xing61/zzz-api

企业级稳定的OpenAI、Claude、Gemini等的API接口-For企业和开发者。OpenAI的api proxy，支持ChatGPT的API调用，支持Anthropic claude的官方接口形式，支持Google gemini的官方接口形式，支持：gpt-5，sora。不需要openai Key, 不需要买openai的账号，不需要美元的银行卡，通通不用的，直接调用就行，稳定好用！！智增增

What it solves

It removes the friction of accessing various frontier AI models (like OpenAI, Claude, and Gemini) for enterprises and developers, eliminating the need for individual foreign accounts or US-based bank cards for payment.

How it works

It acts as a unified API gateway that is compatible with the OpenAI interface format. Users replace the official OpenAI base URL with the project's endpoint and use a provided API key to access a wide range of models from different providers including OpenAI, Google, Anthropic, and several Chinese LLM providers.

Who it’s for

Developers and enterprises who want a stable, centralized way to integrate multiple large language models into their applications without managing multiple separate accounts and payment methods.

Highlights

  • Broad Model Support: Access to OpenAI (including o1, GPT-4o, Sora-2), Claude, Gemini, Grok, and various Chinese models like Wenxin Yiyan and ChatGLM.
  • Full Feature Parity: Supports advanced OpenAI features such as Batch API, Assistants API, Fine-tuning, Embeddings, Whisper (speech-to-text), and TTS (text-to-speech).
  • Easy Integration: Fully compatible with OpenAI's API format, making it a drop-in replacement for existing OpenAI-based code or frameworks like LangChain.
  • Flexible Payment: Supports local payment methods including WeChat and corporate payments.

Related

  • Project
    chatanywhere/GPT_API_free

    A unified API gateway providing direct, proxy-free access to multiple frontier LLMs like GPT, DeepSeek, and Claude using a standardized OpenAI protocol.

  • Project
    QuantumNous/new-api

    New API is an open‑source, self‑hosted gateway that unifies access to many LLM providers behind a single OpenAI‑compatible API. It handles routing, usage/cost tracking, fine‑grained access control, and offers a multilingual web console plus extensible JavaScript task plugins. Deployable via Docker or Docker‑Compose, it’s built with Go (backend) and React/Bun (frontend) and is licensed under AGPL‑v3.

  • Project
    router-for-me/CLIProxyAPI

    CLI Proxy API is an open‑source proxy server that presents a unified OpenAI‑compatible API for many LLM providers (OpenAI, Gemini, Claude, Grok, Kimi, Meta, etc.). It handles OAuth logins, multi‑account load‑balancing, streaming, function calls, and multimodal inputs, and offers optional dashboards for usage and cost tracking. Ideal for developers with multiple AI subscriptions who want a single local endpoint for their CLI tools.

  • Project
    Mirrowel/LLM-API-Key-Proxy

    A self-hosted universal LLM API proxy that provides OpenAI and Anthropic compatible endpoints for multiple providers with built-in key rotation and failover.

  • Project
    justlovemaki/AIClient2API

    AIClient2API is a Node.js‑based proxy that converts client‑only LLM services (Gemini, Claude, Grok, Codex, etc.) into a standard OpenAI‑compatible REST API. It uses adapters to translate requests/responses, supports multi‑account pooling, TLS fingerprint spoofing, and provides a web console, full logging, and agent‑friendly skill files. Run via Docker, configure providers in `configs/provider_pools.json`, and point any OpenAI‑compatible tool to the proxy URL.