API ReferenceResponses

Create a response (native proxy)

Native pass-through proxy to upstream /v1/responses. Request and response bodies are forwarded as-is. Streaming uses SSE and ends with [DONE]. Requires Authorization: Bearer $ROUTIFY_API_KEY.

Authentication

AuthorizationBearer

Bearer authentication header of the form Authorization: Bearer $ROUTIFY_API_KEY.

Request

This endpoint expects an object.
modelstringOptional

Model ID used to generate the response. Use GET /v1/models to list all available models.

inputstring or list of objectsOptional
Text, image, or file inputs to the model, used to generate a response. Can be a string or an array of input items.
streambooleanOptionalDefaults to false

If set to true, the response is streamed using server-sent events. The stream ends with a response.completed event.

instructionsstringOptional

A system (or developer) message inserted into the model’s context.

previous_response_idstringOptional

The unique ID of the previous response. Use this to create multi-turn conversations. Cannot be used together with conversation.

toolslist of objectsOptional

An array of tools the model may call (e.g. web_search_preview, file_search, function, code_interpreter).

tool_choiceanyOptional

Controls which tool is called. Can be auto, none, required, or an object specifying a particular tool.

reasoningobjectOptional

Configuration for reasoning models. Supports effort (low/medium/high/xhigh) and summary (auto/concise/detail).

max_output_tokensintegerOptional
An upper bound for the number of tokens that can be generated in the response, including reasoning tokens.

Response

Successful response (JSON or SSE stream)

Errors