Is your Claude / GPT real?

Detect whether your API relay's upstream has been swapped for a cheaper model (e.g. Claude → Qwen / DeepSeek). Behavioral fingerprinting — it sees through upstreams prompted to claim they are Claude.

⚠️ v0.3 · behavioral fingerprint + proprietary capability check: zero false positives on official endpoints; the CLI (Method A) now catches cheap-model backends disguised as Claude — based on endpoint capability traits that impersonation prompts cannot fake (detection details not disclosed). Some edge cases may still evade. Probabilistic signals, not conclusive; Method A is most accurate.

Method A — Local CLI · most accurate · key never leaves your machine

Recommended

Download one file and run it — it will ask you for the details interactively. Your key is used only to call your own endpoint, never uploaded.

curl -O https://panshi.io/relay-check/relay_check.py
python3 relay_check.py

Python 3 only, no dependencies. It prompts for your relay URL, key, and model, then prints Genuine / Suspected-substitution / Unknown + evidence.

Method B — Quick web check · no key needed · paste output

① Model the relay claims to serve

② Copy these probes → send to your relay as one message

③ Paste the relay's answers back here

⚠️ Results are probabilistic signals, not legal proof. Quantized / distilled variants and models outside our reference set cannot be determined. Detection by panshi.io.