中文 | English | Français | 日本語

[!NOTE] MT (Machine Translation): This document is machine translated. For the most accurate information, please refer to the Chinese version.

[!NOTE]
This is an open-source project developed based on One API

[!IMPORTANT]

• This project is for personal learning purposes only, with no guarantee of stability or technical support.
• Users must comply with OpenAI's Terms of Use and applicable laws and regulations, and must not use it for illegal purposes.
• According to the 《Interim Measures for the Management of Generative Artificial Intelligence Services》, please do not provide any unregistered generative AI services to the public in China.

 

No particular order

 

For detailed documentation, please visit our official Wiki: https://docs.newapi.pro/

You can also access the AI-generated DeepWiki:

New API offers a wide range of features, please refer to Features Introduction for details:

1. 🎨 Brand new UI interface
2. 🌍 Multi-language support
3. 💰 Online recharge functionality, currently supports EPay and Stripe
4. 🔍 Support for querying usage quotas with keys (works with neko-api-key-tool)
5. 🔄 Compatible with the original One API database
6. 💵 Support for pay-per-use model pricing
7. ⚖️ Support for weighted random channel selection
8. 📈 Data dashboard (console)
9. 🔒 Token grouping and model restrictions
10. 🤖 Support for more authorization login methods (LinuxDO, Telegram, OIDC)
11. 🔄 Support for Rerank models (Cohere and Jina), API Documentation
12. ⚡ Support for OpenAI Realtime API (including Azure channels), API Documentation
13. ⚡ Support for OpenAI Responses format, API Documentation
14. ⚡ Support for Claude Messages format, API Documentation
15. ⚡ Support for Google Gemini format, API Documentation
16. 🧠 Support for setting reasoning effort through model name suffixes:
    1. OpenAI o-series models
       • Add -high suffix for high reasoning effort (e.g.: o3-mini-high)
       • Add -medium suffix for medium reasoning effort (e.g.: o3-mini-medium)
       • Add -low suffix for low reasoning effort (e.g.: o3-mini-low)
    2. Claude thinking models
       • Add -thinking suffix to enable thinking mode (e.g.: claude-3-7-sonnet-20250219-thinking)
17. 🔄 Thinking-to-content functionality
18. 🔄 Model rate limiting for users
19. 🔄 Request format conversion functionality, supporting the following three format conversions:
    1. OpenAI Chat Completions => Claude Messages
    2. Claude Messages => OpenAI Chat Completions (can be used for Claude Code to call third-party models)
    3. OpenAI Chat Completions => Gemini Chat
20. 💰 Cache billing support, which allows billing at a set ratio when cache is hit:
    1. Set the Prompt Cache Ratio option in System Settings-Operation Settings
    2. Set Prompt Cache Ratio in the channel, range 0-1, e.g., setting to 0.5 means billing at 50% when cache is hit
    3. Supported channels:
       • OpenAI
       • Azure
       • DeepSeek
       • Claude

This version supports multiple models, please refer to API Documentation-Relay Interface for details:

1. Third-party models gpts (gpt-4-gizmo-*)
2. Third-party channel Midjourney-Proxy(Plus) interface, API Documentation
3. Third-party channel Suno API interface, API Documentation
4. Custom channels, supporting full call address input
5. Rerank models (Cohere and Jina), API Documentation
6. Claude Messages format, API Documentation
7. Google Gemini format, API Documentation
8. Dify, currently only supports chatflow
9. For more interfaces, please refer to API Documentation

For detailed configuration instructions, please refer to Installation Guide-Environment Variables Configuration:

• GENERATE_DEFAULT_TOKEN: Whether to generate initial tokens for newly registered users, default is false
• STREAMING_TIMEOUT: Streaming response timeout, default is 300 seconds
• DIFY_DEBUG: Whether to output workflow and node information for Dify channels, default is true
• GET_MEDIA_TOKEN: Whether to count image tokens, default is true
• GET_MEDIA_TOKEN_NOT_STREAM: Whether to count image tokens in non-streaming cases, default is true
• UPDATE_TASK: Whether to update asynchronous tasks (Midjourney, Suno), default is true
• GEMINI_VISION_MAX_IMAGE_NUM: Maximum number of images for Gemini models, default is 16
• MAX_FILE_DOWNLOAD_MB: Maximum file download size in MB, default is 20
• CRYPTO_SECRET: Encryption key used for encrypting Redis database content
• AZURE_DEFAULT_API_VERSION: Azure channel default API version, default is 2025-04-01-preview
• NOTIFICATION_LIMIT_DURATION_MINUTE: Notification limit duration, default is 10 minutes
• NOTIFY_LIMIT_COUNT: Maximum number of user notifications within the specified duration, default is 2
• ERROR_LOG_ENABLED=true: Whether to record and display error logs, default is false

For detailed deployment guides, please refer to Installation Guide-Deployment Methods:

[!TIP] Latest Docker image: calciumion/new-api:latest

• Environment variable SESSION_SECRET must be set, otherwise login status will be inconsistent across multiple machines
• If sharing Redis, CRYPTO_SECRET must be set, otherwise Redis content cannot be accessed across multiple machines

• Local database (default): SQLite (Docker deployment must mount the /data directory)
• Remote database: MySQL version >= 5.7.8, PgSQL version >= 9.6

Install BaoTa Panel (version 9.2.0 or above), find New-API in the application store and install it. Tutorial with images

# Download the project
git clone https://github.com/Calcium-Ion/new-api.git
cd new-api
# Edit docker-compose.yml as needed
# Start
docker-compose up -d

# Using SQLite
docker run --name new-api -d --restart always -p 3000:3000 -e TZ=Asia/Shanghai -v /home/ubuntu/data/new-api:/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 /home/ubuntu/data/new-api:/data calciumion/new-api:latest

Channel retry functionality has been implemented, you can set the number of retries in Settings->Operation Settings->General Settings->Failure Retry Count, recommended to enable caching functionality.

1. REDIS_CONN_STRING: Set Redis as cache
2. MEMORY_CACHE_ENABLED: Enable memory cache (no need to set manually if Redis is set)

For detailed API documentation, please refer to API Documentation:

• Chat API (Chat Completions)
• Response API (Responses)
• Image API (Image)
• Rerank API (Rerank)
• Realtime Chat API (Realtime)
• Claude Chat API
• Google Gemini Chat API

• One API: Original project
• Midjourney-Proxy: Midjourney interface support
• neko-api-key-tool: Query usage quota with key

Other projects based on New API:

• new-api-horizon: High-performance optimized version of New API

If you have any questions, please refer to Help and Support:

• Community Interaction
• Issue Feedback
• FAQ