SCscaleapi

Update Model Endpoint

Changed on

Updates the Model endpoint.

put/v1/model-endpoints/{model_endpoint_id}

Request

  • The document declares no server URL.
  • Auth
    • HTTP basic
    • or OAuth 2
      Password
      Token URL: token

Path parameters

model_endpoint_idstring required

Request body

model_bundle_idstring nullable
metadataobject nullable
post_inference_hooksstring[] nullable
gpusinteger nullable
gpu_type'nvidia-tesla-t4' | 'nvidia-ampere-a10' | 'nvidia-ampere-a100' | 'nvidia-ampere-a100e' | 'nvidia-hopper-h100' | 'nvidia-hopper-h100-1g20gb' | 'nvidia-hopper-h100-3g40gb'

Lists allowed GPU types for Launch.

optimize_costsboolean nullable
min_workersinteger nullable
max_workersinteger nullable
per_workerinteger nullable
concurrent_requests_per_workerinteger nullable
forwarder_max_concurrencyinteger nullable

Max in-flight requests admitted by the HTTP forwarder container, independent of per_worker / autoscaling. When None (default), the forwarder inherits its --concurrency flag from per_worker (current behavior). Upper bound matches LIRA's FORWARDER_MAX_CONCURRENCY_LIMIT.

labelsobject nullable
prewarmboolean nullable
high_priorityboolean nullable
billing_tagsobject nullable
default_callback_urlstring nullable
public_inferenceboolean nullable
queue_message_timeout_secondsinteger nullable

For async endpoints, the queue message visibility/lock timeout in seconds. Controls how long a worker has to process a message before it becomes visible again (SQS VisibilityTimeout / ASB lock_duration). Note: Azure Service Bus has a maximum of 300 seconds; values above this will be clamped.

task_expires_secondsinteger nullable

For async endpoints, how long a task can wait in queue before expiring (in seconds). Default: 86400 (24 hours).

Response

Successful Response

endpoint_creation_task_idstring required

Changes

  • ea1812999de9Revision changes
    • warning

      removed the request property

    • warning

      removed the request property

    • warning

      removed the request property

    • warning

      removed the optional property // from the response with the status

    • warning

      removed the optional property // from the response with the status