Documentation renewed! For old docs, visit doc.newapi.pro
New APINew API
User GuideInstallationAPI ReferenceAI ApplicationsHelp & SupportBusiness Cooperation

Feature Description

  1. 🎨 Brand new UI interface (some interfaces are still pending updates)
  2. 🌍 Multi-language support (to be improved)
  3. 🎨 Added Midjourney-Proxy(Plus) API support
  4. 💰 Supports online top-up functionality, configurable in System Settings:
      • Epay
  5. 🔍 Supports querying usage Quota by key:
    • In conjunction with the project neko-api-key-tool, querying usage by key can be achieved.
  6. 📑 Pagination supports selecting the number of items displayed per page
  7. 🔄 SQLite database storage support, ready to use out of the box, lightweight and convenient
  8. 💵 Supports model billing by usage count, configurable in System Settings - Operation Settings
  9. ⚖️ Supports weighted random Channel selection
  10. 📈 Data Dashboard (Console)
  11. 🔒 Configurable models that a Token can call
  12. 🤖 Supports Telegram authorized login:
    1. System Settings - Configure Login & Registration - Allow login via Telegram
    2. Enter command /setdomain to @Botfather
    3. Select your bot, then enter http(s)://your_website_address/login
    4. The Telegram Bot Name is the bot username string without the @
  13. 🎵 Added Suno API API support
  14. 🔄 Supports Rerank models, currently compatible with Cohere and Jina, and can be integrated with Dify
  15. ⚡ OpenAI Realtime API - Supports OpenAI's Realtime API, supports Azure Channel
  16. Supports using the route /chat2link to enter the chat interface
  17. 🧠 Supports setting reasoning effort via model name suffix:
    1. OpenAI o-series models
        • Add suffix -high to set as high reasoning effort (e.g.: o3-mini-high)
        • Add suffix -medium to set as medium reasoning effort (e.g.: o3-mini-medium)
        • Add suffix -low to set as low reasoning effort (e.g.: o3-mini-low)
    2. Claude thinking models
        • Add suffix -thinking to enable thinking mode (e.g.: claude-3-7-sonnet-20250219-thinking)
  18. 🔄 Thinking to Content, supports setting the thinking_to_content option in Channel - Edit - Channel Extra Settings, default false. When enabled, it will convert the thinking content reasoning_content into a <think> tag and append it to the returned content.
  19. 🔄 Model Rate Limiting, supports setting model rate limits in System Settings - Rate Limit Settings, including total request count limit and successful request count limit.
  20. 💰 Cache Billing Support, when enabled, billing can occur at a set Ratio upon cache hit:
    1. Set the Prompt Cache Ratio option in System Settings - Operation Settings
    2. Set the Prompt Cache Ratio in the Channel, range 0-1. For example, setting it to 0.5 means billing at 50% upon cache hit.
    3. Supported Channels:
        • OpenAI
        • Azure
        • DeepSeek
        • Claude

How is this guide?

Last updated on

Project Introduction

Learn about New API, the next-generation AI Gateway and Asset Management System

Technical Architecture

Next Page

On this page

No Headings