Stop a generation that has not finished, and refund it. Only where its provider can really stop it (today: models that run on Replicate); otherwise 409 not_cancelable and it finishes on its own.

post/v1/generations/{id}/cancel

Request

  • Base URL: https://api.lumeta.ai
  • URL: https://api.lumeta.ai/v1/generations/{id}/cancel
  • Auth: HTTP bearer

Path parameters

idstring required

The public id (gen_<n>, file_<n>, shelf_<n>, hook_<n>) or its number.

Response

OK

idstring
status'queued' | 'processing' | 'succeeded' | 'failed'
status_messagestring nullable

While status is queued or processing, one plain sentence on what the generation is waiting on, when there is a long wait worth telling the person about (today: Seedance clearing new face photos, which can take several minutes, a slow hand-over to Seedance, or the safety check after Seedance did not answer). It changes as the wait moves on, and is null otherwise and once the generation has finished. Show it as it is.

projectstring nullable
inputobject
textstring nullable

The words of a model that answers in text rather than a file, such as Speech-to-Text's transcript (its outputs is empty); null otherwise.

credits_chargedinteger

What was charged; a refunded failure reads 0.

origin'web' | 'api' | 'mcp' | 'cli'
request_idstring nullable
created_atstring
completed_in_secondsnumber nullable
credits_remaininginteger

On POST /v1/generations only.

cap_remaininginteger nullable

Changes

No recorded changes to this operation across all 1 revision of this API.