OpenAI API (unofficial showcase)
GET/evals/{eval_id}/runs/{run_id}/output_items

List output items for an evaluation run

Lists output items for a specific evaluation run, with optional cursor pagination, status filtering, and timestamp ordering. Use after to continue from a previous response and status to view only passing or failing output items.

6 parameters
eval_idstringrequired
The identifier of the evaluation that owns the run.
run_idstringrequired
The identifier of the run whose output items to list.
afterstringoptional
The identifier of the last output item from the previous page; omit it to start from the beginning.
limitintegeroptional
The number of output items to retrieve. Defaults to 20 when omitted.
Default:20
statusstringoptional
Filter output items by status: `fail` or `pass`.
Allowed:failpass
orderstringoptional
Sort order by timestamp: `asc` or `desc`. Defaults to `asc` when omitted.
Allowed:ascdescDefault:asc

4 status codes
200Returns a list of evaluation run output items, with pagination identifiers and a `has_more` flag.
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.
400Returned when the output item list parameters are invalid.
errorobjectrequired
404Returned when the evaluation or evaluation run was not found.
errorobjectrequired
429Returned when the request is rejected because a rate limit was exceeded.
errorobjectrequired

Error handling

A 400 is returned when output item list parameters are invalid. A 404 is returned when the evaluation or run is not found. A 429 is returned when the request exceeds a rate limit. status must be fail or pass, and order must be asc or desc.