amazee.ai, a Mirantis company, announced the launch of the amazee.ai Private AI Gateway, an OpenAI-compatible API that ensures organizations can deploy AI applications with multiple frontier and open weight AI models like GPT, Claude, Gemini, or Kimi securely in specific regions with no retention of data. This assures complete privacy and sovereignty of data so that it cannot be used by others for training AI models.

Intended for enterprises operating in regulated or security-sensitive industries such as financial services, healthcare, government, and legal services, amazee.ai Private AI Gateway provides organizations with a single OpenAI-compatible endpoint that routes requests to multiple AI models while maintaining private, isolated tenants. It provides enterprise-grade compliance and – unlike any competitive offering – is ISO 27001 and SOC 2 Type II certified.

Because the amazee.ai gateway is OpenAI-compatible, development teams can continue using existing SDKs, frameworks, and applications without rewriting integrations or modifying AI workflows.

“We’re addressing the biggest issue in enterprise AI adoption – data governance of sensitive corporate data, along with unauthorized use, to maintain operational control and avoid data leakage,” said Michael Schmid, co-founder and managing director of amazee.ai. “We built the amazee.ai Private AI Gateway as an enterprise trust layer: an OpenAI-compatible gateway that gives organizations sovereignty, audit readiness, and stronger security controls by default.”

Unlike many other AI routing services, the amazee.ai Private AI Gateway is designed so customers can select their designated region. The platform supports sovereign-region pinning – where workloads remain in the chosen region – including the U.S., EU GDPR region's 30 nations, as well as countries that include Australia, Germany, Switzerland, and the U.K, enabling organizations to align deployments with residency and compliance requirements. For organizations with specialized architecture requirements, amazee.ai can also deploy dedicated, individual AI gateways, including within a customer's own infrastructure.