Retrieve run step

Retrieves a run step.

GET /threads/{thread_id}/runs/{run_id}/steps/{step_id}

Retrieve run step

cURL

curl --request GET \
  --url https://api.openai.com/v1/threads/{thread_id}/runs/{run_id}/steps/{step_id} \
  --header 'Authorization: Bearer <token>'

200

{
  "id": "<string>",
  "object": "thread.run.step",
  "created_at": 123,
  "assistant_id": "<string>",
  "thread_id": "<string>",
  "run_id": "<string>",
  "type": "message_creation",
  "status": "in_progress",
  "step_details": {
    "type": "message_creation",
    "message_creation": {
      "message_id": "<string>"
    }
  },
  "last_error": {
    "code": "server_error",
    "message": "<string>"
  },
  "expired_at": 123,
  "cancelled_at": 123,
  "failed_at": 123,
  "completed_at": 123,
  "metadata": {},
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}

Authorizations

Authorization · string · header · required

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

Path Parameters

thread_id · string · required

The ID of the thread to which the run and run step belongs.

run_id · string · required

The ID of the run to which the run step belongs.

step_id · string · required

The ID of the run step to retrieve.

Query Parameters

include[] · enum<string>[]

A list of additional fields to include in the response. Currently the only supported value is step_details.tool_calls[*].file_search.results[*].content to fetch the file search result content.

See the file search tool documentation for more information.

Available options: step_details.tool_calls[*].file_search.results[*].content

Response

200 - application/json

OK

Represents a step in execution of a run.

id · string · required

The identifier of the run step, which can be referenced in API endpoints.

object · enum<string> · required

The object type, which is always thread.run.step.

Available options: thread.run.step

created_at · integer · required

The Unix timestamp (in seconds) for when the run step was created.

assistant_id · string · required

The ID of the assistant associated with the run step.

thread_id · string · required

The ID of the thread that was run.

run_id · string · required

The ID of the run that this run step is a part of.

type · enum<string> · required

The type of run step, which can be either message_creation or tool_calls.

Available options: message_creation, tool_calls

status · enum<string> · required

The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.

Available options: in_progress, cancelled, failed, completed, expired

step_details · Message creation · object · required

Details of the message creation by the run step.

Message creation

Tool calls

Show child attributes

last_error · object · required

The last error associated with this run step. Will be null if there are no errors.

Show child attributes

expired_at · integer | null · required

The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.

cancelled_at · integer | null · required

The Unix timestamp (in seconds) for when the run step was cancelled.

failed_at · integer | null · required

The Unix timestamp (in seconds) for when the run step failed.

completed_at · integer | null · required

The Unix timestamp (in seconds) for when the run step completed.

metadata · object · required

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Show child attributes

usage · object · required

Usage statistics related to the run step. This value will be null while the run step's status is in_progress.

Show child attributes