Prices updated 2026-06-23 — sourced from live provider data

AWS A10G Pricing Options

All available A10G instance types on AWS, sorted by lowest hourly rate.

Region Instance Type Price/hr GPUs vCPUs RAM
us-east-1 g5.xlarge On-Demand $1.0060/hr Cheapest 1× GPU 4 vCPU 16 GB
us-east-1 g5.xlarge (1x A10G) On-Demand $1.0060/hr 1× GPU 4 vCPU 16 GB
us-east-1 g5.2xlarge On-Demand $1.2120/hr 1× GPU 8 vCPU 32 GB
us-east-1 g5.4xlarge On-Demand $1.6240/hr 1× GPU 16 vCPU 64 GB
us-east-1 g5.8xlarge On-Demand $2.4480/hr 1× GPU 32 vCPU 128 GB
us-east-1 g5.16xlarge On-Demand $4.0960/hr 1× GPU 64 vCPU 256 GB
us-east-1 g5.12xlarge On-Demand $5.6720/hr 4× GPU 48 vCPU 192 GB
us-east-1 g5.24xlarge On-Demand $8.1440/hr 4× GPU 96 vCPU 384 GB
us-east-1 g5.48xlarge On-Demand $16.2880/hr 8× GPU 192 vCPU 768 GB

About AWS A10G Cloud Pricing

Amazon Web Services dominates the GPU cloud market with the broadest instance family portfolio and deepest regional coverage. AWS GPU instances run on custom Nitro hypervisors with dedicated hardware tenancy options.

Why Choose AWS for A10G

  • Widest regional availability (30+ regions)
  • Savings Plans and Reserved Instances for 1–3 year commitments
  • Tight integration with SageMaker, Bedrock, and EKS for ML pipelines
  • Elastic Fabric Adapter (EFA) for multi-node training

Best suited for: Enterprise teams running production ML pipelines who need SLA guarantees, compliance certifications (HIPAA, SOC2, FedRAMP), and deep AWS ecosystem integration.

A10G Technical Overview

ArchitectureAmpere
Memory24 GB GDDR6
Best ForInference workloads, real-time inference APIs, and cost-efficient model serving

The A10G is an inference-focused GPU commonly used in AWS G5 instances. It offers a good balance of Tensor Core performance and VRAM for serving models up to ~7B parameters.

Pricing Analysis

AWS's cheapest A10G option starts at $1.0060/hr, which is 32% below the market average of $1.4859/hr. AWS currently offers on-demand pricing only for A10G. This means no commitment required, but you won't access the deeper discounts available from reserved or spot pricing.

Note: AWS pricing is typically 15–40% higher than specialized GPU clouds, but the ecosystem depth and enterprise support often justify the premium for production workloads.

Market context: A10G is widely available through AWS and other providers, making it a reliable choice for production inference deployments.

Top Alternatives to AWS for A10G

Side-by-side cost comparison vs the cheapest AWS A10G rate ($1.0060/hr).

Provider Price/hr Type vs AWS
Vast.ai $0.1800/hr Spot -82% cheaper vs AWS
RunPod $0.2800/hr Spot -72% cheaper vs AWS
TensorDock $0.3500/hr Spot -65% cheaper vs AWS
Vultr $0.6500/hr On-Demand -35% cheaper vs AWS
Lepton AI $0.7800/hr On-Demand -22% cheaper vs AWS

View all A10G providers →

Calculate Your Exact A10G Cost

Enter your hours, job type, and GPU count. Our calculator compares AWS against all 32 providers instantly.

● $19 — no subscription
Track AWS A10G prices — daily alerts
Get emailed when AWS drops below your budget. $19 for 30 days. No account needed.
Set Price Alert → Calculator →

Frequently Asked Questions

How much does AWS A10G cost per hour in 2026? +
AWS A10G starts at $1.0060/hr (on-demand). This is below the A10G market average of $1.4859/hr — AWS is among the more competitively priced options for this GPU. AWS offers 9 A10G configurations ranging from $1.0060 to $16.2880/hr. Use the GPU cost calculator to estimate total cost based on your hours and workload type.
What are the cheapest alternatives to AWS for A10G? +
There are 5 providers offering A10G cheaper than AWS: Vast.ai at $0.1800/hr, RunPod at $0.2800/hr, TensorDock at $0.3500/hr, and 2 more. 1 other provider offers A10G at higher rates. See the full comparison table for all A10G providers.
Does AWS offer reserved or spot A10G pricing? +
AWS offers 1 pricing type for A10G: on-demand. With on-demand only, you pay per hour with no commitment. While you won't get reserved or spot discounts, this provides maximum flexibility for unpredictable workloads.
What workloads is AWS A10G best suited for? +
The A10G (Ampere architecture, 24 GB GDDR6) is best suited for Inference workloads, real-time inference APIs, and cost-efficient model serving. AWS is a hyperscaler provider — Enterprise teams running production ML pipelines who need SLA guarantees, compliance certifications (HIPAA, SOC2, FedRAMP), and deep AWS ecosystem integration.
How much does it cost to run A10G on AWS for a month? +
At AWS's cheapest A10G rate of $1.0060/hr: running 24/7 costs ~$24.14/day or ~$734.38/month per GPU. For training jobs, costs scale linearly — a 100-hour training run would cost ~$100.60. Multi-GPU configurations multiply accordingly. Use the cost calculator for precise estimates with your specific parameters.
Compare across all providers

Not sure which GPU configuration fits your budget?

Get a personalized recommendation based on your monthly budget, workload, and real pricing data from all 58 providers.

Budget Optimizer — $19 →
$19 One-Time

Is a reserved contract worth it here?

Get the break-even math for AWS A10G — calculated from real 90-day pricing data, not an LLM.

Get Analysis — $19