Endpoint · inferencePOSTblockrun.ai /api/v1/messages
Anthropic-compatible Messages API — pay per token with USDC on Base
Overview
Grade?
UNRATED
7 of 30 paid calls toward a letter
Price
$0.011 per call
Paid calls
16
16 delivered
More info
Seller?
URL
https://blockrun.ai/api/v1/messages
Seen
first 16 days ago · last 9 hr ago
42 free handshakes
Payment
Pays through
x402
Offered on?
Base USDC
Listed on?
Base
Scoreweights 2026.09.6
UN
RATED
RATED
0.200 outcome verified, no letter
To a letter · 30 paid calls
7 of 30
Held back by sample size, not by the seller · gap to 1.000 is 0.800: 0.774 uncertain ? + 0.026 short ? · 0.250 to D
| Component | Weight | Measured | Lower bound ? | Adds | Short ? | Uncertain ? | |
|---|---|---|---|---|---|---|---|
| correctnesscosts the most the answer was right |
0.41 | 1.00 | 0.123 | 0.051 | 0 | −0.361 | |
| honesty it charged what it advertised |
0.29 | 1.00 | 0.123 | 0.036 | 0 | −0.258 | |
| liveness it answered at all |
0.18 | 1.00 | 0.123 | 0.022 | 0 | −0.155 | |
| latency p95 it answered as fast as its class |
0.06 | 0.56 | 0.558 | 0.033 | −0.026 | 0 | |
| price stability the price stayed where it was listed |
0.06 | 1.00 | 1.000 | 0.059 | 0 | 0 | |
| Composite | 1.00 | 0.200 | gap to 1.000 = 0.800 · 0.026 short · 0.774 uncertain | 0.200 | −0.026 | −0.774 |
Not measured: schema conformance · no answer had a published shape to check
The multiplication, written out
0.412 × 0.123 correctness
+ 0.294 × 0.123 honesty
+ 0.176 × 0.123 liveness
+ 0.059 × 0.558 latency p95
+ 0.059 × 1.000 price stability
= 0.200 → UNRATED: 7 of 30 paid calls weights 2026.09.6 · 7 samples · seed cap_01M2SGNCND9FBXFPWR4CQ29Z0H|2026-07-06T07:41:48.926Z|2026.09.6
Verify it yourself
npx teppi-check https://blockrun.ai/api/v1/messagescurl -s https://api.teppi.xyz/v1/trust/cap_01M2SGNCND9FBXFPWR4CQ29Z0H