> For clean Markdown of any page, append `.md` to the page URL.
> Documentation index: https://you.com/docs/llms.txt (section indexes: append `/llms.txt` to any section URL).
> Search these docs: Docs MCP at https://you.com/docs/_mcp/server (`searchDocs`, no API key).
> Call live You.com APIs: Product MCP at https://api.you.com/mcp (keyless `?profile=free` exposes `you-search` and `you-discover`. Research and finance use `/mcp/research`, `/mcp/finance`, or `?tools=` on `/mcp`). To pick an API or integration path, call `you-discover` on that server instead of guessing.
> OpenAPI: https://you.com/docs/openapi.json—auth header `X-API-Key`, env `YDC_API_KEY`.

# Inference Router Overview

## What Is the Inference Router?

The Inference Router serves language models from one base URL, `https://api.you.com`, with one You.com API key. It exposes an OpenAI-compatible endpoint at `/v1/chat/completions` and an Anthropic-compatible endpoint at `/v1/messages`, so existing OpenAI and Anthropic SDKs work by changing the base URL and key. The [Quickstart](/docs/guides/inference-router/quickstart) sends a first request.

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 the sources it used. See [Web Tools](/docs/guides/inference-router/web-tools).

---

## Endpoints

For a complete list of endpoints, see the [API reference](/docs/api-reference/inference-router/create-chat-completion).

| Endpoint                                       | Format                         | API reference                                                                       |
| ---------------------------------------------- | ------------------------------ | ----------------------------------------------------------------------------------- |
| `POST https://api.you.com/v1/chat/completions` | OpenAI-compatible              | [/v1/chat/completions](/docs/api-reference/inference-router/create-chat-completion) |
| `POST https://api.you.com/v1/messages`         | Anthropic-compatible           | [/v1/messages](/docs/api-reference/inference-router/create-message)                 |
| `GET https://api.you.com/v1/models`            | OpenAI or Anthropic model list | [/v1/models](/docs/api-reference/inference-router/list-models)                      |

---

## Next Steps

* [Quickstart](/docs/guides/inference-router/quickstart): send your first request.
* [Tool Calling](/docs/guides/inference-router/tool-calling): call your own functions, alone or with web tools.
* [Reasoning](/docs/guides/inference-router/reasoning): reasoning tokens and output limits.
* [Web Tools](/docs/guides/inference-router/web-tools): search the web and fetch pages for the model.
* [API reference](/docs/api-reference/inference-router/create-chat-completion): every field of every endpoint.