Api Inference Create Endpoint

Create a serverless inference endpoint.

If min_workers >= 1, a worker container is provisioned immediately. Billing is real-time from credits (per-second compute + per-token inference).

post/api/v2/inference/endpoints

Request body

model_namestring required

gpu_typestring

regionstring

docker_imagestring

min_workersinteger

max_workersinteger

max_batch_sizeinteger

max_concurrentinteger

scaledown_window_secinteger

modestring

health_endpointstring

api_formatstring

Successful Response

{"stackTrail":"paths:/api/v2/inference/endpoints:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}