US host of abliterated open-weight models for security, red-team and trust and safety work.
abliteration.ai (Abliteration AI, Inc., Palo Alto) serves open-weight models whose refusal behaviour has been removed, so they follow through on requests other models decline. Its catalogue is aimed at security research, red teaming, agent testing, trust and safety and synthetic training data. Models run in the United States.
Call the 2 models on abliteration.ai through Opper with one API key. Sign up without a credit card.
Every model we route through abliteration.ai. 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 |
|---|---|---|---|---|---|---|
| US | No | 1M | $3.00 | $5.00 | ||
| US | No | 262K | $1.00 | $3.00 |
abliteration.ai 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 or used for training. No training on customer data. US; unknown.
