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
Rank 7 this week: MiMo V2.6 Flash AbliteratedxiaomiCapabilities: Reasoning, Tools, Vision1M$0.50$1.50
A MiMo V2.6 Flash finetune with refusal-direction ablation, image input, a 1M-token context window, separate reasoning output, and tool calling.
- Model ID
- Tier
- Open weights
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Added
- Sep 25
Rank 17 this week: MiMo V2.6 Flash UncensoredxiaomiCapabilities: Reasoning, Tools, Vision1M$0.50$1.50
A lower-refusal MiMo V2.6 Flash finetune with a 1M-token context window, separate reasoning output, and tool calling. Supports image input and adjustable thinking effort.
- Model ID
- Tier
- Open weights
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Added
- Sep 25
Rank 24 this week: MiMo V2.6 Flash Uncensored ThinkingxiaomiCapabilities: Reasoning, Tools, Vision1M$0.50$1.50
MiMo V2.6 Flash Uncensored with maximum thinking enabled. Supports a 1M-token context window and tool calling.
- Model ID
- Tier
- Open weights
- Context
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Added
- Sep 26
Reference pricing in USD per 1M tokens, as published by model providers. Tiers describe model metadata, not benchmark rankings.