POST /v1/responses

Part of the API reference; this page is generated from the OpenAPI document that the gateway builds from its own route tables.

Provenance

• Contract version: 1.10.0
• Contract title: acumen gateway API
• Source: acumen:docs/openapi/acumen-v1.openapi.json

Operations

POST /v1/responses

OpenAI Responses door

The OpenAI Responses dialect door. Accepts input as a string or item array and answers a response object or response.* SSE events.

• Operation id: postV1Responses
• Scope: chat
• Exposure: public
• Mutating: no
• Auth: bearerAuth, apiKeyAuth

Request

• Request body (application/json, required): ResponsesRequest: ResponsesRequest (object)

Field	Type	Required	Notes
input		yes	string or item array
instructions	string	no
max_output_tokens	integer	no
model	string	yes
stream	boolean	no
tools	array of object	no

Responses

• 200: Completion, or an SSE stream when the request sets stream:true
  • Streaming: text/event-stream
  • application/json: ResponsesResponse: ResponsesResponse (object)
• 400: schema_invalid
  • application/json: ResponsesError: ResponsesError (object)
• 401: bad_credentials
  • application/json: ResponsesError: ResponsesError (object)
• 402: quota_exhausted (cool-down applied)
  • application/json: ResponsesError: ResponsesError (object)
• 403: auth_scope
  • application/json: ResponsesError: ResponsesError (object)
• 413: payload_too_large
  • application/json: ResponsesError: ResponsesError (object)
• 429: rate_limited (RPM or concurrency)
  • application/json: ResponsesError: ResponsesError (object)
• 502: upstream_error — every attempted seat failed
  • application/json: ResponsesError: ResponsesError (object)
• 503: model_no_eligible_seat
  • application/json: ResponsesError: ResponsesError (object)