Submit a prediction job

Start an asynchronous segmentation job for a ready image.

Returns immediately with a job_id; the segmentation runs on a GPU worker. Poll GET /job/{job_id} until it is COMPLETED, then read the segmentation_id off that response. Starting a job counts against your plan’s monthly analysis quota (402 when exceeded). The image_id and model_id are org-scoped: an id outside your organization returns 404.

POST /api/v1/job/prediction

Submit a prediction job

cURL

curl --request POST \
  --url https://api.halfpagetechnologies.com/backend/api/v1/job/prediction \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model_id": "<string>",
  "image_id": "<string>"
}
'

200

{
  "job_id": "<string>",
  "reason": "<string>",
  "task_id": "<string>",
  "runpod_job_id": "<string>"
}

Authorizations

Authorization · string · header · required

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

Body

application/json

Run a model over one uploaded image. image_id must be ready and model_id must be one of the ids returned by GET /models.

model_id · string · required

Example:

"c0ffee00-1234-5678-9abc-def012345678"

image_id · string · required

Example:

"3fa85f64-5717-4562-b3fc-2c963f66afa6"

Response

200

application/json

Successful Response

The acknowledgement returned when a job is accepted onto the queue. status is submitted for a fresh job or skipped when an identical job is already running. Poll GET /job/{job_id} for progress.

status · enum<string> · required

Available options: submitted, skipped

job_id · string · required

reason · string | null

task_id · string | null

runpod_job_id · string | null