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, depending on upstream and compatibility support. |
Request Example
bash
curl https://llmapi.site/v1/responses \
-H 'Authorization: Bearer YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "gpt-5.1",
"input": "Write a concise release note.",
"stream": false
}'Response Example
json
{
"id": "resp_123",
"object": "response",
"status": "completed",
"model": "gpt-5.1",
"output": []
}WebSocket Compatibility Entry
GET /v1/responses is an OpenAI Responses WebSocket compatibility entry for specific clients.
Compatible Paths
/responses without /v1 and the Codex-specific /backend-api/codex/responses are also registered. See Aliases.