Responses

/v1/responses is the OpenAI Responses API compatible entrypoint for Codex CLI and Responses protocol clients.

Interface

Item	Value
Method	POST
Path	/v1/responses, /v1/responses/*
Content-Type	application/json
Authentication	Authorization: Bearer YOUR_API_KEY

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	Requested model.
input	string or array	Yes	Responses API input.
stream	boolean	No	Whether to stream the response.
instructions	string	No	System-level instructions.
reasoning	object	No	Reasoning configuration, applied by model capability.
tools	array	No	Tool definitions. Availability depends on the selected model and API mode.

Request Example

curl https://api.llmapi.site/v1/responses \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gpt-5.5",
    "input": "Write a concise release note.",
    "stream": false
  }'

Response Example

{
  "id": "resp_123",
  "object": "response",
  "status": "completed",
  "model": "gpt-5.5",
  "output": []
}

Field	Description
id	Response ID returned by the upstream-compatible API.
status	Response lifecycle status, commonly completed for non-streaming requests.
model	Model used for the response.
output	Responses API output items.

When stream is true, the response uses OpenAI Responses-compatible server-sent events.

WebSocket Entry

GET /v1/responses is available for clients that use the Responses WebSocket flow.

Errors

Status	Cause
400	Request body, model, input, tools, or reasoning parameters are invalid.
401	API key is missing or invalid.
403	Balance, quota, group, or subscription check failed.
404	Requested model or Responses-compatible route is unavailable.
429	Rate limit or concurrency limit was reached.
500 / 502 / 503	Gateway or upstream provider failed.