---
title: Akamai Launches AI Inference and Agent Sandbox for Akamai Cloud
url: https://www.dataloco.com/en/akamai-launches-ai-inference-and-agent-sandbox-for-akamai-cloud
published: 2026-10-30T16:21:16+00:00
language: en
section: AI
source: https://www.techtalkthai.com/akamai-launches-inference-and-agent-sandbox-on-akamai-cloud/
organizations: Akamai, NVIDIA
publisher: Dataloco
---

# Akamai Launches AI Inference and Agent Sandbox for Akamai Cloud

Akamai has launched Akamai Inference, a managed model serving service, and Akamai Agent Sandbox, an isolated environment for running AI Agent code on Akamai Cloud.

Akamai Inference allows organizations to access open-weight and custom models through an API compatible with OpenAI. At launch, 12 open-weight models are available, ranging from 8 billion to 2.8 trillion parameters, including Google Gemma 4, OpenAI gpt-oss-120b, and NVIDIA Nemotron 3 Ultra. The service also provides embedding models for Retrieval-Augmented Generation. Customers can choose between serverless billing based on usage or dedicated deployment. Models can retrieve organizational data from object storage and managed databases on Akamai Cloud, or from connected public and private clouds.

Akamai Agent Sandbox provides a space to run AI Agents and the code they generate. The agents operate on Akamai Functions, while the generated code runs in an environment separate from the agent runtime. This sandbox is an open source component of the Spin framework and utilizes WebAssembly isolation to define limits for system capability, outbound connections, memory, and compute. Developers can choose architectures including dedicated CPU, managed Kubernetes, or serverless options via Akamai Functions at the edge and core, as well as infrastructure accelerated by NVIDIA.

To support these services, Akamai has expanded its GPU fleet with NVIDIA Blackwell Ultra GPU clusters. Each Blackwell Ultra node contains 8 GPUs with 288 GB of HBM3e memory per GPU, totaling 2.3 TB. These are intended for frontier models and workloads involving agentic tasks, chain-of-thought reasoning, and test-time scaling. The fleet also includes NVIDIA RTX PRO 6000 Blackwell Server Edition for low latency inference. Akamai is preparing data centers for the NVIDIA Vera Rubin platform in 2027.

Akamai Cloud currently provides CPU and GPU clusters in core regions and over 4,350 edge locations. The company has secured multi-year contracts for Akamai Cloud totaling more than 14 billion dollars. Both Akamai Inference and Akamai Agent Sandbox are currently available in beta.

## This story in other languages

- [Español](https://www.dataloco.com/es/akamai-lanza-servicios-de-inferencia-y-entorno-aislado-para-agentes-de-inteligencia-artificial-en-su-nube)
- [Português (Brasil)](https://www.dataloco.com/pt-br/akamai-lanca-akamai-inference-e-agent-sandbox-para-expandir-servicos-de-inteligencia-artificial)
- [עברית](https://www.dataloco.com/he/akamai)
- [Deutsch](https://www.dataloco.com/de/akamai-fuhrt-akamai-inference-und-agent-sandbox-fur-die-akamai-cloud-ein)
- [Italiano](https://www.dataloco.com/it/akamai-lancia-akamai-inference-e-agent-sandbox-per-potenziare-lintelligenza-artificiale-su-akamai-cloud)
- [Nederlands](https://www.dataloco.com/nl/akamai-lanceert-akamai-inference-en-agent-sandbox-voor-kunstmatige-intelligentie-op-akamai-cloud)
- [Polski](https://www.dataloco.com/pl/akamai-wprowadza-akamai-inference-i-akamai-agent-sandbox-na-akamai-cloud)