Message credits system
Our platform operates on a message credits system, where each query posed by a user consumes a certain number of message credits. This system is designed to provide flexibility and efficiency, accommodating the diverse computational needs of different AI models.
Credits Required per Model
Each AI model available on our platform requires a different amount of message credits per query. This structure allows users to select the model that best fits their requirements, balancing between the depth of insight needed and the credits they wish to expend.
Model Group | Model | Credits | ๐ฏ Accuracy | ๐งญ Steerability | ๐ Tool Usage | โก Speed | Reasoning |
---|---|---|---|---|---|---|---|
GPT-5 | GPT-5 | 5 | ๐ฏ๐ฏ๐ฏ๐ฏ๐ฏ 5 | ๐งญ๐งญ๐งญ๐งญ๐งญ 5 | ๐ ๐ ๐ ๐ ๐ 5 | โกโกโก 3 | โ (minimal by default) |
| GPT-5 Mini | 3 | ๐ฏ๐ฏ๐ฏ๐ฏ 4 | ๐งญ๐งญ๐งญ๐งญ 4 | ๐ ๐ ๐ ๐ 4 | โกโกโกโก 4 | โ (minimal by default) |
| GPT-5 Nano | 1 | ๐ฏ๐ฏ๐ฏ 3 | ๐งญ๐งญ๐งญ 3 | ๐ ๐ ๐ ๐ 4 | โกโกโกโกโก 5 | โ (minimal by default) |
GPT-4o | GPT-4o | 5 | ๐ฏ๐ฏ๐ฏ๐ฏ 4 | ๐งญ๐งญ๐งญ 3 | ๐ ๐ ๐ 3 | โกโก 2 | โ |
| GPT-4o Mini | 1 | ๐ฏ๐ฏ 2 | ๐งญ๐งญ 2 | ๐ ๐ 2 | โกโกโกโก 4 | โ |
GPT-4.1 | GPT-4.1 | 4 | ๐ฏ๐ฏ๐ฏ 3 | ๐งญ๐งญ๐งญ๐งญ 4 | ๐ ๐ ๐ ๐ 4 | โกโก 2 | โ |
| GPT-4.1 Mini | 3 | ๐ฏ๐ฏ๐ฏ 3 | ๐งญ๐งญ๐งญ 3 | ๐ ๐ ๐ 3 | โกโกโก 3 | โ |
| GPT-4.1 Nano | 0.5 | ๐ฏ๐ฏ 2 | ๐งญ๐งญ 2 | ๐ ๐ ๐ 3 | โกโกโกโก 4 | โ |
Reasoning | o3 Mini | 12 | ๐ฏ๐ฏ๐ฏ๐ฏ 4 | ๐งญ๐งญ 2 | ๐ ๐ ๐ 3 | โก 1 | โ (medium by default) |
Deprecated | GPT-4 | 60 | ๐ฏ 1 | ๐งญ 1 | ๐ 1 | โก 1 | โ |
| GPT-4 Turbo | 10 | ๐ฏ๐ฏ 2 | ๐งญ 1 | ๐ ๐ 2 | โกโก 2 | โ |
Why the Difference in Credit Cost?
Our AI model offerings are designed to balance accuracy, response time, and computational demand, providing flexibility to meet diverse user needs.
GPT 4o-mini is our base model, delivering fast and accurate responses at a cost-effective price. It is ideal for applications where speed is a priority without compromising too much on accuracy.
GPT 5-nano is currently being considered as our new default model.
GPT 5 is our top recommendation for new projects. It offers the highest accuracy, greatly exceeding the previously recommended GPT 4o.
We no longer recommend GPT 4 and GPT 4 Turbo due to their higher costs and inferior performance metrics compared to GPT 4o and GPT 5. However, these models remain available for users who prefer to maintain the behavior of their existing chatbots.
By choosing between model sizes, users can effectively tailor their experience on our platform according to their specific requirements, whether they prioritize maximum accuracy with GPT 5 or cost-effectiveness with GPT 4o-mini or GPT 5 nano.
Algorithm cost
In addition to the base model costs, we offer the option to enhance your queries with the fusion algorithm. This add-on helps to refine the responses further but requires additional computational resources.
Add-On | Additional Credits Required |
---|---|
Default | 0 credits |
Fusion Algorithm | 1 credit |
Please note that the additional credits for the fusion algorithm are added on top of the base credits required for the selected model.