List evals

List evaluations for a project.

GET /evals

List evals

cURL

curl --request GET \
  --url https://api.openai.com/v1/evals \
  --header 'Authorization: Bearer <token>'

200

{
  "object": "list",
  "data": [
    {
      "object": "eval",
      "id": "<string>",
      "name": "Chatbot effectiveness Evaluation",
      "data_source_config": {
        "type": "custom",
        "schema": "{\n  \"type\": \"object\",\n  \"properties\": {\n    \"item\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"label\": {\"type\": \"string\"},\n      },\n      \"required\": [\"label\"]\n    }\n  },\n  \"required\": [\"item\"]\n}\n"
      },
      "testing_criteria": "eval",
      "created_at": 123,
      "metadata": {},
      "share_with_openai": true
    }
  ],
  "first_id": "<string>",
  "last_id": "<string>",
  "has_more": true
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

after · string

Identifier for the last eval from the previous pagination request.

limit · integer · default: 20

Number of evals to retrieve.

order · enum<string> · default: asc

Sort order for evals by timestamp. Use asc for ascending order or desc for descending order.

Available options: asc, desc

order_by · enum<string> · default: created_at

Evals can be ordered by creation time or last updated time. Use created_at for creation time or updated_at for last updated time.

Available options: created_at, updated_at

Response

200 - application/json

A list of evals

An object representing a list of evals.

object · enum<string> · default: list · required

The type of this object. It is always set to "list".

Available options: list

data · Eval · object[] · required

An array of eval objects.

Show child attributes

first_id · string · required

The identifier of the first eval in the data array.

last_id · string · required

The identifier of the last eval in the data array.

has_more · boolean · required

Indicates whether there are more evals available.