Skip to main content
POST
/
v2
/
tasks
/
{task_id}
/
trigger
Trigger a task run
curl --request POST \
  --url https://api.arize.com/v2/tasks/{task_id}/trigger \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "data_start_time": "2026-03-01T00:00:00Z",
  "data_end_time": "2026-03-07T00:00:00Z",
  "max_spans": 5000,
  "override_evaluations": false
}
'
{
  "id": "VGFza1J1bjo5OTpxUndY",
  "task_id": "T25saW5lVGFzazo0NTpxUndY",
  "status": "pending",
  "run_started_at": null,
  "run_finished_at": null,
  "data_start_time": "2026-03-01T00:00:00.000Z",
  "data_end_time": "2026-03-07T00:00:00.000Z",
  "num_successes": 0,
  "num_errors": 0,
  "num_skipped": 0,
  "created_at": "2026-03-07T10:30:00.000Z",
  "created_by_user_id": "VXNlcjoxOm5OYkM="
}

Authorizations

​
Authorization
string
header
required

Most Arize AI endpoints require authentication. For those endpoints that require authentication, include your API key in the request header using the format

Path Parameters

​
task_id
string
required

The task global ID (base64) A universally unique identifier

Example:

"RW50aXR5OjEyMzQ1"

Body

application/json

Body containing task run trigger parameters

​
data_start_time
string<date-time>

ISO 8601 start of the data window to evaluate.

​
data_end_time
string<date-time>

ISO 8601 end of the data window to evaluate. If omitted, defaults to now.

​
max_spans
integer

Maximum number of spans to process (default 10000).

Required range: x >= 1
​
override_evaluations
boolean

Whether to re-evaluate data that already has evaluation labels (default false).

​
experiment_ids
string[]

Experiment global IDs (base64) to run against. Only applicable for dataset-based tasks.

Response

Returns the created task run

A task run is an async job that executes the work defined on a task.

​
id
string
required

The unique identifier for the task run.

​
task_id
string
required

The parent task global ID (base64).

​
status
enum<string>
required

The current status of the run.

Available options:
pending,
running,
completed,
failed,
cancelled
​
run_started_at
string<date-time> | null
required

When the run started processing.

​
run_finished_at
string<date-time> | null
required

When the run finished processing.

​
data_start_time
string<date-time> | null
required

Start of the data window evaluated.

​
data_end_time
string<date-time> | null
required

End of the data window evaluated.

​
num_successes
integer
required

Number of successfully evaluated items.

​
num_errors
integer
required

Number of items that errored during evaluation.

​
num_skipped
integer
required

Number of items that were skipped.

​
created_at
string<date-time>
required

When the run was created.

​
created_by_user_id
string | null
required

The unique identifier for the user who triggered the run.