Akamai launches managed AI inference and an agent sandbox on Akamai Cloud

Akamai has added two managed AI services to Akamai Cloud, Akamai Inference and Akamai Agent Sandbox, both in beta, and expanded its GPU fleet with NVIDIA Blackwell Ultra clusters.

Akamai Inference gives enterprises managed access to open-weight and custom models through OpenAI-compatible APIs, so existing applications should move without rewrites. Customers can choose serverless pay-per-use inference or dedicated deployments. The launch catalogue has 12 open-weight models from 8 billion to 2.8 trillion parameters, including NVIDIA Nemotron 3 Ultra, OpenAI gpt-oss-120b and Google Gemma 4, plus embedding models for retrieval-augmented generation. Requests run across Akamai's global network, which the company says cuts latency.

Akamai Agent Sandbox gives AI agents, and the code they write, a restricted place to run. Agents run on Akamai Functions and generated code runs in its own isolated environment, separate from the agent's runtime. It is an open-source component of the Spin framework and uses WebAssembly isolation to limit compute, memory, outbound connections and system capabilities. Akamai notes that agent isolation is converging on several models, from microVMs to policy-enforced containers to WebAssembly, and says developers can pick the one that suits the workload. It also plans to add controls over what agents can reach and what can reach them.

On hardware, Akamai's dedicated GPU fleet now includes Blackwell Ultra clusters, each eight-GPU node carrying 288 GB of HBM3e memory per GPU, 2.3 TB in total. The company is preparing its data centres for the NVIDIA Vera Rubin platform in 2027. Customers who want a Blackwell B300 cluster need to contact Akamai Sales for availability.

Adam Karon, Chief Operating Officer and GM of Akamai Cloud, said: "They want to build, run, and protect AI on the same platform." Jon Alexander, Senior Vice President of Cloud Technology at Akamai, said: "Enterprises should not have to choose between speed and control when they put AI into production".

Akamai says the platform spans dense GPU and CPU clusters in core regions and more than 4,350 edge locations, and that it has already secured multiyear Akamai Cloud contracts worth more than $14 billion.

To stay across the latest in cloud, AI and enterprise tech analysis from Compare the Cloud, subscribe to our weekly newsletter at https://www.comparethecloud.net/newsletter

More News