Open-model inference on dedicated hardware in the European Economic Area. The API is OpenAI-compatible: point any OpenAI SDK at our base URL and it works.

Base URL

https://api.heabsy.com/v1

Authentication

Every request carries your API key in the Authorization header. Keys are issued and managed in the Heabsy Platform console.

Authorization: Bearer sk-your-key

Quick start

curl https://api.heabsy.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-coder",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

With the official OpenAI SDK — only the base URL changes:

# Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.heabsy.com/v1",
    api_key="sk-your-key",
)
reply = client.chat.completions.create(
    model="qwen3-coder",
    messages=[{"role": "user", "content": "Hello!"}],
)

// JavaScript / TypeScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.heabsy.com/v1",
  apiKey: "sk-your-key",
});
const reply = await client.chat.completions.create({
  model: "qwen3-coder",
  messages: [{ role: "user", content: "Hello!" }],
});

Endpoints

Lists the models currently available to your key. Model names here are the values accepted by the model field.

Chat completion, request and response bodies follow the OpenAI schema — including tool calls and JSON mode where the underlying model supports them.

Streaming

Set "stream": true to receive server-sent events, token by token, in the OpenAI streaming format. All SDK streaming helpers work unchanged.

Errors

Errors use the OpenAI error format: an error object with message, type and code.

Data residency