ETHUXChoose your AI. Run it on ours.
Open models on racks we own in the Netherlands, GPU instances coming soon. One API key, prices you can read before you spend.
Your prompts never leave the Netherlands.
Choose your AI
Open models, ready on one API.
Pick a model, change one line in your code, done. Every price is on the plate.
ModelGood atPer million tokens
qwen3.8-27bGeneral chat and tool use. The default. Our own mixed quant, not FP8 or INT4.€ 0.10 in · € 1.20 out€ 0.05 cached in · excl. VATTry →qwen3-embeddingsVectors for search and retrieval.€ 0.10 inexcl. VATTry →clef-flashA decision model. Fast and cheap.€ 0.04 inexcl. VATGet notified →Not your model, not your knowledge.
Our own hardware
No cloud in between.
We own the racks, the GPUs and the network. That is why we can say where your data is, and why prices stay put.
0clouds in between
NLwhere every request runs
- We own the racks.The GPUs, the servers and the network are ours, in the Netherlands.
- Prices stay put.No cloud bill underneath that can change ours.
- You can leave.Open models and a standard API, so your code works anywhere.
Everything ETHUX
One company, a few sharp tools.
Pricing
Read it before you spend it.
Excluding VAT. No minimums for the API; GPU instances will bill per started hour.
| What | Unit | Price |
|---|---|---|
| qwen3.8-27b | per million tokens in / cached in / out | € 0.10 / € 0.05 / € 1.20 |
| qwen3-embeddings | per million tokens | € 0.10 |
| clef-flash | per million tokens in, coming soon | € 0.04 |
| 1 × RTX 3090 | per hour, coming soon | € 0.35 |
| 2 × RTX 3090 | per hour, coming soon | € 0.70 |
| Sandbox | per hour, coming soon | € 0.02 |