Akamai Launches AI Inference Service and Agent Execution Environment
Akamai Technologies, Tuesday, October 27th, 2026
Akamai launches Akamai Inference, a managed model-serving service, and Agent Sandbox, an isolated runtime for AI agent code.
Akamai introduced two AI products on Akamai Cloud, both in beta.
Akamai Inference is a managed model-serving service offering open-weight and custom models through OpenAI-compatible APIs, with serverless pay-per-use or dedicated deployments and a launch catalog of 12 open-weight models plus embedding models for RAG.
Akamai Agent Sandbox runs agent-written code in an isolated WebAssembly environment that limits compute, memory, outbound connections, and system access, and is an open source part of the Spin framework.
Akamai also expanded its GPU fleet with NVIDIA Blackwell Ultra clusters and plans to prepare data centers for NVIDIA Vera Rubin in 2027.