§ Docs

API documentation.

OpenAI-compatible API. Swap the endpoint, keep your code. Requests run in the EU and are billed via your grunden.ai wallet or subscription.

§ 01

Beta

grunden.ai is pre-launch. The service is open for registration but has no paying customers in production yet — pilots are planned for H2 2026. Prices, model and features may change; breaking changes are published with notice. Don't use in production without checking with us at hej@grunden.ai first.

§ 02

Getting started

Create an account if you don't already have one.
Go to Settings → API keys in your team and create a key.
Top up your wallet under Wallet to pay per token, or activate a chat subscription under Subscription if you primarily use the web chat.

§ 03

Base URL and authentication

All requests go to https://api.grunden.ai. Send your key in the Authorization header:

Authorization: Bearer sk-grunden-…

Keys begin with sk-grunden- and are scoped per team. The rate limit per key (RPM + TPM) is set at creation and can be adjusted in the admin UI.

bash

curl https://api.grunden.ai/v1/chat/completions \
  -H "Authorization: Bearer $GRUNDEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.1",
    "messages": [{"role": "user", "content": "Hej!"}]
  }'

§ 04

Use it in your editor (VS Code, Cursor, Codex CLI)

Because the API is OpenAI-compatible, most AI coding tools can point at grunden.ai directly — swap out Claude/Codex as the backend without switching tools. Across the board: set the base URL to https://api.grunden.ai/v1, your sk-grunden-… key as the API key and glm-5.1 as the model. Calls run on the normal tier and are billed per token from your wallet (top up under Billing).

Se chat-kapaciteten →