Heabsy
AI model developer and inference platform operated by FEYA.
Heabsy develops specialist derivatives of open-weight language models and operates an inference platform. Its releases include CyberHeabsy and its own Qwen Uncensored Fast build. Model cards identify the underlying families and changes for each release.
heabsy.comCall Heabsy models through Opper with one API key. Sign up without a credit card. Abliterated models are enabled per account after a review. About abliterated models
Models from Heabsy
| Model | Context | Provider | Region | Zero data retention | Training | Input | Output | Cache read |
|---|---|---|---|---|---|---|---|---|
| 1M | EU | No | $1.21 | $3.64 | $0.22 | |||
| 524K | EU | No | $0.67 | $2.12 | $0.12 |
Release timeline
Every dated Heabsy release, newest first — 1 of 1 run on the Opper gateway today. Releases without a published date aren't listed. See the AI model release tracker.