Google for Developers Blog - News about Web, Mobile, AI and Cloud

Google Cloud API Gateway now offers a model routing feature in Public Preview, allowing developers to dynamically route traffic to models like Gemini, Claude, or OpenAI OSS-GPT without hardcoding endpoints or managing open-source proxies. Developers can easily configure these routing rules directly within their OpenAPI 3.x specifications by mapping virtual model names to specific backend targets on a shared host. Once deployed, the Gateway acts as a serverless ingress layer that accepts standard OpenAI-compatible requests, automatically transcodes the payload to the native schema of the target model, and routes the traffic on the fly.

Overview of model routing  |  API Gateway  |  Google Cloud Documentation

Model routing for API Gateway is a managed traffic management layer that accepts OpenAI-compatible prompt requests, transcodes them in-flight, and routes them to specific Gemini Enterprise Agent Platform models. Model routing acts as a managed alternative to client-side proxies such as LiteLLM, providing centralized infrastructure to manage the lifecycle of AI agents.

OpenAPI 3.x Extensions in API Gateway  |  Google Cloud Documentation

API Gateway accepts a set of Google-specific extensions to the OpenAPI specification that configure the behaviors of the gateway. These extensions allow you to specify API management settings, authentication methods, quota limits, and backend integrations directly within your OpenAPI document. Understanding these extensions helps you tailor your service behavior and integrate with API Gateway features.

AI gateway capabilities  |  Apigee  |  Google Cloud Documentation

Learn how to use Apigee AI gateway features to govern, optimize, and scale AI traffic.

Google Gemini Enterprise: Vertex AI Rebrand at Cloud Next 26 | AI Automation Global

Google rebranded Vertex AI as Gemini Enterprise Agent Platform at Cloud Next 26. A2A protocol v1.0, Workspace Studio, 200+ models, 150 deployments.

Google Sunsets Vertex AI, Launches Agent Control Plane | Awesome Agents

Google replaced Vertex AI with the Gemini Enterprise Agent Platform at Cloud Next 2026 - a full-stack control plane that assigns every agent a cryptographic ID and routes all tool calls through a central policy gateway.

Google expands Gemini Enterprise, consolidates Vertex AI services to simplify agent deployment

Gemini Enterprise Agent Platform aims to help organizations to build, scale, govern, and optimize AI agents

Agent Gateway overview  |  Gemini Enterprise Agent Platform  |  Google Cloud Documentation

Secure and govern AI agent connectivity with Agent Gateway. Centralize access policies, mTLS, and Model Context Protocol (MCP) security for agent-to-agent and agent-to-tool interactions across diverse runtimes.

docs: Rebrand Vertex AI to Gemini Enterprise Agent Platform (#14472) · googleapis/google-cloud-go@4e3f219

Updated README to reflect rebranding of Vertex AI to Gemini Enterprise Agent Platform.

Pricing | OpenRouter

Transparent pricing for OpenRouter. Pay only for what you use with access to 400+ AI models. Free tier, Pay-as-you-go, and Enterprise plans available.

OpenAI Model Spec

The Model Spec specifies desired behavior for the models underlying OpenAI's products (including our APIs).

LMRouter/lmrouter

An open-source, all-in-one AI API router

Issue · BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr...

BerriAI/litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

OpenAI SDK Integration - OpenRouter SDK Support

Using OpenRouter with OpenAI SDK

Introducing Gemini Enterprise Agent Platform | Google Cloud Blog

Gemini Enterprise Agent Platform is our new platform to build, scale, govern, and optimize agents. It integrates the model selection, model building, and agent building capabilities of Vertex AI, with new features for agent integration, DevOps, and orchestration, and security.