Get a model response

GEThttps:/api.openai.com/v1/responses/{response_id}

Retrieves a model response with the given ID.

Path parameters

response_id
string
Required
The ID of the response to retrieve.

Query parameters

include
array
Additional fields to include in the response. See the include parameter for Response creation above for more information.

Response

The Response object matching the specified ID.

Example request

1curl https://api.openai.com/v1/responses/resp_123 \
2    -H "Content-Type: application/json" \
3    -H "Authorization: Bearer $OPENAI_API_KEY"

Example response

1{
2  "id": "resp_67cb71b351908190a308f3859487620d06981a8637e6bc44",
3  "object": "response",
4  "created_at": 1741386163,
5  "status": "completed",
6  "error": null,
7  "incomplete_details": null,
8  "instructions": null,
9  "max_output_tokens": null,
10  "model": "gpt-4o-2024-08-06",
11  "output": [
12    {
13      "type": "message",
14      "id": "msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44",
15      "status": "completed",
16      "role": "assistant",
17      "content": [
18        {
19          "type": "output_text",
20          "text": "Silent circuits hum,  \nThoughts emerge in data streams—  \nDigital dawn breaks.",
21          "annotations": []
22        }
23      ]
24    }
25  ],
26  "parallel_tool_calls": true,
27  "previous_response_id": null,
28  "reasoning": {
29    "effort": null,
30    "summary": null
31  },
32  "store": true,
33  "temperature": 1.0,
34  "text": {
35    "format": {
36      "type": "text"
37    }
38  },
39  "tool_choice": "auto",
40  "tools": [],
41  "top_p": 1.0,
42  "truncation": "disabled",
43  "usage": {
44    "input_tokens": 32,
45    "input_tokens_details": {
46      "cached_tokens": 0
47    },
48    "output_tokens": 18,
49    "output_tokens_details": {
50      "reasoning_tokens": 0
51    },
52    "total_tokens": 50
53  },
54  "user": null,
55  "metadata": {}
56}

Built with