For the complete documentation index, see llms.txt. This page is also available as Markdown.

Rate Limit

Rate Limit is a mechanism used to control the number of requests or tokens within a specified period of time. It helps protect the system from abuse, ensures fairness when multiple users share the

1. Access the Rate Limit Feature

  1. After creating an Authentication Token, navigate to the token list and select the icon in the Action column, as illustrated below, to open the Rate Limit configuration panel.

  1. Or you may select Configure Rate Limit directly when creating an Authentication Token.

2. Create a New Rate Limit Configuration

  1. Limit by (Select one or both options)

  • Requests: Set a limit for the number of API requests.

    • Minimum: 1 request

    • Maximum: 1,000,000 requests

    • Supported time windows:

      • 1 Minute

      • 1 Hour

      • 1 Day

      • 1 Month

    • Window Time Type: Currently supports Fixed Window only.

  • Tokens: Set a limit for the number of tokens consumed

    • Minimum: 100 tokens

    • Maximum: 5,000,000,000 tokens

    • Supported time windows:

      • 1 Minute

      • 1 Hour

      • 1 Day

      • 1 Month

    • Window Time Type: Currently supports Fixed Window only.

3 Nhấn Lưu cấu hình.

Last updated