Pilot
One model. One target. A number you can show your board.
We take one of your models and run it encrypted on your target, a customer site, an edge device or a partner cloud. It is never decrypted there, and you get the measured cost of that.
Steps
- 01
Architecture review
- 02
Scope and fixed fee
- 03
Convert the model
- 04
Run on your target
- 05
Report and decision memo
One model, one target
Fixed fee
€20K to €50K
Indicative range, depending on model and target. The fixed fee is confirmed in writing after the architecture review.
Deliverables
- Your model converted and running encrypted on your target hardware
- Benchmark report on your hardware: latency, accuracy delta, memory
- Deployment recipe
- Threat-model fit for your deployment
- Decision memo for the approver
- For medtech: the technical-file annex template
What you provide
- The model (ONNX or TensorRT)
- Representative inputs
- A target device or VM
- One engineer for two hours a week
What happens after
Annual terms by site, device or model, agreed after the pilot on the basis of what it measured.
Bring one model and one target.
We tell you what it costs in latency and what it buys in protection.