SuperAPI AI Directory

HongMaCC

HongMaCC (self-branded as HongMaCode on its official website) is an AI API relay service platform for domestic developers, focusing on direct domestic access to model services such as Claude Code, Codex, and Gemini. It claims millisecond-level response, supports Alipay and WeChat Pay, and requires no VPN. It is suitable for developers who need to call mainstream overseas AI programming/chat model APIs within the domestic network environment. The specific list of available models, pricing, call limits, stability, and compliance status are not yet provided.

Open website

About this tool

HongMaCC is an AI API relay service platform for domestic developers. According to its official introduction, the platform mainly addresses the network and payment obstacles when accessing overseas AI model services from within the country, providing API relay capabilities directly accessible domestically.

Purpose For developers who need to call mainstream overseas AI model APIs within the domestic network environment, especially in scenarios involving development and programming assistance using tools or models such as Claude Code, Codex, and Gemini.

Main capabilities Officially claims direct domestic access to Claude Code, Codex, and Gemini; claims millisecond-level response; supports Alipay and WeChat Pay; can be used without a VPN.

How to use No specific access method, API address, key acquisition process, sample code, or installation commands are provided in the information, and are not yet available.

Applicable scenarios Suitable for developers and teams developing in the domestic network environment who wish to call overseas model APIs such as Claude Code, Codex, and Gemini.

Limitations and notes The information does not specify the specific model versions, call pricing, billing method, rate limits, availability guarantees, data privacy, or compliance policies, and these are not yet provided. The stability, latency performance, and account security of the relay service need to be evaluated by users themselves.