Endpoint · computePOSTlinked-aimed-reproduced-changing.trycloudflare.com /v1/attest/model
Proof-of-Model: detect silent model substitution at any OpenAI-compatible inference endpoint.
Read more
Proof-of-Model: detect silent model substitution at any OpenAI-compatible inference endpoint. mode=fingerprint records what a seller serves today; mode=verify re-probes later and proves whether the weights changed. Deterministic, evidence included, no model used to judge.Overview
Grade?
UNRATED
0 of 30 paid calls toward a letter
Price
$0.10 per call
Paid calls
none yet
delivery unknown until someone pays
More info
Seller?
URL
https://linked-aimed-reproduced-changing.trycloudflare.com/v1/attest/model
Seen
first 40 days ago · last 39 days ago
8 free handshakes
Payment
Pays through
x402
Offered on?
Base USDC
Listed on?
Base
Score, from free handshakes onlyweights 2026.09.6
UN
RATED
RATED
0.233 liveness verified, no letter
To a letter · 30 paid calls
0 of 30
Held down by liveness · gap to 1.000 is 0.767: 0.083 uncertain ? + 0.684 short ? · 0.217 to D
| Component | Weight | Measured | Lower bound ? | Adds | Short ? | Uncertain ? | |
|---|---|---|---|---|---|---|---|
| livenesscosts the most it answered at all |
0.75 | 0.11 | 0.000 | 0.000 | −0.667 | −0.083 | |
| latency p95 it answered as fast as its class |
0.25 | 0.93 | 0.932 | 0.233 | −0.017 | 0 | |
| Composite | 1.00 | 0.233 | gap to 1.000 = 0.767 · 0.684 short · 0.083 uncertain | 0.233 | −0.684 | −0.083 |
Not measured: correctness · nobody paid; honesty · nobody paid; schema conformance · no answer had a published shape to check; price stability · nothing to score
The multiplication, written out
0.750 × 0.000 liveness
+ 0.250 × 0.932 latency p95
= 0.233 → UNRATED: 8 of 30 paid calls weights 2026.09.6 · 8 samples · seed cap_01M4FK5PF3Y2AZT8X1Q4BXF009|2026-09-30T10:16:51.693Z|2026.09.6
Verify it yourself
npx teppi-check https://linked-aimed-reproduced-changing.trycloudflare.com/v1/attest/modelcurl -s https://api.teppi.xyz/v1/trust/cap_01M4FK5PF3Y2AZT8X1Q4BXF009