Response Schema

With each request, Prisma AIRS AI Gateway sends back gateway-specific headers that can help you identify the state of specific AI Gateway features you are using. We send the following 4 response headers:

Header	Value
`x-portkey-trace-id`	Returns a `unique trace id` for each response. In case the user has already sent a trace id with x-portkey-trace-id in their `request body,` then that is used here instead of generating a new id.
`x-portkey-retry-attempt-count`	Returns the number of `retry attempts` made for the call. Request made for the first time is not counted, `only` the attempts are counted. So, if the value is 3, that means that a total of 4 (1+3) calls were made.
`x-portkey-cache-status`	Returns the `cache status` for the call. • HIT (simple cache hit) • SEMANTIC HIT (semantic cache hit) • MISS (simple cache header was sent in the request, but returned a miss) • SEMANTIC MISS (semantic cache header was sent in the request, but returned a miss) • DISABLED (no cache header sent) • REFRESH (cache force refresh was true in the request header)
`x-portkey-last-used-option-index`	Returns the nested `target index` (as jsonpath) for the Config id used while making the call.

API Reference

Inference