openai/ prefix is how LiteLLM addresses an OpenAI-compatible third-party endpoint with a custom api_base; what follows the prefix is the catalog ID sent to Nito.
Proxy, in config.yaml:
litellm --config config.yaml and call the proxy with the bare model_name.
Privacy
Use a catalog ID, not an OpenAI name. For attested hardware use a:confidential variant; GET /v1/models lists their :confidential IDs. Encrypted needs client-side encryption and extra headers, which these frameworks do not add. See Privacy Levels.
Related
Framework Integrations
The shared pattern.
OpenAI Compatibility
What differs.
Privacy Levels
The four levels.

