Multi-model AI API platform, one API Key, a set of OpenAI compatible interfaces to call 150+ pictures, videos, speech and large language models (GPT Image 2, Nano Banana, Seedance, Kling, Veo, Claude, Gemini, DeepSeek, etc.), each model automatically switches multiple channels when errors occur, no deductions are made for failed calls, image and video tasks support asynchronous callbacks, the price is generally lower than the official price, and there is no monthly fee for pay-as-you-go billing; you need to write code to call the API
Description translated from the developer's original Chinese by machine translation. 中文原页 ↗
多模型 AI API 平台，一个 API Key、一套 OpenAI 兼容接口调用 150+ 个图片、视频、语音和大语言模型（GPT Image 2、Nano Banana、Seedance、Kling、Veo、Claude、Gemini、DeepSeek 等），每个模型多条渠道出错自动切换、调用失败不扣费、图片视频任务支持异步回调，价格普遍低于官方价，按量计费无月费；需要写代码调用 API
AI plug-in directory, organizes MCP tools, Skills and editor plug-ins according to specific tasks, and provides Chinese usage instructions, access methods and original project links one by one. It has included 124 projects and provides multi-language interfaces such as Chinese and English.
AI picture to layer tool splits a picture into editable named layers and completes the blocked background. It can export PNG/PSD, and can also extract only one element you named; it has a Figma plug-in and a Chrome extension, a web English interface, and each account can be tried once for free
MIT's open source Chrome extension and the local MCP bridge allow Agents such as Codex to use the existing login state to read web pages and prepare forms in the background task window. Users can pause and take over; the Node.js tool needs to be installed and the extension manually loaded.
WYSIWYG Markdown editor supports formulas, tables and Mermaid, optional AI writing assistant gives modification suggestions sentence by sentence, supports more than 20 models such as DeepSeek and Ollama local models; free and open source, no account required, supports macOS, Windows, Linux
AI network environment detection web page, open it and immediately test the current IPv4/IPv6 export region, ASN and proxy/VPN/Tor signal, and detect the connectivity of public resources such as ChatGPT, Claude, Gemini and other services, and identify the exports actually seen by each AI manufacturer; each dimension is listed separately, no single "purity" score is given, and server command line read-only detection is also provided
Natural language task management, just say a word and change it to a structured task operation, which is executed after diff preview and confirmation; supports multi-layer nested subtasks, and the task list can be upgraded to a shared project space (@member + Gantt chart); a CLI with JSON output is also provided for AI agent to call, online version https://ai-todo.stringzhao.life, open source (MIT)
About this listing
This page is part of Indie Maker, a directory of works by Chinese indie developers. We sync daily from the open-source repository chinese-independent-developer; this product was added on 2026-10-18.
About pricingAny pricing, membership, plans or premium features mentioned in a product's description belong to that product itself, not to this directory. We don't build, host or resell any product — the directory is entirely free.