Smart Proxy

Configure caching, rate limiting, retries, and fallbacks for your AI Gateway

Caching

Cache responses to reduce cost and latency

Cache TTL (seconds)3600s

1 min24 hrs

Rate Limiting

Control request volume

Request Retry

Auto-retry failed requests

Max Attempts3

Retry Delay (ms)

Backoff Strategy

Logging

Store request and response logs

Log Payloads

Store request/response bodies

Request Timeout

Maximum time to wait for a response

30s