Skip to main content
GET
/
replicate
/
v1
/
predictions
/
{id}
cURL
PREDICTION_ID="<prediction_id>"

curl "https://api.cometapi.com/replicate/v1/predictions/$PREDICTION_ID" \
  -H "Authorization: Bearer $COMETAPI_KEY"
{
  "id": "<prediction_id>",
  "model": "black-forest-labs/flux-schnell",
  "status": "succeeded",
  "output": [
    "https://replicate.delivery/xezq/.../out-0.webp"
  ],
  "error": null
}
Use this endpoint after you already have a Replicate prediction id. It reports the current task state and returns output URLs when the prediction completes.

​
Check these fields first

  • status to see whether the prediction is still running or already finished
  • output for generated asset URLs
  • error for provider-side failures
  • metrics when you need execution timing or image-count details

​
Polling pattern

1

Create the prediction first

Start with Create a Replicate prediction.
2

Poll by prediction id

Keep querying until status becomes terminal and output is either populated or a provider error is returned.
3

Persist finished assets

Treat returned asset URLs as delivery URLs and move them into your own storage if you need long retention.

Authorizations

​
Authorization
string
header
required

Bearer token authentication. Use your CometAPI key.

Path Parameters

​
id
string
required

Prediction id returned by the create endpoint.

Response

200 - application/json

Current prediction state.

​
id
string
required
​
input
object
required
​
model
string
required
​
output
string[] | null
required
​
status
string
required
​
created_at
string
required
​
data_removed
boolean
required
​
logs
string
​
urls
object
​
error
string | null
​
metrics
object
​
version
string
​
started_at
string | null
​
completed_at
string | null