Skip to content
Checking statusStatus

How routing works

How evolved.to reaches OpenAI and Anthropic, routes simple prompts to lighter models and scales effort with your task.

What evolved.to is

evolved.to is an independent API gateway. It is not ChatGPT or Claude, and it is not an official product of OpenAI or Anthropic. It gives you one key for the Claude, ChatGPT and Gemini model families and handles the connection to the providers for you. Our prices are possible because of how that connection is engineered, which this page explains.

The proxy layer

Every request goes through our proxy infrastructure and on to OpenAI's, Anthropic's and Google's servers, and the response comes back in the same protocol you called. Requests from all customers share that infrastructure, which lets us use provider capacity far more efficiently than a single account could, and pass the difference on in our credit packs.

Smart routing

Not every message needs a frontier model. In the dashboard chat, smart routing lets a short, simple follow-up, such as a thank-you, a yes or a quick question, be answered by a lighter, faster model, so your credit lasts longer. Anything substantial, such as code, files, long messages or real reasoning, stays on the model you picked.

  • The first message of every chat always goes to the model you picked.
  • A reply from the lighter model is marked Auto in the chat, rather than with that model's name. Every other reply shows the model you picked.
  • It is on by default. Turn it off any time in the chat's menu (Smart routing), and every message goes to the model you picked.
  • Requests to our API from your own tools, such as Claude Code, Cursor or the SDKs, are always served by the model you name.
In the dashboard chatYou pickedAnswered by
Your first message in a chatclaude-opus-5.5claude-opus-5.5
Thanks, that works!claude-opus-5.5Auto
Add tests for the orders APIclaude-opus-5.5claude-opus-5.5
Any message, with smart routing offclaude-opus-5.5claude-opus-5.5

Chat history and effort

Two more settings in the chat's menu decide how much credit a message uses. With Read chat history on (the default), the model reads the whole chat so far. Turn it off and only your latest message is sent: the model does not see earlier messages, and long chats cost far less.

Effort sets how hard the model thinks before it answers: Low is quickest and uses the least credit, High thinks deepest and uses the most. Medium is the default.

Billing and transparency

  • Each request uses credit for the model that served it: a reply marked Auto uses the lighter model's.
  • Your Usage page shows what every request used, and how much credit is left, updated every few minutes.
  • Rates for every model are public on the Models page, and the full terms are in our Terms of Service.