equivalents of r8a.48xlarge on other clouds?
The closest matches by vCPU, memory, CPU architecture and instance class are on Azure, E192s v7 (192 vCPU, 1,536 GiB, $16.67/hour in East US); on Google Cloud, c3-highmem-192-metal (192 vCPU, 1,536 GiB, $12.70/hour in Iowa); on Vultr, vbm-64c-1536gb-amd (128 vCPU, 1,536 GiB, $4.007/hour in Los Angeles).