Dedicated Models

Deploy Rebalance Cancel

Changed on

Stop an in-flight GPU pool rebalance; instances already moved stay, and both deployments keep min/max instances fixed at their current counts.

post/deploy/{deploy_id}/rebalance/cancel

Request

  • Base URL: https://api.deepinfra.com
  • URL: https://api.deepinfra.com/deploy/{deploy_id}/rebalance/cancel
  • Auth: HTTP bearer

Path parameters

deploy_idstring required

Headers

xi-api-keystring nullable
x-api-keystring nullable

Request body

replace_idstring nullable

Rebalance to cancel; defaults to the active one.

Response

Successful Response

replace_idstring required

Id of the cancelled rebalance.

placedinteger required

Target instances delivered before the cancel.

countinteger required

Target instances requested.

Changes