v4

latestOpenAPI 3.1.02026-08-01207318738.7 KB

AI Eval

Get an eval run

Get an eval run with every per-prompt result row, including the underlying agentic job state and any scoring data.

get/api/v1/ai/eval/runs/{runId}

Path parameters

runIdstring uuid required

The unique identifier of the eval run.

Example:660e8400-e29b-41d4-a716-446655440001

The unique identifier of the eval run.

Response

Run detail.

Example response

{
  "run": {
    "created_at": "2025-01-15T10:00:00.000Z",
    "id": "660e8400-e29b-41d4-a716-446655440001",
    "model_id": "880e8400-e29b-41d4-a716-446655440003",
    "prompt_set_id": "550e8400-e29b-41d4-a716-446655440000",
    "repeat_count": 1,
    "results": [
      {
        "agentic_job": {
          "conversation_id": "770e8400-e29b-41d4-a716-446655440002",
          "id": "990e8400-e29b-41d4-a716-446655440004",
          "state": "COMPLETE"
        },
        "ai_timing_ms": 4121,
        "cost": 0.0021,
        "eval_prompt_id": "bb0e8400-e29b-41d4-a716-446655440007",
        "expectation": "The top product by revenue should be Aniseed Syrup.",
        "id": "aa0e8400-e29b-41d4-a716-446655440005",
        "prompt": "What are the top 5 products by revenue?",
        "query_count": 4,
        "query_timing_ms": 1800,
        "score": 0.9,
        "scoring_cost": 0.0004,
        "timing_ms": 4321,
        "tool_timing_ms": 200
      }
    ],
    "run_number": 3,
    "status": "RUNNING"
  }
}