Google Cloud API Gateway 推出统一模型路由功能，支持 Gemini、Claude 与 OpenAI OSS-GPT

在构建 AI 应用程序时，开发者需要自由地将流量路由到最适合任务的模型，而无需硬编码端点或管理开源代理。Google Cloud API Gateway：https://docs.cloud.google.com/api-gateway/docs 现已在公开预览中提供模型路由功能，以解决此问题。它提供了一个轻量级、无服务器的入口层，可接受与 OpenAI 兼容的请求，并动态将其路由到 Gemini、Claude 或 OpenAI OSS-GPT。

API Gateway 可独立使用，以实现简单的速率限制和令牌追踪，或者无缝地与 Gemini Enterprise Agent 平台配合使用。例如，您可以通过 Agent Gateway 路由您的代理出口流量以进行严格的安全管理，然后将请求传递给 API Gateway，以处理到 Google 托管的 LLM 的动态路由。这是配置路由逻辑的分步指南。

设置模型路由逻辑只需几个步骤：

注意：由单个路由器引用的所有后端必须共享同一个主机（例如 aiplatform.googleapis.com）。路由会在该共享的 Vertex 主机上选择不同的模型和路径——它不会跨不同主机进行路由。

2. 部署网关：部署更新后的 API 配置，使网关处于活动状态并准备处理流量。

3. 发送标准请求：您的应用程序只需发送标准的 OpenAI POST /v1/chat/gemini-claude 或 POST /v1/chat/openai-gemini 请求。网关会拦截请求、将负载转码为后端的本地模式，并实时路由。例如（请为 $API_KEY 和 my-gateway-url.com 使用适当的值）：

API Gateway 的模型路由现已在公开预览中提供。要停止管理代理并开始统一您的 AI 流量，请查看我们的文档：https://docs.cloud.google.com/api-gateway/docs/model-routing-overview，以便今天就部署您的首个模型路由器。

如何使用 Google 微基准测试评估 TPU 性能

使用会话感知负载均衡扩展实时 AI 代理

在TPU上运行Ray，第2部分：Ray人工智能库

Gemini Enterprise Agent 平台中的代理和模型评估现已通用可用

When building AI applications, developers need the freedom to route traffic to the best model for the job without hardcoding endpoints or managing open-source proxies. Google Cloud API Gateway：https://docs.cloud.google.com/api-gateway/docs now offers model routing in Public Preview to solve this. It provides a lightweight, serverless ingress layer that accepts OpenAI-compatible requests and dynamically routes them to Gemini, Claude, or OpenAI OSS-GPT.

API Gateway can be used standalone for simple rate limiting and token tracking, or paired seamlessly with the Gemini Enterprise Agent Platform. For example, you can route your agent's egress through Agent Gateway for strict security governance, and then pass the request to API Gateway to handle dynamic routing to Google-hosted LLMs. Here is a step-by-step guide on how to configure your routing logic.

Setting up your model routing logic takes just a few steps:

Note: All backends referenced by a single router must share the same host (for example, aiplatform.googleapis.com). Routing selects a different model and path on that shared Vertex host — it does not route across different hosts.

2. Deploy the Gateway: Deploy your updated API config so the Gateway is active and ready to process traffic.

3. Send standard requests: Your application simply sends a standard OpenAI POST /v1/chat/gemini-claude or POST /v1/chat/openai-gemini request. The Gateway intercepts it, transcodes the payload to the native schema of the backend, and routes it on the fly. As an example (use appropriate values for $API_KEY and my-gateway-url.com ) :

Model routing is now available in Public Preview for API Gateway. To stop managing proxies and start unifying your AI traffic, check out our documentation：https://docs.cloud.google.com/api-gateway/docs/model-routing-overview to deploy your first model router today.

How to use Google microbenchmarks for evaluating TPU performance

Scaling real-time AI agents with session-aware load balancing

Run Ray on TPU, Part 2: Ray AI libraries

Agent and Model Evaluations in Gemini Enterprise Agent Platform are now GA