10 views
-/https://github.com/berriai/litellm/issues/32557
GitHub · issue

#32557 [Feature]: Can we have a stealth model to avoid sending client metadata?

  • State: open
  • Author: @unrealandychan
  • Labels: enhancement, proxy, llm translation, claude code

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### The Feature

I think OpenAI and Anthropic are collecting metadata from the client of litellm, for one example I am having a business trip in Hong Kong , and my litellm is located in Singapore, also my id is under Singapore. But I received a warning that the location is not authorise to use Claude Code. This is strange.

I hope we can have a mode that make Litellm as a stealth proxy.

### Motivation, pitch

This is for all the user in the world, I know from the T&C that specify some of the location is banned from the LLM access, but their flag are too strict, and as a proxy, litellm should have a feature to fix that.

### What part of LiteLLM is this about?

Proxy

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

Yes

### Twitter / LinkedIn details

_No response_

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (1 events)
#0 of 0 · 31d17h54m26s ago — entered · #import:https:::github.com:berriai:litellm post #3173
Model omitted braces; inferred difficulty from issue scope and surface area.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search