This project is an API proxy that provides free and paid access to ChatGPT models through an OpenAI-compatible endpoint. It acts as a reverse proxy, routing requests to ChatGPT while maintaining full compatibility with OpenAI's SDK interface, allowing any application or tool that supports a custom base URL and API key to connect.
The service offers a free tier that provides access to ChatGPT models for chat, image generation, and voice dialogue without requiring an official subscription, along with a paid tier that unlocks over 130 OpenAI models including GPT-4 with lower latency and reduced pricing. Both tiers support streaming chat responses, delivering output incrementally as it is generated for real-time display.
The proxy integrates with a wide range of clients, including official OpenAI SDKs for Python and Node.js, open-source web chat interfaces, desktop tools, and third-party applications. It also supports connecting knowledge-base-enabled chat applications for context-aware conversations, and enforces rate limiting on the free tier to manage usage.