Access all large models through the standard OpenAI API format and use it out of the box This project is an open source project. Users must use it in accordance with OpenAI's terms of use and laws and regulations, and must not use it for illegal purposes. According to the requirements of the Interim Measures for the Management of Generative Artificial Intelligence Services, please do not provide all unregistered generative artificial intelligence services to the public in China. Account number: root/123456 ##Function 1. Support multiple large models: + [x] [OpenAI ChatGPT Series Model](https://platform.openai.com/docs/guides/gpt/chat-completions-api)(Support [Azure OpenAI API](https://learn.microsoft.com/en-us/azure/ai-services/openai/reference)) + [x] [Anthropic Claude Series Models](anthropic.com) (Supports AWS Claude) + [x] [Google PaLM2/Gemini Series Models](developers.generativeai.google) + [x] [Mistral Series Models](https://mistral.ai/) + [x] [ByteDance Bean Bag Big Model](https://console.volcengine.com/ark/region:ark+cn-beijing/model) + [x] [Baidu Wenxin Yiyan Series Models](https://cloud.baidu.com/doc/WENXINWORKSHOP/index.html) + [x] [Ali Tongyi Thousand Questions Series Models](https://help.aliyun.com/document_detail/2400395.html) + [x] [iFlytek Spark Cognitive Model](https://www.xfyun.cn/doc/spark/Web.html) + [x] [ChatGLM Series Models](bigmodel.cn) + [x] [360 Intelligent Brain](ai.360.cn) + [x] [Tencent Mixed Model](https://cloud.tencent.com/document/product/1729) + [x] [Moonshot AI](https://platform.moonshot.cn/) + [x] [Baichuan Model](platform.baichuan-ai.com) + [x] [MINIMAX](https://api.minimax.chat/) + [x] [Groq](https://wow.groq.com/) + [x] [Ollama](https://github.com/ollama/ollama) + [x] [One and One Things](https://platform.lingyiwanwu.com/) + [x] [Step Stars](https://platform.stepfun.com/) + [x] [Coze](https://www.coze.com/) + [x] [Cohere](https://cohere.com/) + [x] [DeepSeek](https://www.deepseek.com/) + [x] [Cloudflare Workers AI](https://developers.cloudflare.com/workers-ai/) + [x] [DeepL](https://www.deepl.com/) + [x] [together.ai](https://www.together.ai/) + [x] [novita.ai](https://www.novita.ai/) + [x] [SiliconCloud](https://siliconflow.cn/siliconcloud) + [x] [xAI](https://x.ai/) 2. Supports configuring images and numerous [third-party proxy services](https://iamazing.cn/page/openai-api-third-party-services). 3. Support accessing multiple channels through ** Load Balancer **. 4. Support **stream mode **, which can achieve typewriter effects through streaming. 5. Support ** multi-machine deployment **,[see here for details](#multi-machine deployment). 6. Support ** token management ** and set the expiration time, quota, allowed IP range and allowed model access of the token. 7. Supports ** redemption code management **, supports batch generation and export of redemption codes, and you can use the redemption code to recharge your account. 8. Support ** channel management ** and create channels in batches. 9. Support ** user grouping ** and ** channel grouping **, and support setting different ratios for different groups. 10. Support channels ** Set up model list **. 11. Support ** View the quota details **. 12. Support ** User invitation rewards **. 13. Support displaying quotas in US dollars. 14. Support issuing announcements, setting recharge links, and setting initial quotas for new users. 15. Support model mapping and redirect the user's request model. Please do not set it if it is not necessary. After setting, the request body will be reconstructed rather than directly transmitted through, and some fields that have not yet been officially supported cannot be successfully delivered. 16. Supports automatic retry for failure. 17. Support drawing interface. 18. Support [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/providers/openai/), just fill in `https://gateway.ai.cloudflare.com/v1/ACCOUNT_TAG/GATEWAY/openai` in the proxy section of channel settings. 19. Support rich ** custom ** settings, 1. Support custom system names, logos and footers. 2. Support customization of the home page and about page. You can choose to customize it using HTML & Markdown code, or use a separate web page to embed it through iframe. 20. Support calling the management API through the system access token, and then ** extend and customize the functions of the ** One API without having to open it. For details, please refer to [API Documentation] here (./ docs/API.md)。。 21. Supports Cloudflare Turnstile user verification. 22. Support user management and support ** multiple user login and registration methods **: + Email login registration (support registration of email whitelist) and password reset through email. + Support [Feishu-authorized login](https://open.feishu.cn/document/uAjLw4CM/ukTukTukTM/reference/authen-v1/authorize/get)([Here are the implementation details of One API for reference](https://iamazing.cn/page/feishu-oauth-login)). + Support [GitHub Authorized Login](https://github.com/settings/applications/new). + Authorization on Weixin Official Accounts (additional deployment of [WeChat Server](https://github.com/songquanpeng/wechat-server) is required). 23. Support theme switching. Just set the environment variable `THEME`. The default is `default`. Welcome more PR topics. Please refer to [here](./ web/README.md)。 24. Use [Message Pusher](https://github.com/songquanpeng/message-pusher) to push alarm messages to multiple apps.
