Единый шлюз моделей в облаках: LiteLLM на Cloud Run и Azure без API-ключей
DEV · 15.11.2026 · 22:23
В статье описывается концепция, в которой два AI-агента взаимодействуют через шлюз моделей, работающий в облаках Google и Azure, без использования API-ключей.
Оригинал
One model gateway across clouds: LiteLLM on Cloud Run and Azure with zero API keys
As of November 2026. All identifiers in this post are examples. We built a proof of concept with two AI agents: one on Google Cloud, in Agent Runtime, and one on Azure, in Microsoft Foundry. Each agent has its own identity in Microsoft Entra Agent ID and stores no secret. Agents call models. This post covers how ours reach them: 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 gatew