curl -X GET 'https://api.openai.com/v1/evals/eval-id/runs?after=example-after&limit=20&order=asc&status=queued' \
  -H "Authorization: Bearer $OPENAI_API_KEY"

# GET /evals/{eval_id}/runs (OpenAI API)
Base URL: https://api.openai.com/v1
Auth: Authorization; OpenAI API key; required.
Last verified: 2026-10-20

> Get eval runs

## Critical Gotchas
* The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
* Audio transcription uploads use multipart form data rather than a JSON request body.

## cURL
curl -X GET 'https://api.openai.com/v1/evals/eval-id/runs?after=example-after&limit=20&order=asc&status=queued' \
  -H "Authorization: Bearer $OPENAI_API_KEY"

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| eval_id | path | string | Yes | The ID of the evaluation to retrieve runs for. |
| after | query | string | No | Identifier for the last run from the previous pagination request. |
| limit | query | integer | No | Number of runs to retrieve. |
| order | query | string | No | Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for... |
| status | query | string | No | Filter runs by status. One of `queued` \| `in_progress` \| `failed` \| `compl... |

## Response example
{"object":"list","data":[{}]}

---
Need an API key? Get one at https://platform.openai.com/api-keys

GET

GET /evals/{eval_id}/runs — OpenAI API

OpenAI API key (required); https://api.openai.com/v1

OpenAI API

Get eval runs

Base URL: https://api.openai.com/v1
Auth: Authorization: Bearer <OPENAI_API_KEY>
Last verified: 2026-10-20 · upstream hash matched

Actions Try in browser→

Agents: curl -H "Accept: text/markdown" this URL
→ 271 tokens · Vary: Accept

Critical gotchas

The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.

Audio transcription uploads use multipart form data rather than a JSON request body.

cURL

curl -X GET 'https://api.openai.com/v1/evals/eval-id/runs?after=example-after&limit=20&order=asc&status=queued' \  -H "Authorization: Bearer $OPENAI_API_KEY"

Parameters

Name	In	Type	Required	Description
eval_id	path	string	Yes	The ID of the evaluation to retrieve runs for.
after	query	string	No	Identifier for the last run from the previous pagination request.
limit	query	integer	No	Number of runs to retrieve.
order	query	string	No	Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`.
status	query	string	No	Filter runs by status. One of `queued` \| `in_progress` \| `failed` \| `completed` \| `canceled`.

Response 200 OK

{
  "object": "list",
  "data": [
    {
      "object": "eval.run",
      "id": "string",
      "eval_id": "string",
      "status": "string",
      "model": "string",
      "name": "string",
      "created_at": 0,
      "report_url": "https://example.com",
      "result_counts": {
        "total": 0,
        "errored": 0,
        "failed": 0,
        "passed": 0
      },
      "per_model_usage": [
        {
          "model_name": "string",
          "invocation_count": 0,
          "prompt_tokens": 0,
          "completion_tokens": 0,
          "total_tokens": 0,
          "cached_tokens": 0
        }
      ],
      "per_testing_criteria_results": [
        {
          "testing_criteria": "string",
          "passed": 0,
          "failed": 0
        }
      ],
      "data_source": {
        "type": "jsonl",
        "source": {
          "type": "file_content",
          "content": [
            "[recursive or deeply nested schema]"
          ]
        }
      },
      "metadata": {},
      "error": {
        "code": "string",
        "message": "string"
      }
    }
  ],
  "first_id": "string",
  "last_id": "string",
  "has_more": true
}

Get a free OpenAI API key → sponsored

Affiliate link - we may earn a commission, at no extra cost to you.