GET
/
eval-runs
{
  "data": [
    {
      "id": "a03fa2f4-900d-482d-afe0-470d4cd8d1f4",
      "agent_id": "basic-agent",
      "model_id": "gpt-4o",
      "model_provider": "OpenAI",
      "name": "Test ",
      "eval_type": "reliability",
      "eval_data": {
        "eval_status": "PASSED",
        "failed_tool_calls": [],
        "passed_tool_calls": [
          "multiply"
        ]
      },
      "eval_input": {
        "expected_tool_calls": [
          "multiply"
        ]
      },
      "created_at": "2025-08-27T15:41:59Z",
      "updated_at": "2025-08-27T15:41:59Z"
    }
  ]
}

Headers

​
authorization
string | null

Query Parameters

​
agent_id
string | null

Agent ID

​
team_id
string | null

Team ID

​
workflow_id
string | null

Workflow ID

​
model_id
string | null

Model ID

​
type
enum<string> | null

Filter type

Available options:
agent,
team,
workflow
​
limit
integer | null
default:20

Number of eval runs to return

​
page
integer | null
default:1

Page number

​
sort_by
string | null
default:created_at

Field to sort by

​
sort_order
enum<string> | null
default:desc

Sort order (asc or desc)

Available options:
asc,
desc
​
db_id
string | null

The ID of the database to use

​
eval_types
string | null

Comma-separated eval types (accuracy,performance,reliability)

Response

Evaluation runs retrieved successfully

The response is of type object.