Skip to content
Panshi
EN / /
← Panshi Sentinel Panshi Sentinel · LLM supply-chain QA

Is the AI model you're using real?

API relays routinely water down their upstream — quietly swapping the Claude / GPT you paid for with a cheaper model (Qwen, DeepSeek, a quantized variant), often prompted to claim it is still Claude. Panshi Sentinel catches that by behavioral fingerprint, end to end.

💧

Upstreams leak

A relay buys real Claude today, then silently routes to a cheaper model tomorrow to widen margin. You never see the switch.

🎭

Disguised identity

A swapped upstream is told to answer "I am Claude." Asking the model who it is proves nothing — fingerprinting sees through it.

📉

Silent quality loss

Your product degrades, your users churn, and you blame your own prompts — when the real cause is the model under you changing.

Two ways in

From a free spot-check anyone can run, to 7×24 continuous monitoring for operators and teams — detection only, catching upstream model substitution.

Free

Panshi Sentinel · Free Check

A free behavioral-fingerprint checker. Paste your relay's answers — or run a one-file local CLI — and find out in seconds whether your Claude / GPT is genuine or substituted.

  • No signup, key never leaves your machine
  • Sees through disguised upstreams
  • Genuine / Suspected-substitution / Inconclusive + evidence
For operators / teams

Panshi Sentinel · Monitor

Continuous-monitoring SaaS for relay operators and heavy users / teams. Watch all your upstream channels around the clock and get alerted the moment a model is swapped or degraded.

  • Scheduled probes + crypto verification per upstream
  • Drift & substitution alerts + per-channel audit trail
  • From $99 / mo · priced by upstream channel count

Why you can trust the verdict

Panshi Sentinel is built on a behavioral-fingerprinting method informed by published research on LLM identification — not vibes.

0

False positives on official endpoints in our testing — genuine models are never flagged as substituted.

🎭→🔎

Still identifies the real model even when the upstream is prompted to disguise itself as Claude.

📚

Informed by published research on LLM identification, not self-reported model identity.

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