Loading Comparison
Fetching pricing data and provider information...
Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between Amazon AWS and Sesterce. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
Average Price Difference: $2.21/hour between comparable GPUs
| GPU Model ↑ | Amazon AWS Price | Sesterce Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A10 24GB VRAM • Amazon AWSSesterce | ↑+$0.18(+21.9%) | |||
A10 24GB VRAM • $1.01/hour Updated: 4/18/2026 $0.82/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$0.18(+21.9%) | ||||
A100 SXM 80GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$1.37(+99.6%) | ||
A100 SXM 80GB VRAM • $2.74/hour 8x GPU configuration Updated: 4/18/2026 $1.38/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$1.37(+99.6%) | ||||
A16 64GB VRAM • Sesterce | Not Available | — | ||
A16 64GB VRAM • | ||||
A30 24GB VRAM • Sesterce | Not Available | — | ||
A30 24GB VRAM • | ||||
A40 48GB VRAM • Sesterce | Not Available | — | ||
A40 48GB VRAM • | ||||
B200 192GB VRAM • Sesterce | Not Available | 8x GPU | — | |
B200 192GB VRAM • | ||||
Gaudi 2 96GB VRAM • Sesterce | Not Available | 8x GPU | — | |
Gaudi 2 96GB VRAM • | ||||
GH200 96GB VRAM • Sesterce | Not Available | — | ||
GH200 96GB VRAM • | ||||
H100 NVL 94GB VRAM • Sesterce | Not Available | 2x GPU | — | |
H100 NVL 94GB VRAM • | ||||
H100 SXM 80GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$5.05(+276.8%) | ||
H100 SXM 80GB VRAM • $6.88/hour 8x GPU configuration Updated: 4/18/2026 $1.83/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$5.05(+276.8%) | ||||
H200 141GB VRAM • Amazon AWSSesterce | 8x GPU | 8x GPU | ↑+$5.44(+219.7%) | |
H200 141GB VRAM • $7.91/hour 8x GPU configuration Updated: 4/18/2026 $2.48/hour 8x GPU configuration Updated: 4/18/2026 ★Best Price Price Difference:↑+$5.44(+219.7%) | ||||
HGX B300 288GB VRAM • Sesterce | Not Available | 8x GPU | — | |
HGX B300 288GB VRAM • | ||||
L4 24GB VRAM • Amazon AWSSesterce | 8x GPU | ↓$0.11(12.2%) | ||
L4 24GB VRAM • $0.80/hour Updated: 4/18/2026 ★Best Price $0.92/hour 8x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.11(12.2%) | ||||
L40 40GB VRAM • Sesterce | Not Available | — | ||
L40 40GB VRAM • | ||||
L40S 48GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$1.10(+145.2%) | ||
L40S 48GB VRAM • $1.86/hour Updated: 4/18/2026 $0.76/hour 8x GPU configuration Updated: 4/18/2026 ★Best Price Price Difference:↑+$1.10(+145.2%) | ||||
A10 24GB VRAM • Amazon AWSSesterce | ↑+$0.18(+21.9%) | |||
A10 24GB VRAM • $1.01/hour Updated: 4/18/2026 $0.82/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$0.18(+21.9%) | ||||
A100 SXM 80GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$1.37(+99.6%) | ||
A100 SXM 80GB VRAM • $2.74/hour 8x GPU configuration Updated: 4/18/2026 $1.38/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$1.37(+99.6%) | ||||
A16 64GB VRAM • Sesterce | Not Available | — | ||
A16 64GB VRAM • | ||||
A30 24GB VRAM • Sesterce | Not Available | — | ||
A30 24GB VRAM • | ||||
A40 48GB VRAM • Sesterce | Not Available | — | ||
A40 48GB VRAM • | ||||
B200 192GB VRAM • Sesterce | Not Available | 8x GPU | — | |
B200 192GB VRAM • | ||||
Gaudi 2 96GB VRAM • Sesterce | Not Available | 8x GPU | — | |
Gaudi 2 96GB VRAM • | ||||
GH200 96GB VRAM • Sesterce | Not Available | — | ||
GH200 96GB VRAM • | ||||
H100 NVL 94GB VRAM • Sesterce | Not Available | 2x GPU | — | |
H100 NVL 94GB VRAM • | ||||
H100 SXM 80GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$5.05(+276.8%) | ||
H100 SXM 80GB VRAM • $6.88/hour 8x GPU configuration Updated: 4/18/2026 $1.83/hour Updated: 4/18/2026 ★Best Price Price Difference:↑+$5.05(+276.8%) | ||||
H200 141GB VRAM • Amazon AWSSesterce | 8x GPU | 8x GPU | ↑+$5.44(+219.7%) | |
H200 141GB VRAM • $7.91/hour 8x GPU configuration Updated: 4/18/2026 $2.48/hour 8x GPU configuration Updated: 4/18/2026 ★Best Price Price Difference:↑+$5.44(+219.7%) | ||||
HGX B300 288GB VRAM • Sesterce | Not Available | 8x GPU | — | |
HGX B300 288GB VRAM • | ||||
L4 24GB VRAM • Amazon AWSSesterce | 8x GPU | ↓$0.11(12.2%) | ||
L4 24GB VRAM • $0.80/hour Updated: 4/18/2026 ★Best Price $0.92/hour 8x GPU configuration Updated: 4/18/2026 Price Difference:↓$0.11(12.2%) | ||||
L40 40GB VRAM • Sesterce | Not Available | — | ||
L40 40GB VRAM • | ||||
L40S 48GB VRAM • Amazon AWSSesterce | 8x GPU | ↑+$1.10(+145.2%) | ||
L40S 48GB VRAM • $1.86/hour Updated: 4/18/2026 $0.76/hour 8x GPU configuration Updated: 4/18/2026 ★Best Price Price Difference:↑+$1.10(+145.2%) | ||||
Explore how these providers compare to other popular GPU cloud services
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Extensive network of data centers across multiple regions worldwide
Flexible pricing model with no upfront commitments required
Comprehensive security tools and compliance certifications
Automatically adjust resources based on demand
Extensive ecosystem of services that work seamlessly together
Comprehensive suite of tools for development, deployment, and management
Datacenters powered by renewable energy across Europe, reducing environmental impact of AI systems
Choose from VM, container, or bare-metal deployment options based on your workload requirements
Bare metal dedicated cluster solutions available within 2 hours with HPC job management
Full-stack AI platform covering training, inference, and data preparation workflows
Virtual servers in the cloud with a wide range of instance types.
Fully managed container orchestration service.
Managed Kubernetes service for container orchestration.
Virtualized GPU instances with flexible configurations and secure SSH access
Dedicated GPU clusters for maximum performance and control
Pay for compute capacity by the second with no long-term commitments.
Use spare EC2 capacity at up to 90% off the On-Demand price.
Save up to 72% compared to On-Demand pricing with a 1 or 3-year commitment.
Save up to 72% on compute usage with a 1 or 3-year commitment to a consistent amount of usage.
Flexible pricing starting at $0.30 per hour with payment based solely on usage
Pre-funded account balance system for streamlined resource management
Create an AWS account to access the cloud platform.
Select from EC2, Lambda, or container services based on your workload needs.
Configure and launch your first compute instance or container.
Configure security groups and access controls for your resources.
Use AWS CloudWatch and Compute Optimizer to monitor performance and reduce costs.
Sign up for Sesterce Cloud platform access
Fund your account with credits for pay-as-you-go billing
Choose your GPU type and configuration, launch in just a few clicks
30+ regions and 100+ availability zones worldwide.
Basic (free), Developer, Business, Enterprise support plans with varying response times and features. Extensive documentation, forums, and training resources.
Multiple regions across Europe with focus on renewable energy datacenters
Documentation available, self-service console, REST API