Publish your app to managed hosting with one command; compare LLM cost/latency with real metered billing; PDF translate, cited research, PPTX — one MCP server.
This diagram is itself rendered by the service — a stateless image URL, no request needed to build it.
npm/PyPI READMEs don't render mermaid; this does.
Hosted open-source AI apps, callable by your agent over MCP — and from your terminal.
npx ai-netcafe compare "dedupe a JS array preserving order"
MODEL COST LATENCY
deepseek-v4-flash $0.00012 7.6s
gemini-3.5-flash $0.000341 10.0s
GLM5.2 $0.001828 9.0s
cheapest: deepseek-v4-flash fastest: deepseek-v4-flash
15.2× between cheapest and priciest
Every number above is read from the upstream usage response, not derived from a
published price list. That distinction matters more than it sounds — while building
this we found the obvious conversion formula was wrong for several models
(one was off by ~9×, another by ~3×), and only billing-delta measurement matched
reality. Full method and data.
npx ai-netcafe install # prints config for Claude Code / Desktop / Cursor
Or directly:
claude mcp add --transport http ai-netcafe https://ainetcafe.com/mcp
| Skill | What it does |
|---|---|
compare_models | One prompt across many LLMs, with real metered cost + latency |
translate_pdf | Translate a PDF keeping formulas, figures and two-column layout intact |
deep_research | Plans sub-questions, searches, reads sources, writes a cited report |
make_slides | Generates a real downloadable .pptx |
list_apps / get_app | Catalogue of the hosted open-source apps, with source repos |
ask_model / list_models | Single model call; model list with prices |
Backed by open-source projects — PDFMathTranslate, GPT Academic, GPT Researcher, NextChat, LobeChat — hosted pre-configured so you can try them without installing Docker, Python, or supplying an API key.
npx ai-netcafe compare "<prompt>" # multi-model comparison with real costs
npx ai-netcafe ask "<prompt>" # single model
npx ai-netcafe apps # hosted apps + source repos
npx ai-netcafe models # models with per-million prices
npx ai-netcafe install # MCP config for your agent
Anonymous calls get a small free quota — enough to try. Heavy skills (whole-PDF translation, deep research, slide generation) need an account or your own key, because one of those runs costs dozens to hundreds of model calls.
export ALLROUTER_API_KEY=sk-... # unlimited, billed to you
MIT
FAQs
Publish your app to managed hosting with one command; compare LLM cost/latency with real metered billing; PDF translate, cited research, PPTX — one MCP server.
We found that ai-netcafe demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
NIST disclosed an unreleased AI tool called V-etalon and opened a broad inquiry into NVD modernization after years of automation plans produced no public enrichment system.
Security News
In his AI Council 2026 talk, Feross Aboukhadijeh covers recent package compromises, vulnerability discovery, and a more automated security model.
Security News
A new federal program will let vetted U.S. cybersecurity firms help investigate and disrupt foreign cybercrime groups under government direction.