---
title: "Get evaluation run output items"
method: GET
path: "/openai/evals/{eval_id}/runs/{run_id}/output_items"
tags: ["Evals"]
---

# Get evaluation run output items

`GET /openai/evals/{eval_id}/runs/{run_id}/output_items`

Get a list of output items for an evaluation run.

## Path parameters

- `eval_id` string, required
- `run_id` string, required

## Query parameters

- `api-version` string, required
- `after` string
- `limit` integer
- `order` 'asc' | 'desc'
- `status` 'fail' | 'pass'

## Response `200`

The request has succeeded.

- object — The response data for a requested list of items.
  - `data` EvalRunOutputItem[], required — The requested list of items.
    - `object` 'eval.run.output_item', required — The type of the object. Always "eval.run.output_item".
    - `id` string, required — Unique identifier for the evaluation run output item.
    - `run_id` string, required — The identifier of the evaluation run associated with this output item.
    - `eval_id` string, required — The identifier of the evaluation group.
    - `created_at` integer, required — Unix timestamp (in seconds) when the evaluation run was created.
    - `status` string, required — The status of the evaluation run.
    - `datasource_item_id` integer, required
    - `datasource_item` object, required — Details of the input data source item.
    - `results` EvalRunOutputItemResult[], required — A list of grader results for this output item.
      - `name` string, required — The name of the grader.
      - `type` string — The grader type (for example, "string-check-grader").
      - `score` number, double, required
      - `passed` boolean, required — Whether the grader considered the output a pass.
      - `sample` object, nullable — Optional sample or intermediate data produced by the grader.
      - `metric` string — The name of the metric (e.g., "fluency", "f1_score").
      - `label` string — The label associated with the test criteria metric (e.g., "pass", "fail", "good", "bad").
      - `threshold` number, float — The threshold used to determine pass/fail for this test criteria, if it is numerical.
      - `reason` string — The reason for the test criteria metric.
      - `properties` object — Additional details about the test criteria metric.
    - `sample` OpenAIEvalRunOutputItemSample, required
      - `input` EvalRunOutputItemSampleInput[], required
        - `role` string, required
        - `content` string, required
        - `tool_calls` CompletionMessageToolCallChunk[], required — Tool calls made within the message, if any.
          - `id` string, required — The Id for the tool call.
          - `type` 'function', required — The type of tool call, which is always "function".
          - `function` FunctionToolCall — Details of a function tool call.
            - `name` string, required — The name of the function to call.
            - `arguments` string, required — The arguments to call the function with, as generated by the model in JSON format.
      - `output` EvalRunOutputItemSampleOutput[], required
        - `role` string
        - `content` string
        - `tool_calls` CompletionMessageToolCallChunk[], required — Tool calls made within the message, if any.
          - `id` string, required — The Id for the tool call.
          - `type` 'function', required — The type of tool call, which is always "function".
          - `function` FunctionToolCall — Details of a function tool call.
            - `name` string, required — The name of the function to call.
            - `arguments` string, required — The arguments to call the function with, as generated by the model in JSON format.
      - `finish_reason` string, required
      - `model` string, required
      - `usage` OpenAIEvalRunOutputItemSampleUsage, required
        - `total_tokens` integer, required
        - `completion_tokens` integer, required
        - `prompt_tokens` integer, required
        - `cached_tokens` integer, required
      - `error` OpenAIEvalApiError, required — An object representing an error response from the Eval API.
        - `code` string, required — The error code.
        - `message` string, required — The error message.
      - `temperature` number, double, required
      - `max_completion_tokens` integer, required
      - `top_p` number, double, required
      - `seed` integer, required
  - `first_id` string — The first ID represented in this list.
  - `last_id` string — The last ID represented in this list.
  - `has_more` boolean, required — A value indicating whether there are additional values available not captured in this list.

## Other responses

- `default` — An unexpected error response.

---

[API](https://skmtc.net/azure/apis/ai-azure-ai-projects.md) · [All operations](https://skmtc.net/azure/apis/ai-azure-ai-projects/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/azure/ai-azure-ai-projects/revisions/b52c14a89ea1/schema)