GPT 4o Mini
GPT 4o Mini, unlike the standard GPT 4 variant, is available primarily for the benefit of free users. The model trades some stability and performance of the standard GPT 4 model for a much faster response time. The model is an unfiltered GPT model available on CrushOn AI. The model is distinct in that it has strong logical reasoning ability, well-structured responses, but more suited for SFW content. And on top of that, sometimes, responses tend to be more formal. Provided by OpenAI, it is derived from the LLM ChatGPT is based on, giving the model an incredibly vast amount of factual knowledge that it could use to its advantage in immersive roleplaying.
- Unlike its standard 4.0 variant, GPT 4o Mini does not come with an Ultra version.
| Free 8K | Pro 8K | Pro 16K | Pro 24K |
|---|---|---|---|
| ✓ | ✓ | ✓ | ✕ |
From here on out, the content may not be fully accurate to each user and act only as general reference. Each user often could see highly different experiences as there are many variables that affect the behavior and quality of the models. From profile cards, the style in which the user converse with the character, the set parameters for the model, and of course the personality of the characters. And periodically, even minimal adjustments made to the model by the developers could also substantially change its behavior whether intended or not.
Strengths and Flaws
Many of the GPT models are often notorious for being 'obviously ChatGPT'. And unfortunately it couldn't be more true for the miniature version of GPT 4.0. Those that are familiar with the quirks and notable way that ChatGPT often presents its responses would often be able to tell immediately that most of the model's responses simply feel like ChatGPT when prompted to roleplay instead of being truly unique or being a believable embodiment of the characters and roles it play. And this is even more apparent in its third person narration. However, this flaw may not entirely be a bad thing. To those more unfamiliar with ChatGPT, the model can still provide fast, immersive, and emotional responses with deep, immersive descriptions, while still being versatile in many scenarios.
The most jarring and frustrating flaw that this model has, however, is likely its incredibly strict filtering, one that remains not so easily jailbroken.
Common Issues with the Model
As specified above, the GPT 4o Mini model suffers quite heavily from an intensely strict filter. And unlike many other models that suffer from this issue, it is not worth it to try and seek jailbreaking with this model. While the model itself is marked as unfiltered, it does better for other adult yet non-sexual topics such as violence, mental issues, substance abuse, etc. But it's still to be noted that extreme scenarios are still rejected by the model outright.
- Trying to switch to another model such as CrushOn Leo, or ticking the "Don't reject what user said" Instruction WILL NOT help you and will likely only serve to waste your coins. It is not advised to try this. Even creator models that mention in the description that it is available for NSFW likely will still struggle heavily against the model's innate filters.
Example of Use
On the right, you could see the example of the models being used regularly with the OC Yumi by Since.