Skip to content

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. πŸ₯

License

Notifications You must be signed in to change notification settings

QuantumNous/new-api

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

new-api

New API

πŸ₯ Next-Generation LLM Gateway and AI Asset Management System

δΈ­ζ–‡ | English | FranΓ§ais | ζ—₯本θͺž

license release docker docker GoReportCard

Calcium-Ion%2Fnew-api | Trendshift
Featured|HelloGitHub New API - All-in-one AI asset management gateway. | Product Hunt

Quick Start β€’ Key Features β€’ Deployment β€’ Documentation β€’ Help

πŸ“ Project Description

Note

This is an open-source project developed based on One API

Important


🀝 Trusted Partners

No particular order

Cherry Studio Peking University UCloud Alibaba Cloud IO.NET


πŸ™ Special Thanks

JetBrains Logo

Thanks to JetBrains for providing free open-source development license for this project


πŸš€ Quick Start

Using Docker Compose (Recommended)

# Clone the project
git clone https://github.com/QuantumNous/new-api.git
cd new-api

# Edit docker-compose.yml configuration
nano docker-compose.yml

# Start the service
docker-compose up -d
Using Docker Commands
# Pull the latest image
docker pull calciumion/new-api:latest

# Using SQLite (default)
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest

# Using MySQL
docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest

πŸ’‘ Tip: -v ./data:/data will save data in the data folder of the current directory, you can also change it to an absolute path like -v /your/custom/path:/data


πŸŽ‰ After deployment is complete, visit http://localhost:3000 to start using!

πŸ“– For more deployment methods, please refer to Deployment Guide


πŸ“š Documentation

Quick Navigation:

Category Link
πŸš€ Deployment Guide Installation Documentation
βš™οΈ Environment Configuration Environment Variables
πŸ“‘ API Documentation API Documentation
❓ FAQ FAQ
πŸ’¬ Community Interaction Communication Channels

✨ Key Features

For detailed features, please refer to Features Introduction

🎨 Core Functions

Feature Description
🎨 New UI Modern user interface design
🌍 Multi-language Supports Chinese, English, French, Japanese
πŸ”„ Data Compatibility Fully compatible with the original One API database
πŸ“ˆ Data Dashboard Visual console and statistical analysis
πŸ”’ Permission Management Token grouping, model restrictions, user management

πŸ’° Payment and Billing

  • βœ… Online recharge (EPay, Stripe)
  • βœ… Pay-per-use model pricing
  • βœ… Cache billing support (OpenAI, Azure, DeepSeek, Claude, Qwen and all supported models)
  • βœ… Flexible billing policy configuration

πŸ” Authorization and Security

  • 😈 Discord authorization login
  • πŸ€– LinuxDO authorization login
  • πŸ“± Telegram authorization login
  • πŸ”‘ OIDC unified authentication
  • πŸ” Key quota query usage (with neko-api-key-tool)

πŸš€ Advanced Features

API Format Support:

Intelligent Routing:

  • βš–οΈ Channel weighted random
  • πŸ”„ Automatic retry on failure
  • 🚦 User-level model rate limiting

Format Conversion:

  • πŸ”„ OpenAI Compatible ⇄ Claude Messages
  • πŸ”„ OpenAI Compatible β†’ Google Gemini
  • πŸ”„ Google Gemini β†’ OpenAI Compatible - Text only, function calling not supported yet
  • 🚧 OpenAI Compatible ⇄ OpenAI Responses - In development
  • πŸ”„ Thinking-to-content functionality

Reasoning Effort Support:

View detailed configuration

OpenAI series models:

  • o3-mini-high - High reasoning effort
  • o3-mini-medium - Medium reasoning effort
  • o3-mini-low - Low reasoning effort
  • gpt-5-high - High reasoning effort
  • gpt-5-medium - Medium reasoning effort
  • gpt-5-low - Low reasoning effort

Claude thinking models:

  • claude-3-7-sonnet-20250219-thinking - Enable thinking mode

Google Gemini series models:

  • gemini-2.5-flash-thinking - Enable thinking mode
  • gemini-2.5-flash-nothinking - Disable thinking mode
  • gemini-2.5-pro-thinking - Enable thinking mode
  • gemini-2.5-pro-thinking-128 - Enable thinking mode with thinking budget of 128 tokens
  • You can also append -low, -medium, or -high to any Gemini model name to request the corresponding reasoning effort (no extra thinking-budget suffix needed).

πŸ€– Model Support

For details, please refer to API Documentation - Relay Interface

Model Type Description Documentation
πŸ€– OpenAI-Compatible OpenAI compatible models Documentation
πŸ€– OpenAI Responses OpenAI Responses format Documentation
🎨 Midjourney-Proxy Midjourney-Proxy(Plus) Documentation
🎡 Suno-API Suno API Documentation
πŸ”„ Rerank Cohere, Jina Documentation
πŸ’¬ Claude Messages format Documentation
🌐 Gemini Google Gemini format Documentation
πŸ”§ Dify ChatFlow mode -
🎯 Custom Supports complete call address -

πŸ“‘ Supported Interfaces

View complete interface list

🚒 Deployment

Tip

Latest Docker image: calciumion/new-api:latest

πŸ“‹ Deployment Requirements

Component Requirement
Local database SQLite (Docker must mount /data directory)
Remote database MySQL β‰₯ 5.7.8 or PostgreSQL β‰₯ 9.6
Container engine Docker / Docker Compose

βš™οΈ Environment Variable Configuration

Common environment variable configuration
Variable Name Description Default Value
SESSION_SECRET Session secret (required for multi-machine deployment) -
CRYPTO_SECRET Encryption secret (required for Redis) -
SQL_DSN Database connection string -
REDIS_CONN_STRING Redis connection string -
STREAMING_TIMEOUT Streaming timeout (seconds) 300
STREAM_SCANNER_MAX_BUFFER_MB Max per-line buffer (MB) for the stream scanner; increase when upstream sends huge image/base64 payloads 64
MAX_REQUEST_BODY_MB Max request body size (MB, counted after decompression; prevents huge requests/zip bombs from exhausting memory). Exceeding it returns 413 32
AZURE_DEFAULT_API_VERSION Azure API version 2025-04-01-preview
ERROR_LOG_ENABLED Error log switch false
PYROSCOPE_URL Pyroscope server address -
PYROSCOPE_APP_NAME Pyroscope application name new-api
PYROSCOPE_BASIC_AUTH_USER Pyroscope basic auth user -
PYROSCOPE_BASIC_AUTH_PASSWORD Pyroscope basic auth password -
PYROSCOPE_MUTEX_RATE Pyroscope mutex sampling rate 5
PYROSCOPE_BLOCK_RATE Pyroscope block sampling rate 5
HOSTNAME Hostname tag for Pyroscope new-api

πŸ“– Complete configuration: Environment Variables Documentation

πŸ”§ Deployment Methods

Method 1: Docker Compose (Recommended)
# Clone the project
git clone https://github.com/QuantumNous/new-api.git
cd new-api

# Edit configuration
nano docker-compose.yml

# Start service
docker-compose up -d
Method 2: Docker Commands

Using SQLite:

docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest

Using MySQL:

docker run --name new-api -d --restart always \
  -p 3000:3000 \
  -e SQL_DSN="root:123456@tcp(localhost:3306)/oneapi" \
  -e TZ=Asia/Shanghai \
  -v ./data:/data \
  calciumion/new-api:latest

πŸ’‘ Path explanation:

  • ./data:/data - Relative path, data saved in the data folder of the current directory
  • You can also use absolute path, e.g.: /your/custom/path:/data
Method 3: BaoTa Panel
  1. Install BaoTa Panel (β‰₯ 9.2.0 version)
  2. Search for New-API in the application store
  3. One-click installation

πŸ“– Tutorial with images

⚠️ Multi-machine Deployment Considerations

Warning

  • Must set SESSION_SECRET - Otherwise login status inconsistent
  • Shared Redis must set CRYPTO_SECRET - Otherwise data cannot be decrypted

πŸ”„ Channel Retry and Cache

Retry configuration: Settings β†’ Operation Settings β†’ General Settings β†’ Failure Retry Count

Cache configuration:

  • REDIS_CONN_STRING: Redis cache (recommended)
  • MEMORY_CACHE_ENABLED: Memory cache

πŸ”— Related Projects

Upstream Projects

Project Description
One API Original project base
Midjourney-Proxy Midjourney interface support

Supporting Tools

Project Description
neko-api-key-tool Key quota query tool
new-api-horizon New API high-performance optimized version

πŸ’¬ Help Support

πŸ“– Documentation Resources

Resource Link
πŸ“˜ FAQ FAQ
πŸ’¬ Community Interaction Communication Channels
πŸ› Issue Feedback Issue Feedback
πŸ“š Complete Documentation Official Documentation

🀝 Contribution Guide

Welcome all forms of contribution!

  • πŸ› Report Bugs
  • πŸ’‘ Propose New Features
  • πŸ“ Improve Documentation
  • πŸ”§ Submit Code

🌟 Star History

Star History Chart


πŸ’– Thank you for using New API

If this project is helpful to you, welcome to give us a ⭐️ Star!

Official Documentation β€’ Issue Feedback β€’ Latest Release

Built with ❀️ by QuantumNous

About

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. πŸ₯

Topics

Resources

License

Code of conduct

Security policy

Stars

Watchers

Forks

Sponsor this project

Packages

No packages published

Contributors 199