Who is really behind that API? Run infrastructure probes against any OpenAI-compatible endpoint and compare the fingerprints. Plumbing does not lie; personality does.
Your keys stay in this tab. Every call goes from your browser straight to the provider. Model lists are fetched live. No key yet? Create one in a minute at openrouter.ai/settings/keys.
tokenizer counts — the same text goes to each model; the API's own usage.prompt_tokens comes back. Tokenizers are built per lab and almost never match across labs. Five texts (English, Chinese, code, emoji, empty) give five independent readings.
template offset — an empty prompt against a one-word prompt reveals how many hidden tokens the serving template adds. A constant +75 offset was one of the clues the community used on Ox Alpha.
error taxonomy — deliberately invalid parameters (temperature 2.5, negative max_tokens) return validation prose written by the lab's own engineers, often with numeric codes. GLM's content filter answers with code 1301; that code appearing behind a stealth model ended the mystery for many.
Why no censorship or personality probes: the community ran both on Ox Alpha and got contradictory verdicts from the same model on the same day. Behaviour bends to a system prompt; tokenizers and error handlers do not. This tool fingerprints the plumbing only.
Every probe is one small JavaScript file in probes/. A probe gets a ctx.chat(payload) function, sends one or two requests, and returns { value }: a string or number that must come out identical when two endpoints run the same stack. Token counts, error wording, limit numbers: good values. Timestamps, latency, random ids: never.
Copy probes/_template.js, keep its header comment (name, description, author, version), and open a pull request. An approved probe is one added line in probes/index.js, and the page loads it automatically. Ideas waiting for an author: logprobs support, stop-sequence limits, system-role handling, streaming chunk shape.