Open beta · 2026

AI models,
through a single
endpoint.

Generate a key, POST your prompt, get a response. That's the entire integration. No SDKs, no setup, no overhead.

Get started free See how it works →
POST api.cuybly.xyz/v1/chat
01
Create your API key
Sign up and generate a key from your dashboard. Takes about 30 seconds.
02
Send your request
POST to api.cuybly.xyz/v1/chat with your key in the Authorization header and your prompt in the body.
03
Get your response
Receive clean JSON back in milliseconds. Stream it or wait for the full result — your choice.
Ultra-low latency · REST API · Streaming support · Global edge network · No setup required · JSON responses · Any language · Ultra-low latency · Streaming support · Global edge network · No setup required · JSON responses · Any language ·
How it works

Three steps.
That's it.

01
Generate your API key
Sign up and get a unique key from your dashboard. No credit card, no forms — just an account.
02
POST to our endpoint
Send a JSON payload to api.cuybly.xyz/v1/chat. Works with curl, Python, JS, Go — anything that speaks HTTP.
03
Get your response
Structured JSON back in milliseconds. Stream token-by-token or wait for the full completion. Scale without changing a line.
Integration

Dead simple
to integrate.

Any language, any framework. If it can make an HTTP request, it works with Cuybly. Full quickstart docs and code examples are now live at /docs.

No SDK or library to install
Plain JSON request and response
Streaming and batch modes
Full TypeScript types available
OpenAI-compatible schema
cuybly.xyz/docs
Documentation
Docs are
out now.
Quickstart guides, API reference, authentication, and more — everything you need to build with Cuybly is at /docs.
Read the docs →
Pricing

Simple.
Transparent.

Free plan
$ 0
Free forever — no credit card needed
Get your API key

Ready to
build?

Get your API key in 30 seconds. No credit card, no config — just intelligence, on demand.

Create free account api.cuybly.xyz/v1/chat