For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.
Resiliency
Configure retries, timeouts, rate limits, and mirroring for fault tolerance.
Simulate failures, disruptions, and adverse conditions to test that your gateway and apps continue to function.
Tip
The guides in this section show example configuration for different types of policies. Policies are applied to routes, which are part of a listener on a bind.
binds:
- port: 3000
listeners:
- routes:
- policies:Mirroring
Send copies of requests to alternative backends for shadow testing.
Rate limiting
Enforce budget and spend limits per key by controlling request and token usage.
Retries
Configure automatic retry attempts for failed backend requests.
Timeouts
Set request and backend timeouts to prevent long-running requests.
