Vibe-coding 101 on TDSPRO

Vibe-coding is building software by describing what you want in plain language and letting an AI write, fix, and refactor the code with you. You stay in charge of the idea; the model handles the typing. This guide gets you from zero to a working call against TDSPRO — one key, every model.

What you need

• A free TDSPRO key — no card required.
• Any editor or AI IDE (VS Code, Cursor, OpenCode, etc.).
• Node.js or Python — whichever you prefer.

Step 1 — get your key

Create a free key on the sign-up page. It appears once — copy it and keep it safe. You can always generate a new one.

Step 2 — make your first call

If your code already talks to OpenAI, it already talks to TDSPRO. Point the base URL at our endpoint and use your key:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.tdspro.lol/v1",
  apiKey: process.env.TDSPRO_KEY,   // your free key
});

const res = await client.chat.completions.create({
  model: "smart",                   // capability alias — picks a great model
  messages: [{ role: "user", content: "Write a haiku about shipping code." }],
});

console.log(res.choices[0].message.content);

Prefer Python? Same idea — the official OpenAI SDK works unchanged:

from openai import OpenAI

client = OpenAI(base_url="https://api.tdspro.lol/v1", api_key="YOUR_TDSPRO_KEY")

res = client.chat.completions.create(
    model="smart",
    messages=[{"role": "user", "content": "Explain a closure in one sentence."}],
)
print(res.choices[0].message.content)

Step 3 — pick the right brain

You do not need to memorize model names. Call a simple capability alias and TDSPRO routes the request to a great model for the job — out of 20+ available:

A healthy vibe-coding loop

1. 1Describe the change in one or two sentences.
2. 2Read the diff the model proposes — do not paste blindly.
3. 3Run it. Tests and the app are your ground truth.
4. 4Refine with a follow-up prompt. Small steps beat giant ones.