Skip to main content
POST
Run a bounded web agent
Start an asynchronous agent task for one public URL. Send url and prompt, then poll GET /v1/web/jobs/. The agent is restricted to the supplied URL, uses low effort, disables data exchange, and stops after 25 provider credits. Creation costs 25 SocialQuery credits; lifecycle reads are free. Results are populated only on completion; failed jobs may include explicitly incomplete partial data. Spark 1 model names are currently provider aliases for Spark 2; requested_model and the actual model are reported separately. Job metadata is retained for 24 hours and belongs to the authenticated account. Use an Idempotency-Key to avoid duplicate submissions.

Authorizations

x-api-key
string
header
required

Headers

Cache-Control
string
Idempotency-Key
string
X-Max-Credits
integer

Optional nonnegative integer cap on the maximum request hold. A live request whose hold exceeds this cap returns 422 CREDIT_BUDGET_EXCEEDED before spending. Metered holds use the requested limit; cache hits and successful idempotent replays cost zero.

Required range: x >= 0

Body

application/json
url
string<uri>
required
prompt
string
required
Required string length: 1 - 10000
model
enum<string>
default:spark-1-mini
Available options:
spark-1-mini,
spark-1-pro

Response

Request completed. Interpret data using the selected resource contract.

success
boolean
required
platform
string
required
endpoint
string
required
credits_used
integer
required
Required range: x >= 0
credits_remaining
integer | null
required
request_id
string
required
cached
boolean
required
data
object
required

The selected operation determines the resource fields in this object. Source data can omit a metric or report it as null.