Sjetz
OpenAI-compatible · hosted in the EU

One key. Every model.
Nothing waits on a single provider.

Sjetz sits in front of every AI provider you use and gives you one endpoint, one key, and one balance. Swap a base URL in your existing OpenAI SDK and every request is routed, metered, and logged for you.

Get your API key Read the docs
~/project · request.sh
# point any OpenAI-compatible client at Sjetz
curl https://sjetz.com/v1/chat/completions \
  -H "Authorization: Bearer $SJETZ_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role":"user","content":"Hello"}]
  }'
How it works

Built on one endpoint, not a new SDK

Sjetz speaks the OpenAI protocol, so anything that already talks to OpenAI — the official SDK, LangChain, your own fetch calls — works the moment you change one line.

client.py
from openai import OpenAI

client = OpenAI(
    base_url="https://sjetz.com/v1",
    api_key=SJETZ_API_KEY,
)

That's the whole integration. No new client library, no rewritten prompts. Behind that one base URL, Sjetz can hold as many provider channels as you configure — each request gets routed to a working one, and every token is metered against your balance automatically.

Under the hood

Everything a gateway should do

Sjetz is built on New API, so the plumbing a serious integration needs is already there — not bolted on later.

01

Unified endpoint

One base URL and one key reach every OpenAI-compatible provider you connect, with no per-provider client changes.

02

Usage-based billing

Every call is metered to the token. Top up credit, issue redemption codes for teammates, or run it on a subscription plan.

03

Load-balanced routing

Spread traffic across multiple channels per model and fail over automatically the moment one stalls or errors out.

04

Chat, image & video tasks

Longer-running generation jobs run as trackable async tasks, not just synchronous chat completions.

05

Full request logs

Every call is recorded with cost, latency, and model — down to the individual key, so usage is never a mystery.

06

Team accounts

Invite teammates, hand out scoped keys, and let everyone draw from one shared balance.

Who it's for

One gateway, three ways to use it

Solo builder

Ship a side project against several models without juggling separate accounts, keys, and bills for each provider.

Small team

Resell metered model access to your own users under one brand, with redemption codes and top-ups handling the billing.

Internal tool

Give your company one gateway and one audit trail instead of scattered provider keys living in different environments.

Pricing

Simple, usage-based pricing

Top up credit once and spend it across every model Sjetz routes to. No subscription required to get started.

Starter
pay as you go
  • Trial credit on sign-up
  • Access to every connected model
  • Usage dashboard & request logs
Team
shared balance
  • Everything in Starter
  • Invite teammates & scoped keys
  • Redemption codes for onboarding
Scale
talk to us
  • Everything in Team
  • Dedicated channels & rate limits
  • Volume pricing

Exact per-model rates are set in your dashboard and shown at checkout before you spend anything.

Ready to stop juggling provider keys?

Create your account