Fetch an eval-run dataset export handle (status + NDJSON body).
GET
/v1/evals/{eval_id}/runs/{run_id}/dataset/{dataset_id}
const url = 'https://app.everruns.com/api/v1/evals/example/runs/example/dataset/example';const options = {method: 'GET'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url https://app.everruns.com/api/v1/evals/example/runs/example/dataset/exampleParameters
Section titled “ Parameters ”Path Parameters
Section titled “Path Parameters”eval_id
required
string
Prefixed public identifier
run_id
required
string
Prefixed public identifier
dataset_id
required
string
Prefixed public identifier
Responses
Section titled “ Responses ”Success
Media typeapplication/json
An async dataset-export handle: the durable result of enqueuing a dataset
export from a completed eval run. The body (NDJSON) is only populated on
the GET .../dataset/{dataset_id} detail view once status is completed.
object
body
The produced NDJSON. Only present on the detail view once completed.
string | null
created_at
required
When the export was enqueued.
string format: date-time
error_message
Failure detail when status is failed.
string | null
eval_run_id
required
The eval run this dataset was exported from.
string
id
required
External identifier (evaldataset_<32-hex>).
string
record_count
Number of NDJSON records (surviving cases). Set on completion.
integer | null format: int64
status
required
Export lifecycle status.
string
updated_at
required
When the export was last updated.
string format: date-time
Example
{ "body": "{\"source_key\": \"evalrun_a/evalresult_b\"}", "created_at": "2026-01-15T10:30:00Z", "error_message": "Export failed", "eval_run_id": "evalrun_01933b5a000070008000000000000001", "id": "evaldataset_01933b5a000070008000000000000001", "record_count": 24, "status": "pending", "updated_at": "2026-01-15T10:30:00Z"}Dataset export not found