BotsRatedBETA

vectorcache-production.up.railway.app

LiveLLM Inference

High-speed semantic vector cache for multi-agent swarms. Redis-backed similarity lookup with in-memory fallback before expensive embedding p (the service's own listing text)

20/20Recent Test Calls That Worked
273 msTypical Response Time (slow end: 529 ms)
$0.003 / $0.003Listed / Actual Price: match
Same AddressPayment Address (payTo): the same on all 19 checks of the main route
1Directories Listing It
27 min agoLast Checked (2026-10-24T10:48:28Z)

Listed Vs. Actual Price

Listed = the price in the directory listing today, for the main route we test. Actual = the price that route asked for when we called it (from our signed records). Some differences are normal, like prices that depend on the request.

PeriodListedActualResult
Recent Checks$0.003$0.003Matches Listing

Latest Signed Records

Signed RecordTime (UTC)ReplyAsked For Payment CorrectlymsPrice Asked
47f66dd9a6f00f545a0a2026-10-24T10:48:28Z402Yes247$0.003
69e7dfc7c9b94f887f9e2026-10-24T10:18:17Z402Yes331$0.003
186897be13881e1b02572026-10-24T09:46:30Z402Yes173$0.003
bf901a17685e5ae16b842026-10-24T09:16:33Z402Yes266$0.003
92cd741d0bb8792859c22026-10-24T08:44:35Z402Yes127$0.003

Every record is digitally signed, so anyone can verify it. More: raw data page · free quick check (JSON)