Detection Pipeline

Detectionpipeline

API Magnifier does not treat the claimed model name as a verdict. The engine collects signals layer by layer, then aggregates an honesty score and finding list. Detection depth comes in onlytwo modes(selectable on the check page) to balance runtime and evidence completeness.

L2

Standard check~2 min

Network, protocol, metadata, tokenizer fingerprint, capability probes, and performance baseline — enough for everyday authenticity checks.

L3

Deep check~8 min

Runs every available layer on top of the standard check (including pool and consistency signals). Longer runtime, fuller evidence.

15-Layer Depth

Layer overview

L1 — L15

Conceptual descriptions below; probes and thresholds evolve by version — rely on findings in your report.

Start

Read enough? Run a real check

Enter your relay URL and key. Keys for one-off checks exist only in memory for that run.