POST /v1/responses

OpenAI Responses compatible — a shim that converts the request into a chat request internally. Anything like previous_response_id is stateful storage, which is not supported.

Body

modelstringYes: Model ID
inputstring | arrayYes: A string, or an array of message / function_call / function_call_output items
instructionsstringNo: system instructions
max_output_tokensintegerNo: Maximum output tokens
temperaturenumberNo: 0–2
top_pnumberNo: 0–1
streambooleanNo: Stream events token by token
backgroundbooleanNo: If true, submits as an async job and returns queued immediately
tools / tool_choicearray / string|objectNo: Same format as chat
reasoning_effortstringNo: none / low / medium / high
userstringNo: End-user identifier
everyaisobjectNo: Gateway caching options

Model-specific options

The model restrictions in GET /v1/models capabilities/limits and Chat options also apply here. Unsupported options, values, and combinations return 400. Omit temperature and top_p when capabilities.sampling: false.

reasoning_effort: "none" is preserved as an explicit request to disable reasoning. It is not omitted or changed to low; models that cannot disable reasoning, including Gemini 3, return 400. Check limits.reasoning_efforts for supported levels.

Web search is exclusive to Chat; Responses tools supports function tools only. response_format and parallel_tool_calls are unsupported by this shim (explicit values return 400). Use Chat Completions for those options.

GET /v1/responses/{id}

Poll the status of a job submitted with background: true.

json

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1709884800,
  "model": "everyais/claude-opus-5",
  "status": "queued",
  "output": [],
  "error": null,
  "incomplete_details": null,
  "usage": null
}

status transitions queued → in_progress → completed / incomplete / failed / cancelled. Once it completes, the full stored Response body is returned.

Returns 404 if the job does not exist, has expired, or belongs to another key or user.