v20

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

Sync

Synchronous inference endpoint (OpenAI-compatible path).

Submits an inference request and polls for results up to 30 seconds. If stream=true, returns SSE text/event-stream with token deltas.

post/v1/inference

Request body

modelstring required

Model name or HuggingFace repo

max_tokensinteger
temperaturenumber
streamboolean

Stream response via SSE

Response

Successful Response

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