Sample - OpenAI API
GET/evals/{eval_id}/runs/{run_id}/output_items

List evaluation run output items

Lists output items produced by a specified evaluation run. Use after to continue from a previous page, limit to control the number of items, and status or order to filter and sort the results.

  • RetriesRetries up to 2×, 500ms backoff, 30s timeout.

6 parameters
eval_idstringrequired
The unique identifier of the evaluation containing the run.
run_idstringrequired
The unique identifier of the evaluation run whose output items to retrieve.
afterstringoptional
The identifier of the last output item from the previous request, used to continue pagination.
limitintegeroptional
The number of output items to retrieve. Defaults to 20 when omitted.
Default:20
statusstringoptional
Filter output items by result status: `fail` or `pass`.
Allowed:failpass
orderstringoptional
Sort output items by timestamp: `asc` or `desc`. Defaults to `asc` when omitted.
Allowed:ascdescDefault:asc

2 status codes
200Returns a list object containing evaluation run output items, the first and last output item identifiers, and a `has_more` flag indicating whether additional items are available.
objectstringrequired
The type of this object. It is always set to "list".
Allowed:listDefault:list
dataarray<EvalRunOutputItem>required
An array of eval run output item objects.
first_idstringrequired
The identifier of the first eval run output item in the data array.
last_idstringrequired
The identifier of the last eval run output item in the data array.
has_morebooleanrequired
Indicates whether there are more eval run output items available.
429Returned when the request is rejected because the rate limit has been exceeded.
errorobjectrequired

Error handling

eval_id must identify the evaluation and run_id must identify the run whose output items you want to list. status must be fail or pass, and order must be asc or desc. A 429 is returned when the request is rejected because the rate limit has been exceeded.