Abliteration.ai sells hosted GLM-5.3 with its refusal behavior stripped at $5 per million tokens
Abliteration.ai removes refusal behavior from Z.AI's GLM-5.3 at the weight level and rents hosted API access at $5 per million input or output tokens, reporting 84.5% on CyberGym and no stored prompts or responses. The novel part is the packaging, not the technique — abliterated weights have circulated on Hugging Face for years, but a turnkey API with no identity verification removes the GPU and skill barrier for both red teams and attackers. TechCrunch got it to produce Chrome password-extraction code and a pathogen-cultivation guide, while SaferAI found unmodified GLM-5.2 refused zero offensive-security tasks, which puts the real demand for abliteration in question.
Source: the-decoder.com ↗
Abliteration.ai doesn't make its modified weights available for public download. Instead, it handles hosting and operations.
Why this matters
- → Removes GPU/skill barriers for both security testing and malicious actors
- → Demand for abliteration unclear — unmodified GLM-5.2 already refuses zero offensive-security tasks
- → Provider stores no prompts but requires no identity verification, complicating abuse investigation