inference
Successful extract work results may carry an aligned per-item error alongside partial data. Transport-level mixed failures retain generic batch behavior: the 200 response includes only successful work results.
post/v1/extract/{model}
Path parameters
modelstring required
Model id. Runtime route is Axum catch-all /v1/extract/{*model}; clients using this OpenAPI path template should percent-encode slashes in model ids, for example BAAI%2Fbge-m3.
Headers
X-SIE-MACHINE-PROFILEstring nullable
Preferred GPU or machine profile
X-SIE-Poolstring nullable
Explicit pool routing override
X-SIE-SDK-Versionstring nullable
Client SDK version for skew warnings
Request body
Response
Extract response