any-api
🥈SilverAI 多模型 API 聚合与协议转换网关：统一调用并互转 OpenAI Chat/Responses、Claude、Gemini 等格式，Provider 仅需实现原生协议。Multi-LLM gateway & protocol transformer: unify and convert OpenAI Chat/Responses, Claude, Gemini, etc.; providers implement native only.
2040Updated 3mo ago
Intermediate30min to implementautomation
Saves ~90 min per use
Quick InstallView Source
git clone https://github.com/nightwhite/any-api.gitWorks with:
Claude
Overview
About This Skill
Any API Gateway is a Cloudflare Workers-based solution that acts as a protocol conversion layer between multiple LLM APIs. It allows developers to configure a single backend provider setup while exposing four different frontend protocol endpoints: OpenAI Chat Completions, OpenAI Responses, Claude Messages, and Google Gemini. The gateway automatically converts requests and responses between these formats, eliminating the need to rewrite code when switching between different LLM providers. This is particularly useful for AI developers and teams who work with multiple LLM services or need to migrate between them without refactoring client code.
How to Use
Install dependencies and configure ANY_API_CONFIG JSON with your upstream providers (e.g., OpenAI Responses, Gemini, Claude). Set WORKER_AUTH_KEY for inbound authentication. Use unified model naming format (provider-id.model-name) across all four protocol endpoints. Deploy to Cloudflare Workers and authenticate requests with Bearer token or x-api-key header.
Use Cases
Route AI requests to different LLM providers without changing client code
Migrate from one LLM API to another with transparent format conversion
Centralize authentication and rate limiting for multiple downstream LLM services
Support multiple frontend protocols to serve diverse client requirements
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/nightwhite/any-apiRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Convert the following response from Claude format to OpenAI Chat format: [CLAUDE_RESPONSE]. Ensure the conversion maintains all relevant metadata and content structure. The output should be ready for integration with an OpenAI-compatible frontend.
Example Output
```json
{
"model": "openai-chat",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The converted response from the original Claude format. This maintains all the semantic meaning and context while adapting to the OpenAI Chat format structure. The conversion process ensures compatibility with systems expecting OpenAI-style responses."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 45,
"completion_tokens": 32,
"total_tokens": 77
}
}
```Apply to these tools
Browse all tools
Gemini
Google's multimodal AI model and assistant
Claude
AI assistant built for thoughtful, nuanced conversation
OpenAI
Pioneering accessible, high-performance AI models
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan