@ishaan-jaff I quickly skimmed through the code and tested the current version of litellm (I personally believe that the documentation at Provider specific Wildcard routing is not detailed enough; developers must browse the source code to get a general understanding of the scope of this functionality). I found that whether setting model to * or {provider}/*, a corresponding provider API key must be set in order for litellm to list all models that the provider is expected to offer. However, this does not meet the requirement I mentioned earlier (I apologize again for not being more detailed in my question).

What I hope to achieve is to connect one litellm to another litellm and, after configuring it similarly to *, be able to obtain and display all available models listed in model_list using a request to /v1/models, rather than having to manually input each model into the configuration file one by one.

Originally posted by @changchiyou in #6948 (reply in thread)