European image and video model lab — compression-optimised inference.
European AI lab focused on model compression and efficient image and video generation. Pruna hosts their own optimised image and video models on EU infrastructure. A specialised pick for image and video generation workloads where compression-efficient inference matters and onchain settlement is preferred.
Every model we route through Pruna. Compare residency, zero retention, training posture, and price at a glance — full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| US | Not by default | No | — | $0.10 / generation | ||
| US | Not by default | No | — | $0.10 / generation | ||
| US | Not by default | No | — | $0.002 / generation | ||
| US | Not by default | No | — | $0.01 / generation | ||
| US | Not by default | No | — | $0.10 / generation | ||
Pruna hosts on 1 route. Each route has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.
Zero data retention is not on by default — abuse monitoring. No training on customer data. US; wallets; deposit available.
