AI Management

The AI Model entity gives clients a single endpoint for one or more upstream LLMs through AI Gateway.

The AI Model Provider entity lets you securely store and manage credentials for connecting to upstream LLM services.

The AI MCP Server entity connects MCP-compatible clients to your backend systems.

The AI Agent entity proxies A2A and HTTP agents through AI Gateway.

A user is a person who signs in to AI Management. An admin, an org chart import, or just-in-time provisioning at first sign-in adds each user.

A group is a list of users and agents that share the same rules.

An identity provider is an external service, like Okta or Auth0, that signs the tokens users present when they sign in.

Token Vault stores credentials so that AI Gateway can call external services on behalf of a caller.

A virtual key is an API key that lets a caller use AI Gateway.

AI Management roles control who can create and manage AI Models, AI MCP Servers, AI Agents, and virtual keys, and who can view cost data.

Kong Identity centralizes authentication in Konnect.

A principal represents an external client, workload, or human authenticating to AI Gateway.

An AI Auth Strategy lets you declare an inbound authentication mechanism at the gateway level and attach it to specific AI Models, AI Agents, or AI MCP Servers.

Monitor traffic, latency, errors, and cost for AI Models, AI MCP Servers, and AI Agents.

Track your organization’s AI model spend, budgets, and alerts across users, groups, models, and teams.

A budget in AI Cost Management tracks AI spend against a limit and sends alerts as spend approaches it.

AI Gateway calculates the cost of every request to an LLM provider, matching what the provider bills.