v1

latestOpenAPI 3.1.0MIT2026-07-13174391.2 KB
Reflex

Fetch async batch results

Return the status block plus a results array — one entry per row, keyed by your id, as inline JSON. A row is completed (carries predictions), failed (carries an error), or still pending if you fetch before the batch finishes.

get/v1/reflex/asynchronous_batches/{batch_id}/results

Path parameters

batch_idstring required

Response

Batch results.

idstring
objectstring
statusstring

Example response

{
  "id": "rbatch-a1b2c3d4-5e6f-7a8b-9c0d-1e2f3a4b5c6d",
  "object": "reflex.batch.results",
  "status": "completed",
  "request_counts": {
    "total": 2,
    "completed": 2
  },
  "results": [
    {
      "id": "row-1",
      "status": "completed",
      "predictions": [
        {
          "model": "jailbreak",
          "mode": "single_label",
          "classes": [
            {
              "label": "jailbreak",
              "score": 0.98,
              "selected": true
            }
          ],
          "error": "model not ready"
        }
      ],
      "error": {
        "type": "input_too_long",
        "message": "text exceeds the token limit"
      }
    }
  ]
}