Advanced AI Requests Usage
View and manage your workspace usage to avoid unexpected expenses.
Last updated
View and manage your workspace usage to avoid unexpected expenses.
Last updated
Bito Inc. (c) 2024
If you are on a paid plan, such as the 10X Developer Plan, and are the owner or admin of a workspace, you can easily view the Advanced AI Model requests (GPT-4o or similar) included for the current month and the number of requests used by your workspace members and AI Agents. If you are on the Forever Free plan, this plan does not include Advanced AI Model requests, so this feature is not relevant to your plan.
To view your usage, simply visit the Requests Usage dashboard.
You can switch between the Usage by members and Usage by agents tabs to view the detailed usage.
Bito uses different AI models (Large Language Models) to offer its services. Some Basic AI models can be used for free, like GPT-4o mini and similar models, while other Advanced AI models like GPT-4o and Anthropic's Claude Sonnet 3.5 are only accessible through paid plans.
When you select the Advanced tab in the Bito IDE chat user interface and ask a question, the system uses Bito’s Advanced AI models in the background to process that request. This type of request is called an Advanced AI Model Request.
Note: Bito Dev Agents, such as the AI Code Review Agent, only use Advanced AI Model Request.
When your Advanced AI Model Request quota is used up, we charge $0.03 per additional request.
To ensure that you have full control over your workspace usage and avoid unexpected expenses, we provide two controls. These are:
Hard Limits
Soft Limits
These controls can be accessed via the Usage Management dashboard. They are designed to help you manage your spending effectively and stay within your intended budget.
You can enter any number (amount in US Dollars) to set Hard and Soft Limits.
Tip: Leave the text box empty for unlimited requests. This mean, your Advanced AI Model requests will not be blocked.
Hard Limit enables workspace owners and admins to automatically block the usage of Advanced AI Model requests when they reach the pre-defined threshold per month.
We highly recommend setting the Hard Limit for your workspace to avoid surprises and stick to your budget.
If the Hard Limit is not set on a workspace, then members can continue to make additional Advanced AI Model requests beyond the available quota without any issues. However, please remember that all of these additional requests will be charged at the rate of $0.03 per request and billed at the end of the month.
To give an example, if you have 2 users in your workspace, then you will receive 1200 Advanced AI model requests per month. If you were to use 1300, which is 100 additional, then you would be charged US $0.03 per additional request, or $3 for 100 requests, in addition to your $30 monthly bill for 2 users.
The workspace owners and admins will get an email notification when the Advanced AI Model requests limit allocated as per the current plan is reached.
If the Hard Limit is set on a workspace, then all of its members will be blocked from making any Advanced AI Model requests when the workspace quota is finished. However, they can still use Basic models (20 AI requests per day per user), which are available in our Forever Free plan.
When the Hard Limit is reached then the owners and admins of the workspace will be notified through an email.
Go to the Usage Management dashboard.
Enter your desired number in the Hard limit input field to set a threshold for the total Advanced AI Model requests allowed on your workspace.
Press the Save button to confirm your settings.
Soft Limit is a warning system that alerts the workspace owners and admins by sending them an email notification when their use of the Advanced AI model reaches a pre-defined threshold.
Unlike a Hard Limit, the Soft Limit does not block workspace members from using the Advanced AI model requests. Its sole purpose is to notify the workspace owners and admins.
The Soft Limit has no impact on the workspace usage, whether set or not. However, we recommend setting a Soft Limit on your workspace to receive an early notification before reaching the Hard Limit.
Go to the Usage Management dashboard.
Enter your desired number in the Soft limit input field to set a threshold for the total Advanced AI Model requests consumed after which an email notification will be sent.
Press the Save button to confirm your settings.
