A layer that picks the cheapest capable model for each request, saving cost and latency.
1 min readupdated 2026-06-22
/ quick answer
An AI router inspects the incoming prompt and dispatches it to the smallest model that can handle it — a small local model for classification, a mid-tier for drafting, a frontier model only for hard reasoning. Products: OpenRouter, Portkey, LiteLLM.
A layer that picks the cheapest capable model for each request, saving cost and latency. An AI router inspects the incoming prompt and dispatches it to the smallest model that can handle it — a small local model for classification, a mid-tier for drafting, a frontier model only for hard reasoning. Products: OpenRouter, Portkey, LiteLLM. In practice: A support agent routes 80% of tickets to GPT-4o mini, 15% to GPT-4o, and 5% to Claude Opus, cutting bill by ~70% with no quality drop. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
An AI router inspects the incoming prompt and dispatches it to the smallest model that can handle it — a small local model for classification, a mid-tier for drafting, a frontier model only for hard reasoning. Products: OpenRouter, Portkey, LiteLLM.
Example
A support agent routes 80% of tickets to GPT-4o mini, 15% to GPT-4o, and 5% to Claude Opus, cutting bill by ~70% with no quality drop.
An AI router inspects the incoming prompt and dispatches it to the smallest model that can handle it — a small local model for classification, a mid-tier for drafting, a frontier model only for hard reasoning. Products: OpenRouter, Portkey, LiteLLM.
What is an example of AI Router?
A support agent routes 80% of tickets to GPT-4o mini, 15% to GPT-4o, and 5% to Claude Opus, cutting bill by ~70% with no quality drop.
Why does AI Router matter for AI and automation?
A layer that picks the cheapest capable model for each request, saving cost and latency. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.