X
Akamai acquires Fermyon to combine WebAssembly function-as-a-service (FaaS) with Akamai’s globally distributed platform. Read news
Login
Login Close
Control Center
Access the Akamai platform
Login Close
Cloud Manager
Manage your cloud resources
Login
Login Close
Control Center
Access the Akamai platform
Login Close
Cloud Manager
Manage your cloud resources
Try Akamai
Under Attack?

GPU

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

Create account
Contact us
Book AI consult

Be among the first to access NVIDIA™ RTX PRO 6000 Blackwell GPUs optimized for AI inference.

Join waitlist

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 lets you choose the right GPU for your workload. 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 NVIDIATM 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. 

See details

Choose the right GPU type for your needs

Akamai offers multiple GPU options. Choose between NVIDIA RTX PRO Servers, featuring NVIDIA RTX PRO 6000 Blackwell Server Edition® GPUs, and Quadro® RTX line of GPUs running NVIDIA’s latest generation of GPU architecture.

See NVIDIA GPUs
Join waitlist

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 dedicated GPU resources.

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 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 or Dedicated CPU 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

Explore other compute plans

Accelerated Compute

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

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
Se muestra a una persona con gafas negras y la cara iluminada por la luz de la pantalla de un ordenador

Book your AI consultation today

AI is moving from the lab to production, and the pressure is on to deliver faster, smarter, and more secure experiences. Whether you’re optimizing inference, scaling models, or reducing latency, we’re here to help you bring AI to life ... at the edge.

  • See how to deploy and scale AI inference closer to your users.
  • Learn how edge native infrastructure improves performance.
  • Explore how to cut costs while maintaining enterprise-grade security.

Book an AI consultation to unlock what’s possible!

Thank you for your submission.

One of our AI consultants will be in touch soon to set up time to speak with you.