Quickstart

Get your first response in three steps.

1. Create an API key

API keys are managed per workspace from the Helmcode Dashboard → API Keys → Create key. The number of keys available depends on your plan — 5 on Starter, 15 on Growth, 40 on Scale. Keys are scoped to your organization and can be revoked at any time.

Store the key as an environment variable:

export HELMCODE_API_KEY="sk-your-key-here"

2. Point your client at Helmcode

Any OpenAI-compatible SDK works. Change two things:

Base URL: https://api.helmcode.com/v1
Auth: Authorization: Bearer $HELMCODE_API_KEY

3. Make a request

from openai import OpenAI

client = OpenAI(
    base_url="https://api.helmcode.com/v1",
    api_key="sk-your-key-here",
)

resp = client.chat.completions.create(
    model="qwen3.6",
    messages=[{"role": "user", "content": "Say hello from the EU."}],
)
print(resp.choices[0].message.content)

That’s it. You’re running open models on private European infrastructure. Head to Examples for Node.js, cURL, streaming, and embeddings.