One model gateway across clouds: LiteLLM on Cloud Run and Azure with zero API keys A developer built a LiteLLM-based model gateway deployed on both Google Cloud Run and Azure that serves Gemini and Azure OpenAI through a single OpenAI-compatible endpoint without storing any provider API keys. Authentication relies on Microsoft Entra Agent ID tokens verified via a custom LiteLLM auth hook against JWKS, with per-agent model allow-lists enforced before any provider call. In a demo, shutting down the gateway in one cloud caused the agent to answer through the other within nine seconds. As of November 2026. All identifiers in this post are examples. In part 1 https://dev.to/migas moreno/google-agent-platform-across-clouds-with-spiffe-zero-secrets-between-google-cloud-and-microsoft-1hjg two AI agents, one on Google Cloud and one on Azure, learned to call each other without any stored secret. Agents also call models. This post covers that half: a model gateway that runs in both clouds, serves Gemini and Azure OpenAI from either side, and holds no API key for any of it. During a demo we switched off the gateway in one cloud. Nine seconds later the agent answered through the other one. An agent can call a model directly. With two agents that is fine. With fifty it gets uncomfortable: A model gateway fixes the three at once. Agents talk to one endpoint, and the rules and the usage records live there. We used LiteLLM https://docs.litellm.ai/ because it speaks to both Vertex AI and Azure OpenAI behind one OpenAI-compatible API. The catch is that a gateway usually introduces two new kinds of secret: the keys it holds for the model providers, and the keys it hands out to its callers. We wanted neither. There is one LiteLLM in each cloud, with the same configuration: Each gateway is connected to both model families. The one on Azure can call Gemini, and the one on Google Cloud can call Azure OpenAI. An agent uses the gateway of its own cloud and gets the same catalogue either way. The model list is the same file on both sides: model list: - model name: gpt-4.1-mini litellm params: model: azure/gpt-4.1-mini api base: https://