AI gateways & model routers
AI gateways & model routers covers services that put one address in front of many model providers and route each request between them.
In brief
AI gateways & model routers, in brief.
What it isAI gateways & model routers covers services that put one address in front of many model providers and route each request between them.
Where it sitsOne of 13 categories in the Inference and serving layer. Inference and serving is everything that turns a trained model into a running service: hosted inference providers, gateways that route between them, serving engines, and the tools that make models smaller and faster.
What we track34 products, including agentgateway, Apache APISIX AI plugins, Apigee (AI gateway features), AWS Bedrock Intelligent Prompt Routing and Azure API Management AI gateway.
The products
34 products in AI gateways & model routers.
Each name opens a search for that product in our index.
ProductMakerIts own site
From our census of 2026-11-08. A product listed here is one that belongs in this category; the search answer says whether we have checked it.
Questions
AI gateways & model routers, answered.
What is AI gateways & model routers in AI infrastructure?AI gateways & model routers covers services that put one address in front of many model providers and route each request between them.
Which layer of AI infrastructure is AI gateways & model routers in?AI gateways & model routers is in the Inference and serving layer. Inference and serving is everything that turns a trained model into a running service: hosted inference providers, gateways that route between them, serving engines, and the tools that make models smaller and faster.
Which products are in AI gateways & model routers?We track 34 products in AI gateways & model routers, including agentgateway, Apache APISIX AI plugins, Apigee (AI gateway features), AWS Bedrock Intelligent Prompt Routing, Azure API Management AI gateway, Bifrost, Cloudflare AI Gateway and Databricks Mosaic AI Gateway. The full list is on this page.
Inference and serving
The other categories in Inference and serving.
Batch inferenceGenerative media inference platformsGenerative media workflow toolsInference benchmarking & load testingInference kernels & attention librariesInference providersKV-cache & prompt-caching infrastructureLoRA serving & adapter hubsModel compilers & graph optimizersOn-device / edge runtimesQuantization / optimizationServing engines & model servers