| id |
string |
Unique identifier for the response, prefixed with 'resp_' |
| object |
string |
The object type, which is always 'response' |
| created_at |
integer |
Unix timestamp (in seconds) of when the response was created |
| model |
string |
The model used to generate the response |
| status |
string |
The status of the response generation |
| output |
array |
An array of content items generated by the model, including messages, function calls, tool invocations, and reasoning items |
| usage |
object |
Token usage statistics for the response |
| error |
object |
An error object if the response generation failed |
| incomplete_details |
object |
Details about why the response is incomplete |
| instructions |
string |
The system or developer instructions provided for the response |
| metadata |
object |
Set of key-value pairs attached to the response for storing additional information |
| temperature |
number |
The sampling temperature used for generation |
| top_p |
number |
The nucleus sampling parameter used for generation |
| max_output_tokens |
integer |
The maximum number of output tokens configured for the response |
| previous_response_id |
string |
The ID of the previous response in a multi-turn conversation |
| reasoning |
object |
The reasoning configuration used for o-series models |
| text |
object |
The text format configuration used for the response |
| tools |
array |
The tools available during response generation |
| truncation |
string |
The truncation strategy used for the model context |
| user |
string |
The end-user identifier |
| service_tier |
string |
The service tier used for processing the request |