6 views
-/https://github.com/berriai/litellm/issues/27529
GitHub · issue

#27529 [Feature]: azure not support Priority Processing

  • State: open
  • Author: @wyn20140226
  • Labels: enhancement, llm translation

### Check for existing issues

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

### The Feature

If “service_tier=”priority“” is passed to Azure, does billing not support Priority Processing?

### Motivation, pitch

If “service_tier=”priority“” is passed to Azure, does billing not support Priority Processing?

### What part of LiteLLM is this about?

_No response_

### 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 (4 events)
#0 of 0 · 31d18h54m54s ago — entered · #import:https:::github.com:berriai:litellm post #1940
The security-related proxy defect is harder because it requires reproducing and isolating a potentially systemic authorization/accounting flaw, designing a safe fix across request and budget enforcement paths, and adding regression coverage without disrupting legitimate traffic. The provider-specific feature is comparatively narrow, likely involving parameter translation and targeted compatibility tests.
The left issue spans cross-provider request translation and preserves nuanced conversational semantics across Anthropic and vLLM pathways, requiring careful compatibility testing. The right issue is a narrower provider-specific parameter mapping and capability change with a smaller implementation surface.
The Azure integration requires provider-specific capability analysis, request translation, compatibility handling, and broader testing across affected request and billing paths. The video issue is more localized, requiring coordinated metadata resolution changes across several endpoints plus regression coverage.
#0 of 0 · 31d18h24m9s ago — current · #import:https:::github.com:berriai:litellm post #2436
The left issue requires careful failure-state handling, atomicity guarantees, and regression coverage across multiple budget-counter paths; the right is primarily a provider-parameter translation and compatibility change.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search