v20

latestOpenAPI 3.1.0MITraw.githubusercontent.com2026-08-037924117.4 KB

Inference

Submit

Submit a serverless inference request.

Schedules a short-lived GPU job that runs the specified model on the provided inputs. Returns a job_id to poll for results.

post/api/inference

modelstring required

Model name or HuggingFace repo (e.g. 'distilbert-base-uncased-finetuned-sst-2-english')

gpu_modelstring

Preferred GPU model or 'any'

max_tokensinteger

temperaturenumber

timeout_secinteger

Successful Response

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