--- title: "Create Responses" method: POST path: "/v1/responses" tags: ["Responses"] --- # Create Responses `POST /v1/responses` Generate a unified response block from various input configurations. ## Headers - `x-api-key` string ## Request body - CreateResponseBody - `model` string, nullable - `input` union - ItemParam[] - union - ItemReferenceParam - `type` 'item_reference', required — The item type. Always `item_reference`. - `id` string, required — The ID of the item to reference. - ReasoningItemParam - `id` string, nullable - `type` 'reasoning', required — The item type. Always `reasoning`. - `summary` ReasoningSummaryContentParam[], required — Reasoning summary content associated with this item. - `type` 'summary_text', required - `text` string, required — The reasoning summary text. - `content` unknown - `encrypted_content` string, nullable - CompactionSummaryItemParam - `id` string, nullable - `type` 'compaction', required — The type of the item. Always `compaction`. - `encrypted_content` string, required — The encrypted content of the compaction summary. - UserMessageItemParam - `id` string, nullable - `type` 'message' - `role` 'user', required - `content` union, required — The message content, as an array of content parts. - Content[] - … - string - `status` string, nullable - SystemMessageItemParam - `id` string, nullable - `type` 'message' - `role` 'system', required - `content` union, required — The message content, as an array of content parts. - Content1[] - … - string - `status` string, nullable - DeveloperMessageItemParam - `id` string, nullable - `type` 'message' - `role` 'developer', required - `content` union, required — The message content, as an array of content parts. - Content1[] - … - string - `status` string, nullable - AssistantMessageItemParam - `id` string, nullable - `type` 'message' - `role` 'assistant', required - `content` union, required — The message content, as an array of content parts. - Content3[] - … - string - `phase` 'commentary' | 'final_answer' - `status` string, nullable - FunctionCallItemParam - `id` string, nullable - `call_id` string, required — The unique ID of the function tool call generated by the model. - `type` 'function_call', required — The item type. Always `function_call`. - `name` string, required — The name of the function to call. - `arguments` string, required — The function arguments as a JSON string. - `status` 'in_progress' | 'completed' | 'incomplete' - FunctionCallOutputItemParam - `id` string, nullable - `call_id` string, required — The unique ID of the function tool call generated by the model. - `type` 'function_call_output', required — The type of the function tool call output. Always `function_call_output`. - `output` union, required — Text, image, or file output of the function tool call. - string - Output[] - … - `status` 'in_progress' | 'completed' | 'incomplete' - string - `previous_response_id` string, nullable - `include` IncludeEnum[], nullable - `tools` ResponsesToolParam[], nullable - union - FunctionToolParam - `name` string, required - `description` string, nullable - `parameters` object, nullable - `strict` boolean, nullable - `type` 'function', required - object - `tool_choice` union - ToolChoice2 - 'none' | 'auto' | 'required' - ToolChoice4 - `type` 'allowed_tools', required - `tools` SpecificToolChoiceParam[], required — The list of tools that are permitted for this request. - `type` 'function', required - `name` string, required — The name of the function tool to call. - `mode` 'none' | 'auto' | 'required' - `text` TextParam - `format` union - SchemasResponsesv2TextResponseFormat - `type` 'text', required - JsonSchemaResponseFormatParam - `type` 'json_schema' - `description` string, nullable — A description of what the response format is for, used by the model to determine how to respond in the format. - `name` string, nullable — The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. - `schema` object, nullable — The schema for the response format, described as a JSON Schema object. - `strict` boolean, nullable - `verbosity` 'low' | 'medium' | 'high' - `temperature` number, nullable - `top_p` number, nullable - `presence_penalty` number, nullable - `frequency_penalty` number, nullable - `parallel_tool_calls` boolean, nullable - `stream` boolean, nullable — Whether to stream response events as server-sent events. - `background` boolean, nullable — Whether to run the request in the background and return immediately. - `max_output_tokens` integer, nullable - `max_tool_calls` integer, nullable - `reasoning` ReasoningParam - `effort` 'none' | 'low' | 'medium' | 'high' | 'xhigh' - `summary` 'concise' | 'detailed' | 'auto' - `prompt_cache_key` string, nullable - `truncation` 'auto' | 'disabled' - `instructions` string, nullable - `store` boolean, nullable — Whether to store the response so it can be retrieved later. - `service_tier` 'auto' | 'default' | 'flex' | 'priority' - `top_logprobs` integer, nullable ## Response `200` Successful Response - ResponseResource - `id` string, required — The unique ID of the response that was created. - `object` 'response', required - `created_at` integer, required — The Unix timestamp (in seconds) for when the response was created. - `completed_at` integer, nullable, required - `status` string, required — The status that was set for the response. - `incomplete_details` IncompleteDetails, required - `reason` string, required — The reason the response could not be completed. - `model` string, required — The model that generated this response. - `previous_response_id` string, nullable, required - `instructions` string, nullable, required - `output` ItemField[], required — The output items that were generated by the model. - union - MessageOutput - `type` 'message', required — The type of the message. Always set to `message`. - `id` string, required — The unique ID of the message. - `status` 'in_progress' | 'completed' | 'incomplete', required - `role` 'user' | 'assistant' | 'system' | 'developer', required - `content` Content4[], required — The content of the message - union - InputTextContent - … - OutputTextContent - … - TextContentOutput - … - SummaryTextContent - … - ReasoningTextContent - … - RefusalContent - … - InputImageContent - … - InputFileContent - … - InputVideoContent - … - `phase` 'commentary' | 'final_answer' - FunctionCall - `type` 'function_call', required — The type of the item. Always `function_call`. - `id` string, required — The unique ID of the function call item. - `call_id` string, required — The unique ID of the function tool call that was generated. - `name` string, required — The name of the function that was called. - `arguments` string, required — The arguments JSON string that was generated. - `status` 'in_progress' | 'completed' | 'incomplete', required - FunctionCallOutput - `type` 'function_call_output', required — The type of the function tool call output. Always `function_call_output`. - `id` string, required — The unique ID of the function tool call output. Populated when this item is returned via API. - `call_id` string, required — The unique ID of the function tool call generated by the model. - `output` union, required - string - Output1[] - union - … - `status` 'in_progress' | 'completed' | 'incomplete', required - ReasoningBody - `type` 'reasoning', required — The type of the item. Always `reasoning`. - `id` string, required — The unique ID of the reasoning item. - `content` Content5[], nullable — The reasoning content that was generated. - union - InputTextContent - … - OutputTextContent - … - TextContentOutput - … - SummaryTextContent - … - ReasoningTextContent - … - RefusalContent - … - InputImageContent - … - InputFileContent - … - `summary` Summary[], required — The reasoning summary content that was generated. - union - InputTextContent - … - OutputTextContent - … - TextContentOutput - … - SummaryTextContent - … - ReasoningTextContent - … - RefusalContent - … - InputImageContent - … - InputFileContent - … - `encrypted_content` string, nullable — The encrypted reasoning content that was generated. - CompactionBody - `type` 'compaction', required — The type of the item. Always `compaction`. - `id` string, required — The unique ID of the compaction item. - `encrypted_content` string, required — The encrypted content that was produced by compaction. - `created_by` string, nullable — The identifier of the actor that created the item. - `error` Error1, required - `code` string, required — A machine-readable error code that was returned. - `message` string, required — A human-readable description of the error that was returned. - `tools` ToolOutput[], required — The tools that were available to the model during response generation. - `type` 'function', required - `name` string, required — The name of the function to call. - `description` string, nullable, required - `parameters` object, nullable, required - `strict` boolean, nullable, required - `tool_choice` union, required - FunctionToolChoice - `type` 'function', required - `name` string, nullable - 'none' | 'auto' | 'required' - AllowedToolChoice - `type` 'allowed_tools', required - `tools` FunctionToolChoice[], required - `type` 'function', required - `name` string, nullable - `mode` 'none' | 'auto' | 'required', required - `truncation` 'auto' | 'disabled', required - `parallel_tool_calls` boolean, required — Whether the model was allowed to call multiple tools in parallel. - `text` TextField, required - `format` union, required - TextResponseFormatOutput - `type` 'text', required - JsonObjectResponseFormatOutput - `type` 'json_object', required - JsonSchemaResponseFormatOutput - `type` 'json_schema', required - `name` string, required - `description` string, nullable, required - `schema` unknown, required - `strict` boolean, required - `verbosity` 'low' | 'medium' | 'high' - `top_p` number, required — The nucleus sampling parameter that was used for this response. - `presence_penalty` number, required — The presence penalty that was used to penalize new tokens based on whether they appear in the text so far. - `frequency_penalty` number, required — The frequency penalty that was used to penalize new tokens based on their frequency in the text so far. - `top_logprobs` integer, required — The number of most likely tokens that were returned at each position, along with their log probabilities. - `temperature` number, required — The sampling temperature that was used for this response. - `reasoning` Reasoning, required - `effort` 'none' | 'low' | 'medium' | 'high' | 'xhigh', required - `summary` 'concise' | 'detailed' | 'auto', required - `usage` SchemasResponsesv2Usage, required - `input_tokens` integer, required — The number of input tokens that were used to generate the response. - `output_tokens` integer, required — The number of output tokens that were generated by the model. - `total_tokens` integer, required — The total number of tokens that were used. - `input_tokens_details` InputTokensDetails, required - `cached_tokens` integer, required — The number of input tokens that were served from cache. - `output_tokens_details` OutputTokensDetails, required - `reasoning_tokens` integer, required — The number of output tokens that were attributed to reasoning. - `max_output_tokens` integer, nullable, required - `max_tool_calls` integer, nullable, required - `store` boolean, required — Whether this response was stored so it can be retrieved later. - `background` boolean, required — Whether this request was run in the background. - `service_tier` string, required — The service tier that was used for this response. - `prompt_cache_key` string, nullable, required ## Other responses - `400` — Bad Request - Invalid query parameters or body format. - `401` — Unauthorized - Missing or invalid API key. - `403` — Forbidden - Key does not have permission or is disabled. - `422` — Unprocessable Entity - Request body validation failed. - `429` — Too Many Requests - Rate limit exceeded. - `500` — Internal Server Error - Internal error occurred. - `502` — Bad Gateway - Provider error occurred. --- [API](https://skmtc.dev/routeway/apis/routeway-api.md) · [All operations](https://skmtc.dev/routeway/apis/routeway-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/routeway/routeway-api/revisions/b6f03282a96b/schema)