6 views
-/https://github.com/berriai/litellm/issues/32628
GitHub · issue

#32628 [Feature]: Add support for Cohere Command A+ in Azure

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

### Check for existing issues

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

### The Feature

Add support for Cohere Command A+ in Azure:

https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-cohere-command-a-in-foundry/4530376

### Motivation, pitch

New model support

### 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_

Open on GitHub

GitHub resolver

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

Refresh page
vote history (5 events)
#0 of 0 · 31d19h14m33s ago — entered · #import:https:::github.com:berriai:litellm post #1737
-/https://github.com/berriai/litellm/issues/255503:1-/https://github.com/berriai/litellm/issues/32628⭐
The right-side task is harder because it affects shared proxy authorization and model-discovery behavior, requiring careful compatibility analysis and regression coverage across key types and filtering paths. The left-side task is comparatively bounded to provider/model registration and translation validation.
#0 of 0 · 31d18h27m8s ago · #import:https:::github.com:berriai:litellm post #2500
-/https://github.com/berriai/litellm/issues/252343:1-/https://github.com/berriai/litellm/issues/32628⭐
Cross-layer time semantics require coordinated database, backend query, UI, migration/backward-compatibility, and regression-test work, with substantial risk around existing timestamp data. The other task is more narrowly scoped to provider/model registration and translation coverage with focused tests.
#0 of 0 · 31d18h8m13s ago · #import:https:::github.com:berriai:litellm post #2821
-/https://github.com/berriai/litellm/issues/32628⭐3:1-/https://github.com/berriai/litellm/issues/25940
The right-side change spans provider integration, model mapping, Azure-specific request/response behavior, and compatibility testing. The left-side work is comparatively localized to diagnosing and guarding a callback regression.
#0 of 0 · 31d18h4m7s ago · #import:https:::github.com:berriai:litellm post #2894
-/https://github.com/berriai/litellm/issues/32628⭐3:1-/https://github.com/berriai/litellm/issues/34297
The harder task spans provider-specific model translation, Azure integration behavior, compatibility handling, and broader test coverage. The easier task is primarily a localized frontend form addition with limited end-to-end payload verification.
#0 of 0 · 31d17h54m5s ago — current · #import:https:::github.com:berriai:litellm post #3072
-/https://github.com/berriai/litellm/issues/32628⭐2:1-/https://github.com/berriai/litellm/issues/31867
The model-integration work is harder because it may require provider-specific request/response handling, deployment and naming logic, capability mapping, and broader compatibility tests. The metadata-forwarding fix is narrower, centered on preserving existing context across one transformation boundary with regression coverage.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search