Skip to main content

Usage

ai12z Copilot Platform - Usage Screen Documentation​

Overview​

The Usage Screen in the ai12z Copilot platform provides users with detailed insights into their usage statistics, balance, and token consumption across different AI models and services. This screen helps users monitor their usage, manage their budget, and optimize their AI resource allocation.

Usage of all your servers, LLM, embeddings, agents, advance scraping cost

Sections and Components​

1. Balance Section​

  • Date Range: Displays the selected date range for the usage data. By default, it shows from the start of the current billing cycle to the present.
  • Remaining Balance: Shows the current remaining balance in the user's account.
  • Threshold Amount (Thresh Amount): The minimum balance threshold set by the user to receive alerts when the balance falls below this amount.
  • Purchased Amount: The total amount of funds added to the account during the selected date range.
  • Balance Bar: A visual representation of the balance, threshold, and purchased amount to give a quick overview of the account status.

2. Token Consumption Charts​

Each chart in this section provides detailed information about the token usage and associated costs for different AI models and services.

  • GPT 3.5 Turbo (0613) 4k

    • Input Tokens: The number of input tokens consumed and the associated cost.
    • Output Tokens: The number of output tokens generated and the associated cost.
    • Graph: A line chart displaying the input and output token usage over the selected date range.

  • GPT 4 (1106-Preview)

    • Input Tokens: The number of input tokens consumed and the associated cost.
    • Output Tokens: The number of output tokens generated and the associated cost.
    • Graph: A line chart displaying the input and output token usage over the selected date range.

  • GPT 3.5 Turbo (0125) 16k

    • Input Tokens: The number of input tokens consumed and the associated cost.
    • Output Tokens: The number of output tokens generated and the associated cost.
    • Graph: A line chart displaying the input and output token usage over the selected date range.

  • GPT-4o

    • Input Tokens: The number of input tokens consumed and the associated cost.
    • Output Tokens: The number of output tokens generated and the associated cost.
    • Graph: A line chart displaying the input and output token usage over the selected date range.

  • Text Embedding 3 Small

    • Embedding Tokens: The number of embedding tokens consumed and the associated cost.
    • Graph: A line chart displaying the embedding token usage over the selected date range.

3. Requests Section​

  • Total Requests: The total number of requests made and the associated cost.
  • Graph: An area chart displaying the number of requests made over the selected date range.

How to Use the Usage Screen​

  1. Select Date Range:

    • Use the date picker to select the desired date range for which you want to view the usage data.

  2. Review Balance Information:

    • Check the remaining balance to ensure you have sufficient funds.
    • Monitor the threshold amount to avoid running out of balance unexpectedly.

  3. Analyze Token Consumption:

    • Review the token consumption charts to understand how many tokens you are using for each AI model and service.
    • Use the graphs to identify trends and peaks in usage, which can help in optimizing your AI resource allocation.

  4. Monitor Requests:

    • Keep track of the total number of requests to ensure you are within your usage limits.
    • Use the area chart to identify periods of high request activity.

Tips for Optimizing Usage​

  • Set Alerts: Configure alerts for when your balance falls below the threshold amount to prevent disruptions in service.
  • Analyze Trends: Regularly review the usage graphs to identify patterns and optimize your usage accordingly.
  • Budget Management: Use the balance and cost information to manage your budget effectively and allocate resources where they are needed most.

The Usage Screen in the ai12z Copilot platform is designed to give you comprehensive insights into your AI usage, helping you stay informed and in control of your AI resource consumption.