---
title: "Cygnal Responses"
method: POST
path: "/cygnal/responses"
---

# Cygnal Responses

`POST /cygnal/responses`

Process and monitor OpenAI-compatible response requests.

This endpoint processes completion requests with monitoring capabilities,
similar to the chat completions endpoint.

Docs: [Guide](https://docs.grayswan.ai/cygnal/creating-responses) |
[API Reference](https://docs.grayswan.ai/api-reference/cygnal/responses)

## Request body

- CreateResponseRequest
  - `background` boolean
  - `context_management` object[], nullable
  - `conversation` union
    - string
    - Conversation
      - `id` string, required
  - `include` unknown[], nullable
    - unknown
  - `input` union
    - string
    - unknown[]
      - unknown
  - `instructions` string, nullable
  - `max_output_tokens` integer, nullable
  - `max_tool_calls` integer, nullable
  - `metadata` object, nullable
  - `model` string, nullable
  - `moderation` object, nullable
  - `parallel_tool_calls` boolean, nullable
  - `previous_response_id` string, nullable
  - `prompt` Prompt
    - `id` string, required
    - `variables` object, nullable
    - `version` string, nullable
  - `prompt_cache_key` string, nullable
  - `prompt_cache_options` object, nullable
  - `prompt_cache_retention` 'in_memory' | 'in-memory' | '24h', nullable
  - `reasoning` object, nullable
  - `safety_identifier` string, nullable
  - `service_tier` 'auto' | 'default' | 'flex' | 'scale' | 'priority', nullable
  - `store` boolean, nullable
  - `stream` boolean, nullable
  - `stream_options` unknown
  - `temperature` number, nullable
  - `text` unknown
  - `tool_choice` union
    - 'none' | 'auto' | 'required'
    - object
  - `tools` unknown[], nullable
    - unknown
  - `top_logprobs` integer, nullable
  - `top_p` number, nullable
  - `truncation` 'auto' | 'disabled', nullable
  - `user` string, nullable
  - `monitor_details` boolean, nullable
  - `policy_id` string, nullable

## Response `200`

Successful Response

- ResponsesEndpointResponse
  - `id` string, nullable
  - `object` string, nullable
  - `model` string, nullable
  - `output` JSONValueOutput[], nullable
    - union
      - union
        - string
        - integer
        - number
        - boolean
      - JSONValueOutput[]
      - object
  - `choices` ResponseChoice[], nullable
    - `index` integer, nullable
    - `finish_reason` string, nullable
    - `message` ResponseMessage
      - `role` string, nullable
      - `content` string, nullable
  - `usage` ResponseUsage
    - `prompt_tokens` integer, nullable
    - `completion_tokens` integer, nullable
    - `total_tokens` integer, nullable
    - `input_tokens` integer, nullable
    - `output_tokens` integer, nullable
  - `error` ResponseError
    - `message` string, nullable
    - `type` string, nullable
    - `code` string, nullable
    - `param` string, nullable

## Other responses

- `400` — Bad Request
- `401` — Unauthorized
- `422` — Unprocessable Content
- `500` — Internal Server Error
- `502` — Bad Gateway

---

[API](https://skmtc.net/grayswan/apis/gray-swan-ai-api.md) · [All operations](https://skmtc.net/grayswan/apis/gray-swan-ai-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/grayswan/gray-swan-ai-api/revisions/6ef1ea32ff13/schema)