Specialized AI model hosting for open, proprietary, and custom stacks
EmpirioLabs serves open-weight models on GPU infrastructure it operates itself from Seattle, adding day-0 support for new releases and exposing full sampling and model settings. US-hosted. The route to pick when you want new open-weight models the day they ship and US hosting is acceptable.
Call the 8 models on EmpirioLabs through Opper with one API key. Sign up without a credit card.
Every model we route through EmpirioLabs. Compare residency, zero data retention, training posture and price at a glance, with full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| Multi | No | 1M | $2.17 | $4.35 | ||
| Multi | No | 262K | $0.17 | $0.50 | ||
| Multi | No | 262K | $0.09 | $0.13 | ||
| Multi | No | 262K | $0.04 | $0.07 | ||
| Multi | No | 262K | $0.05 | $0.29 | ||
| Multi | No | 131K | $0.20 | $0.80 | ||
| Multi | No | 131K | $0.07 | $0.42 | ||
| Multi | No | 1M | $0.70 | $1.40 |
EmpirioLabs hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs; DPA available.
