GET
/
evals
/
{eval_id}
/
runs
/
{run_id}
/
output_items
Get eval run output items
curl --request GET \
  --url https://api.openai.com/v1/evals/{eval_id}/runs/{run_id}/output_items \
  --header 'Authorization: Bearer <token>'
{
  "object": "list",
  "data": [
    {
      "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
      }
    }
  ],
  "first_id": "<string>",
  "last_id": "<string>",
  "has_more": true
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

​
eval_id
string
required

The ID of the evaluation to retrieve runs for.

​
run_id
string
required

The ID of the run to retrieve output items for.

Query Parameters

​
after
string

Identifier for the last output item from the previous pagination request.

​
limit
integer
default:20

Number of output items to retrieve.

​
status
enum<string>

Filter output items by status. Use failed to filter by failed output items or pass to filter by passed output items.

Available options:
fail,
pass
​
order
enum<string>
default:asc

Sort order for output items by timestamp. Use asc for ascending order or desc for descending order. Defaults to asc.

Available options:
asc,
desc

Response

200 - application/json

A list of output items for the evaluation run

An object representing a list of output items for an evaluation run.

​
object
enum<string>
default:list
required

The type of this object. It is always set to "list".

Available options:
list
​
data
EvalRunOutputItem · object[]
required

An array of eval run output item objects.

​
first_id
string
required

The identifier of the first eval run output item in the data array.

​
last_id
string
required

The identifier of the last eval run output item in the data array.

​
has_more
boolean
required

Indicates whether there are more eval run output items available.