Inference Router for OpenAI- and Anthropic-Compatible Requests
The Inference Router serves language models from one base URL, https://api.you.com, with one You.com API key. POST /v1/chat/completions accepts the OpenAI Chat Completions format and POST /v1/messages accepts Anthropic Messages, so an existing OpenAI or Anthropic SDK works after changing its base URL and key.
Declare a web_search or web_extract tool and the router runs You.com searches and page fetches for the model, then returns the answer with every source it used in web_results. Function tools work alone or alongside the web tools, both endpoints stream, and reasoning models expose reasoning_content while reasoning tokens count against the output limit.