Add Traffic Controls

After the request path is working, traffic controls let you decide how that path should behave under real application traffic. They protect shared model capacity, enforce spend policy, block unsafe content, and cache repeat responses.

Some controls run before AISIX calls the provider. Others run after the provider returns a response. The request path looks like this:

ApplicationCaller request

AISIX AI Gateway

Before provider

Caller API key

Model alias

Request controlsRate limits, budgets, input guardrails

Cache lookupHit returns early; miss calls upstream

After provider

Response controlsOutput guardrails

Provider upstreamCache miss path

Response to callerSame model alias

Request-side controls can stop a request before AISIX calls the provider. Rate limits, budgets, and input guardrails decide whether the request is allowed to continue. Cache lookup can return a stored response on a hit; on a miss, AISIX calls the provider.

After the provider returns, output guardrails can inspect the response before AISIX returns it to the caller.

Start with the control that matches the policy you need first. Add more controls after you understand where each one runs in the request path.