AAaabiro
Serverless (compat)

Create Endpoint

Changed on
post/api/v2/inference/endpoints

Request

  • Base URL
    https://xcelsior.ca
  • URL
    https://xcelsior.ca/api/v2/inference/endpoints
  • Auth
    HTTP bearer

Request body

namestring
modestring
managed_enginestring
model_namestring
model_refstring
image_refstring
docker_imagestring
source_typestring
source_refstring
source_ref_branchstring
gpu_typestring
gpu_tierstring
gpu_countinteger
regionstring
min_workersinteger
max_workersinteger
max_concurrencyinteger
idle_timeout_secinteger
scaledown_window_secinteger nullable
scaling_policy_typestring
scaling_policy_valueinteger
execution_modestring
queue_timeout_secinteger
startup_commandstring
http_portinteger
health_check_pathstring
health_endpointstring
cuda_versionstring
request_timeout_secinteger
max_request_bytesinteger
envobject
lora_adaptersobject[]

Response

Successful Response

unknown required

Changes

  • 016014e16810Revision changes
    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      the request property default value changed from 300 to 60

    • info

      the request property default value changed from 4 to 1

    • info

      the request property default value changed from 4 to 3

    • info

      the request property default value changed from 0 to 1

  • cbe3ad94235cRevision changes
    • warning

      the request property's max was set to 32.00

    • warning

      the request property's max was set to 32.00

    • warning

      the request property's min was set to 1.00

    • warning

      the request property's min was set to 0.00

    • warning

      removed the request property

    • warning

      removed the request property

    • warning

      removed the request property

    • info

      api operation id api_inference_create_endpoint_api_v2_inference_endpoints_post removed and replaced with api_inference_compat_create_endpoint_api_v2_inference_endpoints_post

    • info

      api tag Serverless (compat) added

    • info

      api tag Inference v2 removed

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      added the new optional request property

    • info

      the request property became optional

    • info

      the request property default value was added

    • info

      the request property default value changed from xcelsior/vllm:latest to

    • info

      the request property default value changed from /health to

    • info

      the request property default value changed from 3 to 4

    • info

      the request property default value changed from sync to preset

    • info

      the request property default value 300 was removed

    • info

      request property list-of-types was widened by adding types null to media type application/json