RouterBase Model Gateway

Use routerbase when an application needs an OpenAI compatible gateway for chat, embeddings, image, video, audio, speech, model routing, or fallback behavior.

The goal is not to rewrite the whole AI layer. The goal is to move provider selection behind a clean server side boundary, keep credentials private, and make model choices reversible.

When To Use

Use this skill when the user asks to:

• Migrate an OpenAI compatible client to RouterBase.
• Add RouterBase to a backend API, worker, command line tool, or agent runtime.
• Route requests across multiple model providers through one API surface.
• Choose primary and fallback models for latency, quality, price, or availability.
• Add image, video, audio, speech, or embedding generation through a gateway.
• Debug RouterBase base URLs, model IDs, streaming, JSON output, or media job polling.

Do not use this skill for: