---
title: "Create a model response (Responses API)"
method: POST
path: "/v1/responses"
tags: ["responses"]
---

# Create a model response (Responses API)

`POST /v1/responses`

## Request body

- CoreResponsesRequest
  - `context_management` unknown
  - `conversation` union — Conversation accepts either a conversation ID string or an object with id.
    - string
    - CoreResponsesConversationRef
      - `id` string, required
  - `include` string[]
  - `input` union — string or []ResponsesInputElement — see docs for array form
    - string
    - CoreResponsesInputElement[]
      - `arguments` string
      - `call_id` string — Function call fields (type="function_call")
      - `content` union — Can be string or []ContentPart
        - string
        - CoreContentPart[]
          - `image_url` CoreImageURLContent
            - `detail` string
            - `media_type` string
            - `url` string
          - `input_audio` CoreInputAudioContent
            - `data` string
            - `format` string
          - `text` string
          - `type` string
      - `name` string
      - `output` string — Function call output fields (type="function_call_output") - CallID shared above
      - `role` string — Message fields (type="" or "message")
      - `status` string
      - `type` string — "message", "function_call", "function_call_output"
  - `instructions` string
  - `max_output_tokens` integer
  - `metadata` object
  - `model` string
  - `parallel_tool_calls` boolean
  - `previous_response_id` string
  - `prompt` unknown
  - `prompt_cache_retention` string
  - `provider` string — Gateway routing hint; stripped before upstream execution.
  - `reasoning` CoreReasoning
    - `effort` string — Effort controls how much reasoning effort the model should use. Valid values are "low", "medium", "high", "xhigh", and "max". "xhigh" and "max" are supported by newer models such as Claude Opus 4.8; providers downgrade unsupported levels to their nearest equivalent.
  - `safety_identifier` string
  - `service_tier` string
  - `store` boolean
  - `stream` boolean
  - `stream_options` CoreStreamOptions
    - `include_usage` boolean — IncludeUsage requests token usage information in streaming responses. When true, the final streaming chunk will include usage statistics.
  - `temperature` number
  - `text` unknown
  - `tool_choice` unknown
  - `tools` object[]
  - `top_logprobs` integer
  - `top_p` number
  - `truncation` string
  - `user` string

## Response `200`

JSON response or SSE stream when stream=true

- CoreResponsesResponse
  - `created_at` integer
  - `error` CoreResponsesError
    - `code` string
    - `message` string
  - `id` string
  - `model` string
  - `object` string — "response"
  - `output` CoreResponsesOutputItem[]
    - `arguments` string
    - `call_id` string
    - `content` CoreResponsesContentItem[]
      - `annotations` object[] — Providers can return structured annotation objects here (for example citations from native tools), so keep the payload shape liberal.
      - `image_url` CoreImageURLContent
        - `detail` string
        - `media_type` string
        - `url` string
      - `input_audio` CoreInputAudioContent
        - `data` string
        - `format` string
      - `text` string
      - `type` string — "output_text", "input_image", "input_audio", etc.
    - `id` string
    - `name` string
    - `role` string
    - `status` string
    - `type` string — "message", "function_call", etc.
  - `provider` string
  - `status` string — "completed", "failed", "in_progress"
  - `usage` CoreResponsesUsage
    - `completion_tokens_details` CoreCompletionTokensDetails
      - `accepted_prediction_tokens` integer
      - `audio_tokens` integer
      - `reasoning_tokens` integer
      - `rejected_prediction_tokens` integer
    - `input_tokens` integer
    - `output_tokens` integer
    - `prompt_tokens_details` CorePromptTokensDetails
      - `audio_tokens` integer
      - `cached_tokens` integer
      - `image_tokens` integer
      - `text_tokens` integer
    - `raw_usage` object
    - `total_tokens` integer

## Other responses

- `400` — Bad Request
- `401` — Unauthorized
- `429` — Too Many Requests
- `502` — Bad Gateway

---

[API](https://skmtc.net/enterpilot/apis/gomodel-api.md) · [All operations](https://skmtc.net/enterpilot/apis/gomodel-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/enterpilot/gomodel-api/revisions/4c27ea61fcfe/schema)