Product

One key, every model: why we built a multi-model gateway

2026-06-18· 4 min read

Juggling a separate SDK, key, and bill for every provider doesn't scale. Here's the case for a single unified surface.

Most teams start with one model. Then a designer wants image generation, a PM wants voiceover, and suddenly you're maintaining four SDKs, four keys, and four invoices. you.bot collapses that into one API and one credit balance.

The cost of fragmentation

Each provider has its own auth, request shape, and polling model.
Switching a model means a code change, not a config change.
Spend is scattered across invoices with no single view.

One surface, swappable models

Submit a task with a model id, poll for the result, and read one balance. Swapping providers becomes a one-line change — the request shape stays the same.

await fetch("/api/v1/generate", {
  method: "POST",
  body: JSON.stringify({ model: "veo-3-1", input: { prompt } }),
});