Run a specific workflow version

Run one pinned version of an Optimization Studio workflow synchronously and return its output. Use this when a caller must keep hitting the same version as the workflow is edited. The body is the workflow’s own input fields, named as its entry node names them.

POST /api/v1/workflows/{workflowId}/{versionId}/run

Run a specific workflow version

Python

import requests

url = "https://app.langwatch.ai/api/v1/workflows/{workflowId}/{versionId}/run"

payload = {}
headers = {
    "X-Auth-Token": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

200

{
  "status": "idle",
  "result": {},
  "trace_id": "<string>",
  "nodes": {},
  "total_cost": 123,
  "duration_ms": 123,
  "error": {
    "type": "<string>",
    "message": "<string>",
    "node_id": "<string>",
    "traceback": "<string>"
  }
}

Authorizations

X-Auth-Token · string · header · required

Project API key for sending traces and accessing project-scoped resources. Format: sk-lw-... (no underscore). Obtain one by creating a project via the Admin API or the LangWatch UI.

Path Parameters

workflowId · string · required

Minimum string length: 1

versionId · string · required

Minimum string length: 1

Body

application/json

The workflow's input fields, named as the workflow's entry node names them

{key} · any

Response

200 - application/json

Success

status · enum<string> · required

Available options: idle, waiting, running, success, error, skipped

result · object | null

Show child attributes

trace_id · string

nodes · object

Show child attributes

total_cost · number

duration_ms · number

error · object

Show child attributes