Apigee Operator for Kubernetes and GKE Inference Gateway integration for Auth and AI/LLM policies- Google Developers Blog

This post details the integration of the Apigee Operator for Kubernetes with the GKE Inference Gateway. This integration leverages the GCPTrafficExtension resource to enable Apigee to enforce API governance policies (e.g., API keys, quotas, rate limiting, OpenAPI spec validation) on AI inference workloads served through GKE Inference Gateway. It also highlights the GKE Inference Gateway's features for optimized load balancing, dynamic LoRA fine-tuned model serving, and integrated AI safety with Model Armor.