A unified API for AI model routing- Google Developers Blog

What this post added

This post introduces model routing in Google Cloud API Gateway, a new capability that allows developers to dynamically route OpenAI-compatible requests to different AI models (Gemini, Claude, OpenAI OSS-GPT) using an OpenAPI 3.x specification. It details how to configure routing rules using the `x-google-api-management` extension, deploy the gateway, and send standard requests. The feature supports routing between models hosted on the same backend host (e.g., aiplatform.googleapis.com) and provides examples of OpenAPI configurations and curl commands for testing.