v20

latestOpenAPI 3.1.0MITraw.githubusercontent.com2026-08-037924117.4 KB
Inference v2

Async

Asynchronous inference — returns job_id immediately for polling.

post/v1/inference/async

Request body

modelstring required

Model name or HuggingFace repo

max_tokensinteger
temperaturenumber
streamboolean

Stream response via SSE

Response

Successful Response

{"stackTrail":"paths:/v1/inference/async:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}