X
+1-8774252624
+1-8774252624
Login
Control Center
Access the Akamai platform
Cloud Manager
Manage your cloud resources
Try Akamai
Under Attack?
Login
Control Center
Access the Akamai platform
Cloud Manager
Manage your cloud resources

GPU

Access powerful on-demand NVIDIA™ GPUs with predictable, cost-effective pricing

Create account
Contact us

Deploy the right GPU to meet your application’s needs and budget

Sustainably test and scale compute-intensive workloads on Akamai’s GPU cloud services without draining your infrastructure budget. Akamai Cloud’s NVIDIA™ GPUs are structured to support your workloads and keep you building. Easily deploy cloud-based GPUs when needed. Predictable pricing and low-cost egress help you manage costs and scale machine learning, AI workloads, data processing, and other high-performance computing with confidence.

Build and scale AI inferencing

Combine the computational power of NVIDIA GPUs with Akamai’s powerful edge network to deliver real-time insights from AI models directly to your applications — AI inferencing that’s both scalable and closer to end users. 

Learn more

Choose the right GPU type for your needs

We’re expanding our GPU availability. Choose between NVIDIA GPUs optimized for lightweight AI inference and media workloads (RTX 4000 Ada) or deep learning and data science price-performance (Quadro RTX 6000). Looking for another type of GPU? Let us know.

Contact us

Deploy on-demand GPUs starting at $0.52 per hour

Empower engineers, scientists, and artists with parallel computing power for high-performance applications and artificial intelligence workloads without contracts, hidden costs, or the overhead of maintaining your own data center.

Reduce AI inference costs by up to 86%

As demonstrated using the Stable Diffusion model on Akamai Cloud, AI inference costs can be reduced by up to 86%. Discover strategies to optimize performance and lower expenses.

Download white paper

Key features

Dedicated GPU resources

Get strong, predictable performance with GPU and CPU resources 100% allocated to your plan.

25x media encoding performance

RTX 4000 Ada GPU plans are built for media workloads, with 2x encoding, 2x decoding, and 1x AV1 encode/decode engines per card.

Superior AI inference performance

Deliver up to 60% lower latency and 3x higher throughput for up to 86% less cost with image generation and AI workloads on RTX 4000 Ada GPUs compared to equivalent hyperscaler GPUs.

Features

  • Low, predictable GPU pricing starting at $0.52 per hour for RTX 4000 Ada GPU plans
  • Configure Backups to retain data with automated daily, weekly, and biweekly snapshots
  • Add GPU nodes to managed Kubernetes clusters with LKE
  • Easily resize a Shared CPU, Dedicated CPU, Premium CPU, or High Memory instance to a GPU instance
  • Save up to 90% on egress with Akamai Cloud ($0.005 per GB in most regions)
  • Set up CI/CD pipelines with custom images, Terraform provider, and more
  • Access full documentation support to install NVIDIA CUDA toolkit to get started
  • Manage infrastructure flexibly with our UI, API, CLI, and developer tool integrations
  • 24/7/365 email and phone support for all customers

GPU pricing plans

Discover flexible GPU pricing with cost-effective scaling to meet your workload demands.

See pricing

*See Promotion Redemption Rules and Conditions

Explore other compute plans

Accelerated Compute

Optimize performance with ASICs and NETINT VPUs for faster media transcoding.

View product details

Premium CPU

Premium instances provide a minimum hardware model for consistent performance on dedicated resources.

View product details

Essential Compute

Match Shared CPU, Dedicated CPU, or High Memory compute plans to your applications’ needs and budget.

View product details

Accessible GPU Instances Unleash Millions of Adventurers

Akamai helps Hero Forge give their tabletop gamers the power to design and 3D-print custom figurines.

Read customer story

See if you qualify for up to US$5,000 in cloud credits

We’re here to help you with large-scale deployments, migrations, app optimization, architecture assessments, security and reliability audits, and much more. For support or account issues, please visit our support page.

Thank you for your submission.