Skip to main content
GET
/
v1
/
prediction
/
{id}
Get Model Prediction
curl --request GET \
  --url https://api.eachlabs.ai/v1/prediction/{id} \
  --header 'X-API-Key: <api-key>'
{
  "id": "abc123-def456-ghi789",
  "input": {
    "prompt": "A beautiful sunset over the ocean with vibrant colors",
    "aspect_ratio": "16:9"
  },
  "status": "success",
  "output": "https://storage.example.com/predictions/abc123/image.jpg",
  "logs": null,
  "metrics": {
    "predict_time": 12.5,
    "cost": 0.05
  },
  "urls": {
    "cancel": "https://api.eachlabs.ai/v1/prediction/abc123-def456-ghi789/cancel",
    "get": "https://api.eachlabs.ai/v1/prediction/abc123-def456-ghi789"
  }
}

Authorizations

​
X-API-Key
string
header
required

API key for authentication

Path Parameters

​
id
string
required

Prediction ID

Response

Prediction retrieved successfully

​
id
string

Unique prediction identifier

Example:

"abc123-def456-ghi789"

​
input
object

Input parameters used for the prediction

Example:
{
  "prompt": "A beautiful sunset over the ocean with vibrant colors",
  "aspect_ratio": "16:9"
}
​
status
enum<string>

Current status of the prediction. starting and processing are non-terminal. success, failed, and cancelled are terminal.

Available options:
starting,
processing,
success,
failed,
cancelled
Example:

"success"

​
output

Prediction output (type varies based on model)

Example:

"https://storage.example.com/predictions/abc123/image.jpg"

​
logs
string | null

Execution logs from the prediction

Example:

null

​
metrics
object

Performance and cost metrics

​
urls
object

Related API endpoints

Last modified on June 17, 2026