Learning
Center

LiteLLM vs OpenRouter: Gateway vs Aggregator Explained

LiteLLM is an open source gateway you deploy and run while OpenRouter is a hosted aggregator with 500+ models and a fee on credit purchases. Compare data path, cost, and operations, plus when teams move to an enterprise AI gateway such as Tetrate Agent Router Enterprise.

What Is an AI Egress Gateway?

An AI egress gateway is the control point for calls leaving your cluster for model providers and MCP servers. The gateway decides which destinations your agents can reach, adds provider keys on the way out, and counts tokens per team.

What Is an AI Ingress Gateway?

An AI ingress gateway is the entry point for requests coming into your AI agents and self-hosted models. The gateway checks who is calling and how many tokens the caller can spend before the request reaches your agent or your GPUs.

AI Ingress vs. AI Egress: Two Directions of AI Traffic, One Control Point

AI ingress controls requests coming into your agents and self-hosted models. AI egress controls calls leaving your cluster for models and MCP servers. One Envoy data plane can govern both directions.

Gateway API Egress: What GEP-4488 Means for AI Traffic

Gateway API has no stable egress API. GEP-4488 proposes a Backend resource for external destinations, and the GEP remains provisional. Your agents need egress control now.

Kubernetes Egress for AI Agents: NetworkPolicy, Egress Gateways, and AI Gateways Compared

Kubernetes gives you NetworkPolicy, service mesh egress gateways, and AI gateways for outbound agent traffic. NetworkPolicy blocks by IP and port. An AI gateway controls by model, token, tool, and team.

How to Keep LLM API Keys Out of Application Code

Provider keys copied into every app create sprawl and hard rotation. The gateway should keep provider keys and add the keys on the way out, so apps hold a gateway key and no provider key.

LLM Cost Chargeback by Team and Agent

Your finance team cannot charge back AI spend until token counts tie to a team or agent at the point where traffic leaves. Token attribution at the egress point makes chargeback exact.

MCP Egress Control: Decide Which Tools Your Agents Can Reach

MCP tool calls leave your cluster and reach outside systems. Treat MCP calls as egress, with an allow list, authentication, and audit on each call.

Envoy AI Gateway becomes Agent Router and joins the Agentic AI Foundation

Learning
Center

LiteLLM vs OpenRouter: Gateway vs Aggregator Explained

What Is an AI Egress Gateway?

What Is an AI Ingress Gateway?

AI Ingress vs. AI Egress: Two Directions of AI Traffic, One Control Point

Gateway API Egress: What GEP-4488 Means for AI Traffic

Kubernetes Egress for AI Agents: NetworkPolicy, Egress Gateways, and AI Gateways Compared

How to Keep LLM API Keys Out of Application Code

LLM Cost Chargeback by Team and Agent

MCP Egress Control: Decide Which Tools Your Agents Can Reach

Ready to enhance your
network
with more
intelligence?

Envoy AI Gateway becomes Agent Router and joins the Agentic AI Foundation

Learning Center

LiteLLM vs OpenRouter: Gateway vs Aggregator Explained

What Is an AI Egress Gateway?

What Is an AI Ingress Gateway?

AI Ingress vs. AI Egress: Two Directions of AI Traffic, One Control Point

Gateway API Egress: What GEP-4488 Means for AI Traffic

Kubernetes Egress for AI Agents: NetworkPolicy, Egress Gateways, and AI Gateways Compared

How to Keep LLM API Keys Out of Application Code

LLM Cost Chargeback by Team and Agent

MCP Egress Control: Decide Which Tools Your Agents Can Reach

Ready to enhance your network with more intelligence?

Learning
Center

Ready to enhance your
network
with more
intelligence?