Evals

List evaluation runs

GET /openai/v1/evals/{eval_id}/runs

Returns a page of runs for the specified evaluation. Results can be filtered by run status and paged by using after and limit.

Paramètres de chemin d’accès

eval_id string obligatoire

The identifier of the evaluation whose runs to list.

after string

The identifier of the last item from the previous page. Use this value to retrieve the next page.

limit integer

The maximum number of items to return. The default is 20.

order enum

The order in which to return items by timestamp. Use asc for ascending order or desc for descending order. The default is asc.

ascdesc

status enum

Filter evaluation runs by status. Accepted values are queued, in_progress, completed, canceled, and failed.

queuedin_progresscompletedcanceledfailed

The request has succeeded.

Content-Type: application/json

data EvalRun[] obligatoire

The requested list of items.

first_id string

The first ID represented in this list.

last_id string

The last ID represented in this list.

has_more boolean obligatoire

A value indicating whether there are additional values available not captured in this list.

GET /openai/v1/evals/{eval_id}/runs HTTP/1.1

Status: 200
Content-Type: application/json

Status: 4XX
Content-Type: application/json

Status: 5XX
Content-Type: application/json