9 views
-/https://github.com/berriai/litellm/issues/26679
GitHub · issue

#26679 [Feature]: Create separate OpenAPI specs for Management API and LLM APIs

  • State: open
  • Author: @AccessRichH
  • Labels: enhancement, proxy, llm translation, stale

### Check for existing issues

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

### The Feature

I would like LiteLLM to provide a distinction between the Management API and the LLM API, via the OpenAPI spec.

This is particularly useful in the Multi-Region with Global Control plane model.

### Motivation, pitch

Context: - The LiteLLM OpenAPI Spec is huge at around 700ish operations. - We run LiteLLM behind Azure API Management

Most of my DEV teams will only need access to the LLM API subset of those operations, so I'd like to be able to expose documentation to them at that level, to reduce their context to something more appropriate.

Additionally, this would make a material difference in how I expose the LLM APIs via APIM, as I can logically separate and control the LLM API and the underlying regional workers without replicating huge sections of the API unnecessarily.

### 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?

No

### 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 · 31d18h18m13s ago — entered · #import:https:::github.com:berriai:litellm post #2558
The left requires broader API-surface partitioning, schema ownership, compatibility handling, and integration across proxy exposure paths. The right is a more localized pricing-state consistency fix with targeted regression coverage.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search