Is That API Really Serving the Model It Claims? A Reproducible Fingerprint Test

An API can return a valid response, use the model name you requested, and still leave an important question unanswered:

Is the endpoint behaving like the model it claims to serve?

A single answer cannot settle this. Style guessing is unreliable, benchmark prompts are easy to overfit, and providers can update models without notice. A useful test needs to be cheap, repeatable, and honest about uncertainty.

This is the workflow we are using for the AllRouter Public Model Fingerprint Lab. AllRouter is not treated as the judge. It is one endpoint under the same public test.

The idea: compare distributions, not prose

The paper provides a TypeScript CLI and library for OpenAI-compatible endpoints.

The fixed experiment definitions, public report schema, and blank result card are in the

The goal is not “trust this router.” The goal is the opposite: make the result reproducible enough that trust is not the only evidence available.

In the next report, we will publish the seven-day drift format, including latency, error rate, split-half consistency, and the exact decision thresholds.