other · Listed · Base · Found · 5 endpoints · Not used for Gateway
pqs
pqs
PQS batch scoring - score up to 10 prompts in one call
Not used for Gateway
Catalogued so agents know it is dead/unreachable — Gateway will not route it. Still catalogued — dead/unreachable knowledge is index value. (Degraded — catalogued (dead/unreachable known) · not used for Gateway)
Indexed from this operator's public /.well-known/x402.json. Found is not operator-owned and is not attested. Claim or opt out.
Agent Read · Cleared Index
SKIP
Skip until Cleared checks or settle mesh clear.
confidence
83%
source
signal
Index before you pay. Same payload for agents:
GET /api/cleared/agent-read?slug=cat-pqs-onchainintel-net
When to call
- Budget between $0.025 and $1.25 per call on published endpoints.
- PQS batch scoring - score up to 10 prompts in one call
Risks
- Found — not operator-owned; claim status unknown.
- No Cleared settlement receipt on file yet.
- Uptime not yet marked stable.
- No Gateway traffic yet — market share unproven.
Price posture
Published 5 endpoints from $0.025 to $1.25.
Category · Gateway
other · no Gateway routes yet — early / unproven on Cleared market share.
Endpoint hints
POST /api/score/batchPQS batch scoring - score up to 10 prompts in one call
POST /api/score/comparePQS cross-model scoring - same prompt through Claude and GPT-4o, judged by a third model
POST /api/score/fullPQS full analysis - optimized prompt plus before/after outputs
POST /api/scorePQS score - 8-dimensional prompt quality breakdown across 5 frameworks with top fixes
POST /api/preflightPass/Fail before you waste budget on a doomed call. Decide whether to make a paid LLM call before you make it. Preflight scores your prompt against an 8-dimensi
Evidence (Cleared)
- → Intake degraded · not used for Gateway
- → Trust 15/100 · fail · tier listed
- → Protocol x402 · Base
- → Manifest pending · schema partial
- → Found listing — indexed from public x402.json, not operator-attested.
Endpoints
PQS batch scoring - score up to 10 prompts in one call
$0.25POST https://pqs.onchainintel.net/api/score/batchPQS batch scoring - score up to 10 prompts in one call
PQS cross-model scoring - same prompt through Claude and GPT-4o, judged by a thi...
$1.25POST https://pqs.onchainintel.net/api/score/comparePQS cross-model scoring - same prompt through Claude and GPT-4o, judged by a third model
PQS full analysis - optimized prompt plus before/after outputs
$0.125POST https://pqs.onchainintel.net/api/score/fullPQS full analysis - optimized prompt plus before/after outputs
PQS score - 8-dimensional prompt quality breakdown across 5 frameworks with top ...
$0.025POST https://pqs.onchainintel.net/api/scorePQS score - 8-dimensional prompt quality breakdown across 5 frameworks with top fixes
Pass/Fail before you waste budget on a doomed call. Decide whether to make a pai...
$0.05POST https://pqs.onchainintel.net/api/preflightPass/Fail before you waste budget on a doomed call. Decide whether to make a paid LLM call before you make it. Preflight scores your prompt against an 8-dimension quality rubric (pass/fail at 28/80) and optionally pulls the target endpoint's on-chain trust signals — total payments, unique payers, last activity. Two-in-one circuit breaker for agents that don't want to waste budget on weak prompts or sketchy endpoints. (rev 2)
Checks
pending
partial
2026-08-24T21:47:38.197Z
Intake degraded · Degraded — catalogued (dead/unreachable known) · not used for Gateway · probed 3/3 · Manifest HTTP 404. Listed anyway. | No settlement evidence found in chain signals.
Claim this listing to upgrade to Cleared attestation.
Claim listing