A comprehensive unified API gateway providing access to over 300 AI models for chat, image, video, and audio generation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-api-transit-station
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ai-api-transit-station using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AIAPI-Doc?
AIAPI-Doc is a powerful technical skill designed to streamline access to a massive ecosystem of artificial intelligence interfaces. By leveraging Openclaw Skills, developers can interact with 302+ distinct API endpoints through a single unified gateway, covering everything from Large Language Models like GPT and Claude to advanced media generation tools like Sora, Midjourney, and Suno. This skill eliminates the complexity of managing multiple providers by offering a standardized authentication and request pattern for the world's leading AI technologies.
The skill provides a robust foundation for building multi-modal applications. Whether you need to process text, generate high-fidelity images, synthesize video from text or images, or handle complex audio transcriptions, AIAPI-Doc ensures a consistent developer experience. It is particularly optimized for Openclaw Skills environments where rapid prototyping and cross-model functionality are essential.
AIAPI-Doc Use Cases
- Building multi-model chat interfaces that toggle between GPT, Claude, Gemini, and DeepSeek.
- Automating high-quality video production using asynchronous Sora or Kling video generation tasks.
- Creating image-to-video workflows by first uploading local assets to the integrated image proxy.
- Implementing professional-grade AI music and audio synthesis for creative applications.
- Developing automated research tools using integrated web search and document analysis functions via Openclaw Skills.
How AIAPI-Doc Works
- Obtain a Bearer Token by registering at the centralized provider dashboard.
- Configure your requests to use the unified base URL for all 302+ supported interfaces.
- Send POST requests to specific endpoints like Chat Completions or Image Generations with your API key in the header.
- For media generation (Video/Music), initiate an asynchronous task and receive a unique task ID.
- Implement a polling loop (suggested 5-10 second intervals) to check the task status via the query endpoint.
- Retrieve the final generated resource URL or data once the task status reaches the completed state.
AIAPI-Doc Setup
To start using this skill with Openclaw Skills, ensure you have your API token ready. You can configure your environment as follows:
# Export your API token for use in your applications
export AI_API_TOKEN="your_sk_token_here"
# Example: Simple Chat Completion request
curl --location 'https://api.winfull.cloud-ip.cc/v1/chat/completions' \
--header "Authorization: Bearer $AI_API_TOKEN" \
--header 'Content-Type: application/json' \
--data '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello, how can I use Openclaw Skills?"}]
}'
AIAPI-Doc Data Schema & Taxonomy
AIAPI-Doc organizes its vast API library into logical categories to simplify discovery within Openclaw Skills. The following table summarizes the data distribution:
| Category | Interface Count | Primary Models Supported |
|---|---|---|
| Image Generation | 82 | DALL-E, Flux, Ideogram, Imagen |
| Video Generation | 54 | Sora, Veo, Kling, Minimax |
| Chat | 43 | GPT-4, Claude 3.5, Gemini 1.5, DeepSeek |
| Task Management | 33 | Async polling for Video/Music tasks |
| Audio & TTS | 16 | Whisper-1, Suno, TTS-1, Audio Understanding |
| Midjourney | 8 | Imagine, Upscale, Variation |
| System & Tools | 16 | File Upload, Token Management, Function Calling |
AIAPI-Doc Advanced Features
- Asynchronous Workflow Management: Specialized endpoints to handle long-running video and music generation tasks with polling logic.
- Integrated Image Proxy: A dedicated upload service at imageproxy.zhongzhuan.chat to convert local files into public URLs for image-to-video generation.
- Full Midjourney Suite: Support for complex Midjourney commands including --ar, --v, and image-to-image prompts through Openclaw Skills.
- Function Calling Support: Native integration for web search and custom code execution within chat completions.
- Multi-Modal Embeddings: High-performance vectorization endpoints for building RAG (Retrieval-Augmented Generation) systems.
SKILL.md
Loading
Related Openclaw Skills
ClawControl Logger
A continuous observability skill that provides real-time, audit-ready logging for every action taken by an AI agent.
metacognition-lite
A lightweight, model-agnostic thinking framework that adds a structured metacognitive layer to AI agents to eliminate hallucinations and task drift.
Novel Character Profile Builder
A specialized AI tool for fiction writers to build, manage, and validate structured character profiles in a bilingual CN/EN format.
Tencent Finance CLI
A powerful Python command-line interface for fetching real-time stock quotes and market comparisons via the Tencent Finance API.
RAGTOP Agent
An advanced RAG assistant designed to automate knowledge base management and perform deep, agentic research via the RAGTOP backend.
Ragtop Planner
A sophisticated orchestration skill that automates the generation of influencer marketing plans by retrieving rules, cases, and pricing from RAGTOP knowledge bases.
Featured*
