Open models through one API. Nothing is stored.

main.py
Saved requests
0 files, 0 B

Prompts and answers stay in memory only while the request runs.

PL · SE · IScountries where our GPUs run, all in the EEA
$0.03per million input tokens, below the market
32.8ktokens of context in the largest model available now
0 Bof your prompts and answers stored

Priced below the market, quantization in plain sight.

Open-weight models on GPUs we run. Models also listed on OpenRouter keep the same ids.

Everything you need to ship, nothing you have to babysit.

A drop-in for the OpenAI SDK

Keep your code. Change two lines and your existing client talks to open models.

Zero data retention

Prompts and completions are streamed through and never written to disk. We keep token counts for billing, nothing else.

  1. Request arrivesRAM
  2. Model answersGPU
  3. Content discarded0 B
  4. Token count kept for billingusage
Read the data policy

Cost on every response

Each response carries its price in USD, so you can attribute spend per feature or user.

"usage": { "prompt_tokens": 1520, "completion_tokens": 488, "cost": 0.000701 }

Budgets per key

Give each key a monthly cap. When it is reached, that key stops, the rest keep running.

production$31 / $50
staging$1.80 / $10

Invoices that pass audit

A VAT invoice is issued for every top-up and sent to your inbox.

Poland23%
EU business, VAT ID0% RC
Outside the EU0%

Keys, spend and limits on one screen.

See what every key costs, how fast the model answers and how close you are to a limit. Set a monthly cap and sleep well.

Prepaid. No subscription. No minimum spend after the first top-up.

Top up

Pay by card from $5. Credit lands in your balance the moment the payment clears.

Create a key

One key per app or environment, each with an optional monthly budget.

Pay per token

Every request is deducted at the published price. Credit never expires.

One price list. Per million tokens.

$0.12
input
$0.85
output
Example workload
1M input tokens$0.12
200k output tokens$0.17
Total, before VAT$0.29
See pricing and VAT

European by design, ready for procurement.

The questions your legal and security teams ask, answered before they ask. A Polish company, GPUs in the European Economic Area, nothing stored, and the paperwork ready to download.

A Polish company under EU law

MADD, Olsztyn, Poland. Contract under Polish law, Polish VAT invoices sent to KSeF, reverse charge for EU businesses.

NIP
PL7422297084
REGON
545106682

Inference in the EEA

Models run on GPUs in Poland, Sweden and Iceland, all inside the European Economic Area. The country of every model is shown on the models page and published in /v1/models.

https://maddlabs.co/v1EEA

Zero retention, always on

Prompts and answers live only in memory while the response is generated. No content logs, no training, no switch to forget.

Store prompts
Train on your data
Billing metadata only

Questions

Short answers to what developers and procurement ask most. Anything missing? We answer on business days, usually the same day.

Your first request in under a minute.

Sign in with email or Google, top up, copy your key.

Get API key