Is your API really serving the model you pay for?
Enter a relay or third-party endpoint, key and model name. We combine independent evidence — output fingerprint, tokenizer, billing and response details — to tell whether it matches the model it claims to be. Runs in your browser, free.
What we check
The model writes a few hundred integers on first instinct. Each model favours certain values, ranges and last digits — like handwriting. The task is disguised as an ordinary request with random wording, language and length, so a relay can’t tell it is a test.
A dozen crafted short texts reveal how the upstream counts input tokens. Each model family splits text differently; this does not depend on what the model says, so rewriting answers can’t hide it.
For the same text, how many output tokens are billed — and how many input tokens an empty request costs, which exposes hidden system prompts or inflated billing.
The model name, response ID and finish reason the endpoint returns, plus speed.
If round one disagrees, a fresh set of prompts runs automatically. “Inconsistent” requires both rounds to disagree, so genuine endpoints are not flagged by chance.
Accuracy
Held-out evaluation: each prompt environment is left out of the library and used for testing, 699 groups in total. The library currently covers 64 models in 14 families and keeps growing.
Models in the library
Models not listed can still be checked: tokenizer, billing and response details work as usual; the fingerprint is a hint only and never decides “Inconsistent” on its own.
FAQ
Is my API key safe?
The check runs in your browser. If the endpoint allows browser requests, your key goes only to that endpoint. Otherwise the request is relayed by ModelBank unchanged — we do not store or log keys or content. You can force direct mode under “Advanced”.
Can I use the result as proof?
It is a statistical consistency check (see the accuracy above), not legal proof. If you get “Suspicious”, run it again later; “Inconsistent” means several independent signals disagree.
Why “Inconclusive”?
Usually the model is not in our library yet, answers were cut off or refused, or the endpoint returns no token usage.
How much does it cost?
About 7–25 requests: 6 of them write a few hundred numbers (roughly 1–2K tokens), the rest are tiny requests of a dozen tokens.
Do you publish lists of bad providers?
No. We provide the tool and the report; sharing is up to you.