post
https://{fqdn}/apis/rackai.rackspace.com/v1alpha1/namespaces//inference//v1/chat/completions
Proxies an OpenAI-compatible chat-completion request to the engine
serving the named ModelDeployment. The request and response bodies are
defined by the engine (vLLM / NIM); only the common fields are shown
here. To target a loaded LoRA adapter, set model to the adapter's
served name.
Recent Requests
Log in to see full request history
| Time | Status | User Agent | |
|---|---|---|---|
Retrieving recent requests… | |||
Loading…
Unauthorized — no or invalid bearer token provided.
Not Found — the resource does not exist.