Getting started

Models and authentication

Discover available models at runtime and authenticate every request with a dashboard API key.

Connection contract

Use the standard OpenAI-compatible base URL. Authentication uses the Authorization: Bearer header; do not expose the key in browser code.

Base URL: https://api.gonka24.com/v1
Authentication: Bearer sk-...
Model: GET /v1/models

Discover models

Call the models endpoint after authenticating. Use the exact returned id, including its spelling and any slashes, in the model field of later requests.

Use a live model ID.

The catalog changes. Call GET /v1/models with your API key and copy an id from the response instead of relying on a model name in a guide.

bash

curl https://api.gonka24.com/v1/models \
  -H "Authorization: Bearer $GONKA24_API_KEY"

SDK examples

The official OpenAI SDKs work when you override the base URL. Set your key through an environment variable in the process that sends requests.

Python

python

import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gonka24.com/v1",
    api_key=os.environ["GONKA24_API_KEY"],
)

response = client.chat.completions.create(
    model="<model-id-from-/v1/models>",
    messages=[{"role": "user", "content": "Hello from Python"}],
)
print(response.choices[0].message.content)

TypeScript / Node.js

typescript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.gonka24.com/v1",
  apiKey: process.env.GONKA24_API_KEY,
});

const response = await client.chat.completions.create({
  model: "<model-id-from-/v1/models>",
  messages: [{ role: "user", content: "Hello from TypeScript" }],
});

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

Keep keys private

Store GONKA24_API_KEY in a server-side secret store or local environment file excluded from Git. Rotate it in the dashboard immediately if it reaches source control, a client bundle, or an untrusted log.