Run steps (Deprecated) - Alibaba Cloud Model Studio

The Assistant API is being deprecated. Migrate to the Responses API as an alternative. The Responses API includes multiple built-in tools and supports multi-turn context management.

List run steps

Returns a list of all steps for a run task.

Sample request

HTTP
SDK

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/threads/thread_cc2a3e9d-436b-482b-91c5-377e0f376506/runs/run_3de634fa-75d4-4370-adcf-92ba2a60c396/steps?limit=20&order=asc' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

import dashscope
from dashscope import Steps
import os

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
steps = Steps.list(
    'run_id',
    # We recommend setting the API key as an environment variable. If not, replace `api_key=os.getenv(...)` with `api_key="your_api_key"`.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    thread_id='thread_id',
    limit=20
)

Request body

Parameter Name	Type	Required	Default	Description
run_id	string	Yes		The ID of the Run for which you want to list the steps.
thread_id	string	Yes		The ID of the Thread.
limit	integer	No	None	The number of running steps to retrieve. The default is None. A value of None uses the server-side default value.
order	string	No	None	The order in which to sort the results based on the created_at field. You can set this parameter to asc (ascending) or desc (descending). The default value is None, which indicates that the server-side default sorting method is used.
after	string	No	None	ID of the run step to use as a cursor for pagination. When provided, returns the page of results immediately after this step.
before	string	No	None	ID of the run step to use as a cursor for pagination. When provided, returns the page of results immediately before this step.
workspace	string	Yes	None	The Workspace ID for Alibaba Cloud Model Studio is required only if the `api_key` is an API key for a sub-workspace.
api_key	string	Yes	None	The API Key of Model Studio. We recommend that you configure the API Key as an environment variable.

Sample response

{
    "object": "list",
    "data": [
        {
            "id": "[REDACTED]",
            "object": "thread.run.step",
            "created_at": 1711517599333,
            "assistant_id": "[REDACTED]",
            "thread_id": "[REDACTED]",
            "run_id": "[REDACTED]",
            "type": "message_creation",
            "status": "completed",
            "step_details": {
                "type": "message_creation",
                "message_creation": {
                    "message_id": "[REDACTED]"
                }
            },
            "last_error": {
                "code": "",
                "message": ""
            },
            "expired_at": 0,
            "cancelled_at": -1,
            "failed_at": -1,
            "completed_at": -1,
            "metadata": {},
            "usage": {}
        }
    ],
    "first_id": "[REDACTED]",
    "last_id": "[REDACTED]",
    "has_more": false,
    "request_id": "[REDACTED]"
}

Response body

A list of run step objects

Retrieve a run step

Sample request

HTTP
SDK

Sample code

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/threads/thread_cc2a3e9d-436b-482b-91c5-377e0f376506/runs/run_3de634fa-75d4-4370-adcf-92ba2a60c396/steps/step_4db180b5-d44a-4b12-9390-4307c6cb87a5' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Sample code

import dashscope
from dashscope import Steps
import os

dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

step = Steps.retrieve(
    'step_id',
    # We recommend setting the API key as an environment variable. If not, replace `api_key=os.getenv(...)` with `api_key="your_api_key"`.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    thread_id='thread_id',
    run_id='run_id'
)

Request body

Parameter name	Type	Required	Default	Description
step_id	string	Yes		The ID of the RunStep to retrieve.
thread_id	string	Yes		The ID of the Thread.
run_id	string	Yes		The ID of the Run.
workspace	string	Yes	None	The Workspace ID for Alibaba Cloud Model Studio is required only if you are using a sub-workspace API Key.
api_key	string	Yes	None	The API Key of Model Studio. We recommend that you configure the API Key as an environment variable.

Sample response

{
    "assistant_id": "[REDACTED]",
    "cancelled_at": null,
    "completed_at": 1735025124000,
    "created_at": 1735025123150,
    "expired_at": null,
    "failed_at": null,
    "id": "[REDACTED]",
    "last_error": null,
    "metadata": {},
    "object": "thread.run.step",
    "request_id": "[REDACTED]",
    "run_id": "[REDACTED]",
    "status": "completed",
    "step_details": {
        "message_creation": {
            "message_id": "[REDACTED]"
        },
        "type": "message_creation"
    },
    "thread_id": "[REDACTED]",
    "type": "message_creation",
    "usage": null
}

Response body

The run step object that matches the specified ID.

Run step object

Represents a step in the execution process of a run.

Object example

{
  "id": "[REDACTED]",
  "assistant_id": "[REDACTED]",
  "cancelled_at": null,
  "completed_at": 1678886400,
  "created_at": 1678886300,
  "expired_at": null,
  "failed_at": null,
  "last_error": null,
  "metadata": {
    "user_id": "[REDACTED]",
    "context": "order_processing"
  },
  "object": "thread.run.step",
  "run_id": "[REDACTED]",
  "status": "completed",
  "step_details": {
    "type": "message_creation",
    "message_creation": {
      "message_id": "[REDACTED]"
    }
  },
  "thread_id": "[REDACTED]",
  "type": "message_creation",
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Object attributes

Parameter Name	Type	Description
id	string	The unique identifier of the run step, which can be referenced in API endpoints.
assistant_id	string	The ID of the assistant associated with this run step.
cancelled_at	integer	The 13-digit UNIX timestamp (in milliseconds) when the run step was canceled.
completed_at	integer	The 13-digit UNIX timestamp (in milliseconds) when the run step was completed.
created_at	integer	The 13-digit UNIX timestamp (in milliseconds) when the run step was created.
expired_at	integer	The 13-digit UNIX timestamp (in milliseconds) when the run step expired. If the parent run has expired, the step is also considered expired.
failed_at	integer	The 13-digit UNIX timestamp (in milliseconds) when the run step failed.
last_error	object	The last error associated with this run step. This parameter is null if no error occurred.
metadata	map	A set of up to 16 key-value pairs that can be attached to the object. This is used to store additional information about the object in a structured format. The maximum length of a key is 64 characters and the maximum length of a value is 512 characters.
object	string	The object type, which is always thread.run.step.
run_id	string	The ID of the run to which this run step belongs.
status	string	The status of the run step. Valid values: in_progress, cancelled, failed, completed, or expired.
step_details	object	The details of the run step.
thread_id	string	The ID of the running thread.
type	string	The type of the run step. Valid values: message_creation or tool_calls.
usage	object	Resource usage statistics.
status_code	integer	The HTTP status code. Note: This parameter is used for internal processing. In most cases, you do not need to concern yourself with this parameter.

Error codes

If a call fails and returned an error message, see Error codes for troubleshooting.

​List run steps

​Sample request

​Request body

​Sample response

​Response body

​Retrieve a run step

​Sample request

​Request body

​Sample response

​Response body

​Run step object

​Object example

​Object attributes

​Error codes

List run steps

Sample request

Request body

Sample response

Response body

Retrieve a run step

Sample request

Request body

Sample response

Response body

Run step object

Object example

Object attributes

Error codes