TLDR: Akamai Technologies has launched its Inference Cloud, a distributed platform designed to extend AI inference capabilities from central data centers to the edge of the internet. This initiative, powered by NVIDIA’s advanced AI infrastructure, aims to deliver low-latency, real-time AI processing globally, supporting the next generation of agentic and physical AI applications.
CAMBRIDGE, Mass. – Akamai Technologies, Inc. (NASDAQ:AKAM) announced on October 28, 2025, the official launch of its Akamai Inference Cloud, a groundbreaking platform poised to redefine the deployment and utilization of artificial intelligence. This new offering expands AI inference from traditional core data centers directly to the internet’s edge, bringing intelligent, agentic AI inference closer to users and devices globally.
The Akamai Inference Cloud is purpose-built for low-latency, real-time edge AI processing on a global scale. The platform leverages Akamai’s extensive expertise in globally distributed architectures and integrates NVIDIA’s cutting-edge Blackwell AI infrastructure. Specifically, it utilizes NVIDIA RTX PRO Servers, featuring NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, NVIDIA BlueField-3 DPUs, and NVIDIA AI Enterprise software, all within Akamai’s distributed cloud computing infrastructure and vast global edge network, which encompasses over 4,200 locations worldwide. Future plans include incorporating the recently announced NVIDIA BlueField-4 DPU to further enhance data access and AI inference workloads from core to edge.
Dr. Tom Leighton, Akamai CEO and co-founder, emphasized the strategic importance of this move, stating, “The next wave of AI requires the same proximity to users that allowed the internet to scale to become the pervasive global platform that it is today. Akamai solved this challenge before – and we’re doing it again. Powered by NVIDIA AI infrastructure, Akamai Inference Cloud will meet the intensifying demand to scale AI inference capacity and performance by putting AI’s decision-making in thousands of locations around the world, enabling faster, smarter, and more secure responses.”
Jensen Huang, founder and CEO of NVIDIA, echoed this sentiment, adding, “Inference has become the most compute-intensive phase of AI — demanding real-time reasoning at planetary scale. Together, NVIDIA and Akamai are moving inference closer to users everywhere, delivering faster, more scalable generative AI and unlocking the next generation of intelligent applications.”
The Akamai Inference Cloud is designed to address critical needs across various AI applications:
Extending Enterprise AI Factories to the Edge: It decentralizes data and processing, routing requests to optimal models using Akamai’s distributed edge locations. This enables smart agents to adapt instantly to user location, behavior, and intent, facilitating real-time negotiation, purchasing, and transaction optimization.
Enabling Streaming Inference and Agents: The edge-native architecture provides virtually instant responses for agentic AI workflows, which often require multiple sequential inferences. This capability is crucial for applications demanding human-like responsiveness, such as fraud detection, accelerating secure payments, and high-speed industrial edge decisions.
Enabling Real-Time Physical AI: For systems like autonomous vehicles, industrial robots, and smart city infrastructure that require millisecond-precision decision-making, the platform allows physical AI to process sensor data, make safety decisions, and coordinate actions at the speed of the physical world.
The platform also accelerates time to value by offering an intelligent orchestration layer that automatically routes AI tasks to optimal locations, managing infrastructure complexity through a unified platform. Routine inference executes instantly at the edge via NVIDIA’s NIM microservices, while more sophisticated reasoning leverages centralized AI factories.
Also Read:
- Check Point and NVIDIA Unveil AI Cloud Protect for Enterprise AI Security
- CrowdStrike and NVIDIA Unveil Autonomous AI Agents for Advanced Cyber Defense
Akamai Inference Cloud is currently available in 20 initial global locations, with further expansion plans already in motion. Akamai, a leading cybersecurity and cloud computing company, aims to leverage its distributed platform to provide industry-leading reliability, scale, and expertise for global enterprises embracing AI.
