OpenAI Inference Proxy POST

View as Markdown
Proxy requests to OpenAI-compatible inference endpoints. All inference requests must resolve to a `VirtualModel`. The platform's provider reconciler auto-creates an implicit `autoprovisioned` VirtualModel for every served model entity (named after the entity, with `default_model_entity` set to the entity ref) so this is the typical case; operators can also create custom VirtualModels for routing, plugin chains, LoRA escape-hatches, etc. Requests for which no VirtualModel can be found return `404`.

Path parameters

workspacestringRequired
trailing_uristringRequired

Request

This endpoint expects a map from strings to any.

Response

Proxy POST request to OpenAI-compatible endpoint

Errors

422
Unprocessable Entity Error