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

AWS L40S Pricing Options

All available L40S instance types on AWS, sorted by lowest hourly rate.

Region Instance Type Price/hr GPUs vCPUs RAM
us-east-1 g6e.48xlarge (8x L40S) On-Demand $13.7440/hr Cheapest 8× GPU 192 vCPU 768 GB

About AWS L40S 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 L40S

  • 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.

L40S Technical Overview

ArchitectureAda Lovelace
Memory48 GB GDDR6X
Best ForInference workloads, real-time rendering, and mixed AI/graphics applications

The L40S is an inference-optimized GPU built on the Ada Lovelace architecture. It provides strong FP8 and INT8 performance for model serving, plus hardware ray-tracing for 3D/visualization workloads.

Pricing Analysis

AWS's cheapest L40S option starts at $13.7440/hr, which is 594% above the market average of $1.9796/hr. AWS currently offers on-demand pricing only for L40S. 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: L40S pricing is typically 40–60% below H100, making it an excellent choice for inference-heavy deployments where training performance is not the primary requirement.

Top Alternatives to AWS for L40S

Side-by-side cost comparison vs the cheapest AWS L40S rate ($13.7440/hr).

Provider Price/hr Type vs AWS
Vast.ai $0.4037/hr Spot -97% cheaper vs AWS
TensorDock $0.5900/hr On-Demand -96% cheaper vs AWS
Lightning AI $0.6500/hr On-Demand -95% cheaper vs AWS
RunPod $0.6900/hr On-Demand -95% cheaper vs AWS
Nebius $0.8700/hr On-Demand -94% cheaper vs AWS

View all L40S providers →

Calculate Your Exact L40S Cost

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

● $19 — no subscription
Track AWS L40S 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 L40S cost per hour in 2026? +
AWS L40S starts at $13.7440/hr (on-demand). The market average for L40S across all providers is $1.9796/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 L40S? +
There are 13 providers offering L40S cheaper than AWS: Vast.ai at $0.4037/hr, TensorDock at $0.5900/hr, Lightning AI at $0.6500/hr, and 10 more. 1 other provider offers L40S at higher rates. See the full comparison table for all L40S providers.
Does AWS offer reserved or spot L40S pricing? +
AWS offers 1 pricing type for L40S: 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 L40S best suited for? +
The L40S (Ada Lovelace architecture, 48 GB GDDR6X) is best suited for Inference workloads, real-time rendering, and mixed AI/graphics applications. 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 L40S on AWS for a month? +
At AWS's cheapest L40S rate of $13.7440/hr: running 24/7 costs ~$329.86/day or ~$10033.12/month per GPU. For training jobs, costs scale linearly — a 100-hour training run would cost ~$1374.40. 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 L40S — calculated from real 90-day pricing data, not an LLM.

Get Analysis — $19