> 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`. # Create Message POST https://api.you.com/v1/messages Content-Type: application/json Anthropic-compatible Messages. Send a `model` from `GET /v1/models`, a `max_tokens` limit, and a list of `messages`. Declaring Anthropic's `web_search_*` server tool makes the router run You.com web searches and return `server_tool_use` and `web_search_tool_result` blocks. Reference: https://you.com/docs/api-reference/inference-router/create-message ## Authentication - `Authorization` header (bearer token, required) — Your You.com API key, sent as `Authorization: Bearer `. Get a key in the ["Get your API key" section of the documentation](https://you.com/docs/quickstart#get-your-api-key). ## Request ### Headers - `x-request-id` (string, optional) — A client-chosen request ID for tracing. The router generates one when the header is absent or invalid, and returns it in the response. - `x-session-id` (string, optional) — A conversation identifier of up to 256 characters. Requests that share a session ID are kept together where possible. - `anthropic-version` (string, optional) — The Anthropic API version, such as `2023-06-01`. Sending this header selects the Anthropic response format. ### Body (application/json) This endpoint expects a MessageRequest. - `model` (string, required) — A model ID from `GET /v1/models`. - `max_tokens` (integer, required) — Maximum tokens to generate. Per-model limits are published as `max_tokens` in `GET /v1/models`. - `messages` (list of MessageRequestMessagesItems, required) — The conversation so far, in Anthropic Messages format. - `system` (MessageRequestSystem, optional) — A system prompt, as a string or an array of text blocks. - `stream` (boolean, optional) — Stream the response as server-sent events. - `temperature` (double, optional) — Sampling temperature. When omitted, the router applies the model vendor's reference value, where one is configured. - `top_p` (double, optional) — Nucleus sampling probability. When omitted, the router applies the model vendor's reference value, where one is configured. - `top_k` (integer, optional) — Sample only from the top K tokens. - `stop_sequences` (list of string, optional) — Sequences where the model stops generating. - `metadata` (map from string to any, optional) - `thinking` (map from string to any, optional) — Extended thinking configuration. - `output_config` (map from string to any, optional) — Output configuration, such as effort and a JSON schema format. - `tool_choice` (map from string to any, optional) — How the model uses tools. - `tools` (list of MessageRequestToolsItems, optional) — Tools the model may call. Declare one Anthropic `web_search_*` server tool for router-run web search. ## Response ### 200 A message, or a stream of Anthropic server-sent events when `stream` is `true`. - `id` (string, optional) - `type` (enum, optional) - Allowed values: `message` - `role` (enum, optional) - Allowed values: `assistant` - `model` (string, optional) - `content` (list of map from string to any, optional) — Content blocks. A web search request adds `server_tool_use` and `web_search_tool_result` blocks for each search the router ran. - `stop_reason` (string, optional, nullable) - `stop_sequence` (string, optional, nullable) - `usage` (MessageResponseUsage, optional) ## Errors ### 400 Bad Request Error An error in Anthropic format. - `type` (enum, required) - Allowed values: `error` - `error` (AnthropicErrorResponseError, required) ### 401 Unauthorized Error An error in Anthropic format. - `type` (enum, required) - Allowed values: `error` - `error` (AnthropicErrorResponseError, required) ### 403 Forbidden Error An error in Anthropic format. - `type` (enum, required) - Allowed values: `error` - `error` (AnthropicErrorResponseError, required) ### 429 Too Many Requests Error An error in Anthropic format. - `type` (enum, required) - Allowed values: `error` - `error` (AnthropicErrorResponseError, required) ### 503 Service Unavailable Error An error in Anthropic format. - `type` (enum, required) - Allowed values: `error` - `error` (AnthropicErrorResponseError, required) ## Types ### MessageRequestMessagesItems - `role` (enum, required) - Allowed values: `user`, `assistant` - `content` (MessageRequestMessagesItemsContent, required) ### MessageRequestSystem A system prompt, as a string or an array of text blocks. - string - list of map from string to any ### MessageRequestToolsItems - AnthropicTool: AnthropicTool - AnthropicWebSearchTool: AnthropicWebSearchTool ### MessageResponseUsage - `input_tokens` (integer, optional) - `output_tokens` (integer, optional) - `cache_creation_input_tokens` (integer, optional) - `cache_read_input_tokens` (integer, optional) ### AnthropicErrorResponseError - `type` (string, required) — One of `invalid_request_error`, `authentication_error`, `permission_error`, `not_found_error`, `request_too_large`, `rate_limit_error`, or `overloaded_error`. - `message` (string, required) — A description of the error. ### MessageRequestMessagesItemsContent - string - list of map from string to any ### AnthropicTool - `name` (string, required) - `input_schema` (map from string to any, required) - `description` (string, optional) ### AnthropicWebSearchTool Anthropic's versioned web search server tool. The router serves it with You.com search. Only one is allowed per request. - `type` (string, required) — A versioned type such as `web_search_20250305`. - `name` (enum, required) - Allowed values: `web_search` - `max_uses` (integer, optional) — Maximum search rounds. A round can run several searches in parallel, so a request can search more than `max_uses` times. - `blocked_domains` (list of string, optional) — Domains to leave out of results. - `user_location` (AnthropicWebSearchToolUserLocation, optional) — Where the user is. The router uses `country`. ### AnthropicWebSearchToolUserLocation Where the user is. The router uses `country`. - `country` (string, optional) — Two-letter ISO 3166-1 alpha-2 country code. ## Examples **Request** ```json { "model": "string", "max_tokens": 1, "messages": [ { "role": "user", "content": "string" } ] } ``` **Response** ```json { "id": "string", "type": "message", "role": "assistant", "model": "string", "content": [ {} ], "stop_reason": "string", "stop_sequence": "string", "usage": { "input_tokens": 1, "output_tokens": 1, "cache_creation_input_tokens": 1, "cache_read_input_tokens": 1 } } ``` **SDK Code** ```python import requests url = "https://api.you.com/v1/messages" payload = { "model": "string", "max_tokens": 1, "messages": [ { "role": "user", "content": "string" } ] } headers = { "Authorization": "Bearer ", "Content-Type": "application/json" } response = requests.post(url, json=payload, headers=headers) print(response.json()) ``` ```javascript const url = 'https://api.you.com/v1/messages'; const options = { method: 'POST', headers: {Authorization: 'Bearer ', 'Content-Type': 'application/json'}, body: '{"model":"string","max_tokens":1,"messages":[{"role":"user","content":"string"}]}' }; try { const response = await fetch(url, options); const data = await response.json(); console.log(data); } catch (error) { console.error(error); } ``` ```go package main import ( "fmt" "strings" "net/http" "io" ) func main() { url := "https://api.you.com/v1/messages" payload := strings.NewReader("{\n \"model\": \"string\",\n \"max_tokens\": 1,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"string\"\n }\n ]\n}") req, _ := http.NewRequest("POST", url, payload) req.Header.Add("Authorization", "Bearer ") req.Header.Add("Content-Type", "application/json") res, _ := http.DefaultClient.Do(req) defer res.Body.Close() body, _ := io.ReadAll(res.Body) fmt.Println(res) fmt.Println(string(body)) } ``` ```java import com.mashape.unirest.http.HttpResponse; import com.mashape.unirest.http.Unirest; HttpResponse response = Unirest.post("https://api.you.com/v1/messages") .header("Authorization", "Bearer ") .header("Content-Type", "application/json") .body("{\n \"model\": \"string\",\n \"max_tokens\": 1,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"string\"\n }\n ]\n}") .asString(); ``` ```csharp using RestSharp; var client = new RestClient("https://api.you.com/v1/messages"); var request = new RestRequest(Method.POST); request.AddHeader("Authorization", "Bearer "); request.AddHeader("Content-Type", "application/json"); request.AddParameter("application/json", "{\n \"model\": \"string\",\n \"max_tokens\": 1,\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"string\"\n }\n ]\n}", ParameterType.RequestBody); IRestResponse response = client.Execute(request); ``` ```swift import Foundation let headers = [ "Authorization": "Bearer ", "Content-Type": "application/json" ] let parameters = [ "model": "string", "max_tokens": 1, "messages": [ [ "role": "user", "content": "string" ] ] ] as [String : Any] let postData = JSONSerialization.data(withJSONObject: parameters, options: []) let request = NSMutableURLRequest(url: NSURL(string: "https://api.you.com/v1/messages")! as URL, cachePolicy: .useProtocolCachePolicy, timeoutInterval: 10.0) request.httpMethod = "POST" request.allHTTPHeaderFields = headers request.httpBody = postData as Data let session = URLSession.shared let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in if (error != nil) { print(error as Any) } else { let httpResponse = response as? HTTPURLResponse print(httpResponse) } }) dataTask.resume() ```