88API88API
User GuideAI ApplicationsAPI ReferenceHelp & Support

Feature Overview

  1. ๐ŸŽจ Brand new UI (some pages are still being updated)
  2. ๐ŸŒ Multi-language support (to be improved)
  3. ๐ŸŽจ Added Midjourney-Proxy(Plus) API support
  4. ๐Ÿ’ฐ Supports online top-up, can be set in system settings:
    • EasyPay
  5. ๐Ÿ” Supports checking usage by key:
  6. ๐Ÿ“‘ Pagination supports selecting the number of items per page
  7. ๐Ÿ”„ Compatible with the original One API database, can directly use the original database (one-api.db)
  8. ๐Ÿ’ต Supports per-call model billing, can be set in System Settings - Operation Settings
  9. โš–๏ธ Supports random channel weighting
  10. ๐Ÿ“ˆ Data dashboard (dashboard)
  11. ๐Ÿ”’ Can set which models a token can call
  12. ๐Ÿค– Supports Telegram OAuth login:
    1. System Settings - Configure Login/Register - Allow login via Telegram
    2. Send command /setdomain to @Botfather
    3. Select your bot, then enter http(s)://your-website-address/login
    4. Telegram Bot name is the bot username without the @
  13. ๐ŸŽต Added Suno API support
  14. ๐Ÿ”„ Supports Rerank models, currently compatible with Cohere and Jina, can be integrated with Dify
  15. โšก OpenAI Realtime API - Supports OpenAI's Realtime API, supports Azure channels
  16. Supports entering the chat interface via /chat2link route
  17. ๐Ÿง  Supports setting reasoning effort via model name suffix:
    1. OpenAI o-series models
      • Add suffix -high for high reasoning effort (e.g.: o3-mini-high)
      • Add suffix -medium for medium reasoning effort (e.g.: o3-mini-medium)
      • Add suffix -low for low reasoning effort (e.g.: o3-mini-low)
    2. Claude reasoning models
      • Add suffix -thinking to enable reasoning mode (e.g.: claude-3-7-sonnet-20250219-thinking)
  18. ๐Ÿ”„ Reasoning-to-content: supports setting thinking_to_content in Channel - Edit - Channel Extra Settings, default is false. When enabled, reasoning content reasoning_content will be converted to <think> tag and appended to the content in the response.
  19. ๐Ÿ”„ Model rate limiting: supports setting model rate limits in System Settings - Rate Limit Settings, supports setting total request limit and successful request limit
  20. ๐Ÿ’ฐ Cache billing support: after enabling, you can bill according to the set ratio when cache hits occur:
    1. Set prompt cache ratio option in System Settings - Operation Settings
    2. Set prompt cache ratio in channels, range 0-1, e.g. 0.5 means 50% billing on cache hit
    3. Supported channels:
    • OpenAI
    • Azure
    • DeepSeek
    • Claude