Model registry
The unrestricted registry.
Every uncensored, abliterated and security-tuned model Ophiris serves, behind one OpenAI-compatible endpoint. Compare capabilities, context windows and reference pricing, then see which models get used most and how they score on public benchmarks.
3 models match these filters
Llama 3.3 70B Instruct abliteratedMetaCapabilities: text generation32.8K$0.70$0.70
An abliterated (removed restrictions and censorship) version of Llama 3.3 70b.
- Model ID
- Tier
- Open weights
- Context
- 32,768 tokens
- Added
- Aug 8, 2025
Llama 3 70B abliteratedMetaCapabilities: text generation8.2K$0.70$0.70
An abliterated (removed restrictions and censorship) version of Llama 3.1 70b.
- Model ID
- Tier
- Open weights
- Context
- 8,192 tokens
- Added
- Jul 26, 2025
Neural Daredevil 8B abliteratedMetaCapabilities: text generation8.2K$0.44$0.44
The best performing 8B abliterated model according to most benchmarks.
- Model ID
- Tier
- Open weights
- Context
- 8,192 tokens
- Added
- Jan 1, 2024
Reference pricing in USD per 1M tokens, as published by model providers. Tiers describe model metadata, not benchmark rankings.