curl --request GET \
--url https://api.openai.com/v1/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id} \
--header 'Authorization: Bearer <token>'
{
"object": "eval.run.output_item",
"id": "<string>",
"run_id": "<string>",
"eval_id": "<string>",
"created_at": 123,
"status": "<string>",
"datasource_item_id": 123,
"datasource_item": {},
"results": [
{}
],
"sample": {
"input": [
{
"role": "<string>",
"content": "<string>"
}
],
"output": [
{
"role": "<string>",
"content": "<string>"
}
],
"finish_reason": "<string>",
"model": "<string>",
"usage": {
"total_tokens": 123,
"completion_tokens": 123,
"prompt_tokens": 123,
"cached_tokens": 123
},
"error": {
"code": "<string>",
"message": "<string>"
},
"temperature": 123,
"max_completion_tokens": 123,
"top_p": 123,
"seed": 123
}
}
Get an evaluation run output item by ID.
curl --request GET \
--url https://api.openai.com/v1/evals/{eval_id}/runs/{run_id}/output_items/{output_item_id} \
--header 'Authorization: Bearer <token>'
{
"object": "eval.run.output_item",
"id": "<string>",
"run_id": "<string>",
"eval_id": "<string>",
"created_at": 123,
"status": "<string>",
"datasource_item_id": 123,
"datasource_item": {},
"results": [
{}
],
"sample": {
"input": [
{
"role": "<string>",
"content": "<string>"
}
],
"output": [
{
"role": "<string>",
"content": "<string>"
}
],
"finish_reason": "<string>",
"model": "<string>",
"usage": {
"total_tokens": 123,
"completion_tokens": 123,
"prompt_tokens": 123,
"cached_tokens": 123
},
"error": {
"code": "<string>",
"message": "<string>"
},
"temperature": 123,
"max_completion_tokens": 123,
"top_p": 123,
"seed": 123
}
}
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
The ID of the evaluation to retrieve runs for.
The ID of the run to retrieve.
The ID of the output item to retrieve.
The evaluation run output item
A schema representing an evaluation run output item.
Was this page helpful?