DEDUPED Hot AI repos, turned into use cases Get the Monday 5
131 stars · JavaScript

How to use Modelprint: what you can do with it

modelprint is a browser tool that runs infrastructure probes against OpenAI-compatible API endpoints and compares their fingerprints side by side.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

Authorization notice. This tool is dual-use. Only use it on software, sites and systems you own or have explicit permission to test, and follow the relevant licenses and terms of service.

What do you want to do?

3 use cases

  • Check which model a provider alias really serves

    Run the nine-probe browser suite to see if a named model matches its claimed lab.

    View prompt
    Using the modelprint repo (github.com/unclecode/modelprint), run the browser probe suite against <endpoint-or-model-name> and report the fingerprint table for each probe. Expected output: one value per probe, with tokenizer rows normalized against the one-character baseline. Verify that no tokenizer row is marked unstable before you call any match.

  • Run the test suites before opening a probe pull request

    Use selftest.mjs and smoke.mjs to confirm a new or edited probe behaves before review.

    View prompt
    In the modelprint repo, add a probe in probes/ following probes/_template.js, then run `node selftest.mjs` from the repo root. Expected output: a pass result for every probe including the new one. Verify the new probe returns the same value on two runs and never throws before you open a pull request.

  • Rank a mystery model against a suspect lineup

    Run suspects.mjs to rank a stealth model against a 12-model field by probe match.

    View prompt
    In the modelprint repo, run `node suspects.mjs` with the OpenRouter key set in the environment. Expected output: a ranked list of the 12 suspect models with probe match counts. Verify that the top candidate's tokenizer row matches on all four normalized counts before you report it as a family match.

Quick start with Modelprint

  1. Check you have what it needs: A web browser and an API key for the OpenAI-compatible endpoint you want to check; Node.js, for the local test scripts (selftest.mjs, smoke.mjs, suspects.mjs); An OpenRouter API key in the environment, only for smoke.mjs and suspects.mjs.
  2. Open unclecode/modelprint on GitHub and read the README and license.
  3. Open https://modelprint.ai/ in your browser (the README calls it 'Try it: Modelprint.ai').
  4. Enter the endpoint and your API key; the README says keys stay in your browser tab and calls go straight to the provider.
  5. Select the model you want to check and run the probes.
  6. Compare the tokenizer and error-code rows with the rows of the model the provider says it serves.

These steps come from our top use case, Check which model a provider alias really serves, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for unclecode/modelprint

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Modelprint alternatives · Best AI repos for Security and science

About this repo

  • Who it is forDevelopers and researchers who need to check which model or lab actually serves an OpenAI-compatible API, and contributors who want to add probes.
  • Why it is hot131 stars, launched 64 days ago
  • LanguageJavaScript
  • Sourcegithub.com/unclecode/modelprint · Back to Hot repos

Requirements

  • A web browser and an API key for the OpenAI-compatible endpoint you want to check
  • Node.js, for the local test scripts (selftest.mjs, smoke.mjs, suspects.mjs)
  • An OpenRouter API key in the environment, only for smoke.mjs and suspects.mjs

Add this badge to your README

Maintain Modelprint? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/unclecode/modelprint.svg)](https://dedupedai.com/use-cases/unclecode-modelprint/?utm_source=github&utm_medium=badge&utm_campaign=unclecode-modelprint)

HTML 

<a href="https://dedupedai.com/use-cases/unclecode-modelprint/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=unclecode-modelprint"><img src="https://dedupedai.com/badge/unclecode/modelprint.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Modelprint

What is Modelprint?

modelprint is a browser tool that runs infrastructure probes against OpenAI-compatible API endpoints and compares their fingerprints side by side. It is an open-source project on GitHub: https://github.com/unclecode/modelprint.

Who is Modelprint for?

Developers and researchers who need to check which model or lab actually serves an OpenAI-compatible API, and contributors who want to add probes.

What can I do with Modelprint?

3 use cases so far, for example: Check which model a provider alias really serves; Run the test suites before opening a probe pull request; Rank a mystery model against a suspect lineup. Each has steps and a copy-paste agent prompt.

What do I need to run Modelprint?

A web browser and an API key for the OpenAI-compatible endpoint you want to check; Node.js, for the local test scripts (selftest.mjs, smoke.mjs, suspects.mjs); An OpenRouter API key in the environment, only for smoke.mjs and suspects.mjs.

What are alternatives to Modelprint?

Other hot AI repos in Security and science: RiftX, Hacker, Codex Privacy Hud, Forge Guardian, Open Keylet.

Is Modelprint safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.