Skip to main content
POST
/
ml
/
projects
/
{id}
/
inference
Create inference request
curl --request POST \
  --url https://acusight.io/api/ml/projects/{id}/inference \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "image_ids": [
    123
  ],
  "model_version_id": 123,
  "confidence_threshold": 0.5,
  "iou_threshold": 0.5
}
'
{
  "data": {
    "applied_to_images": true,
    "completed_at": "<string>",
    "confidence_threshold": 123,
    "created_at": "<string>",
    "error_message": "<string>",
    "id": 123,
    "image_count": 123,
    "image_ids": [
      123
    ],
    "iou_threshold": 123,
    "model_version_id": 123,
    "project_id": 123,
    "request_type": "<string>",
    "results": [
      123
    ],
    "status": "<string>",
    "updated_at": "<string>"
  },
  "error": {
    "code": "<string>",
    "details": "<string>",
    "message": "<string>"
  },
  "meta": {
    "count": 123,
    "limit": 123,
    "offset": 123,
    "total": 123
  },
  "success": true
}

Authorizations

Authorization
string
header
required

JWT access token. Paste the token only; the Bearer prefix is added automatically.

Path Parameters

id
integer
required

Project ID

Body

application/json

Inference request payload

image_ids
integer[]
required
model_version_id
integer
required
request_type
enum<string>
required
Available options:
test,
batch,
auto-annotate
confidence_threshold
number
Required range: 0 <= x <= 1
iou_threshold
number
Required range: 0 <= x <= 1

Response

Inference request queued

data
object
error
object
meta
object
success
boolean